{"type":"models-filter","generated_at":"2026-06-22","source":"/api/v1/models.json","total":37,"count":37,"query":{"capability":[],"provider":[],"availability_status":[],"deprecated":null,"model_type":[],"tool_schema_format":[],"context_min":null,"max_input_price":null,"max_output_price":null,"free":null},"available_filters":["capability","provider","availability_status","deprecated","model_type","tool_schema_format","context_min","max_input_price","max_output_price","free"],"items":[{"slug":"claude-fable-5","id":"claude-fable-5","type":"model","title":"Claude Fable 5","description":"Anthropic's most capable widely released model. First public Mythos-class model, released under Project Glasswing safeguards. 80.3% SWE-bench Pro. 1M context, adaptive thinking always on.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-fable-5.md","html_url":"/models/claude-fable-5","api_url":"/api/v1/models/claude-fable-5.json","content_hash":"50bf0fc6d4e12fb88b4e4ea0b57092e673cfe4327b47f823292c57dde28adf2b","sha256":"50bf0fc6d4e12fb88b4e4ea0b57092e673cfe4327b47f823292c57dde28adf2b","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-fable-5","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","adaptive_thinking"],"availability_status":"available","deprecated":false,"tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"low","sources":[{"title":"Anthropic: Claude Fable 5 and Claude Mythos 5","url":"https://www.anthropic.com/news/claude-fable-5-mythos-5"},{"title":"Anthropic Claude models overview","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"TechCrunch: Anthropic releases Claude Fable 5","url":"https://techcrunch.com/2026/06/09/anthropic-released-claude-fable-5-its-most-powerful-model-publicly-days-after-warning-ai-is-getting-too-dangerous/"}],"benchmark_sources":[{"title":"Anthropic: Claude Fable 5 and Claude Mythos 5","url":"https://www.anthropic.com/news/claude-fable-5-mythos-5"},{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$10.00 / 1M tokens","output":"$50.00 / 1M tokens","input_per_1m":10,"output_per_1m":50,"currency":"USD","note":"Double Opus 4.8 pricing. Uses the Opus 4.7 tokenizer: the same text produces roughly 30% more tokens than pre-4.7 Claude models."},"benchmarks":{"reasoning":99,"coding":99,"math":97,"writing":97,"multilingual":92,"speed":60},"context_window":"1M tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image","frontier"],"website":"https://anthropic.com","release_date":"2026-06-09","relationships":{"links":[],"related":[{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-haiku-4.5","id":"claude-haiku-4.5","type":"model","title":"Claude Haiku 4.5","description":"Anthropic's fastest and most cost-efficient model. Matches Claude Sonnet 4's performance on coding and agent tasks while being dramatically faster and cheaper.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-haiku-4.5.md","html_url":"/models/claude-haiku-4.5","api_url":"/api/v1/models/claude-haiku-4.5.json","content_hash":"a0a41c619ec0381d9f0c8751c6e5fae6b01eaede2fd2cb10f1ae12075f77db9d","sha256":"a0a41c619ec0381d9f0c8751c6e5fae6b01eaede2fd2cb10f1ae12075f77db9d","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-haiku-4-5","knowledge_cutoff":"2025-02","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","extended_thinking"],"availability_status":"available","deprecated":false,"tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Anthropic Claude Haiku 4.5","url":"https://www.anthropic.com/claude/haiku"},{"title":"Anthropic Claude models overview","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"Anthropic API pricing","url":"https://platform.claude.com/docs/en/about-claude/pricing"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$1.00 / 1M tokens","output":"$5.00 / 1M tokens","input_per_1m":1,"output_per_1m":5,"currency":"USD","cache_read_per_1m":0.1,"cache_write_5m_per_1m":1.25,"cache_write_1h_per_1m":2,"batch_input_per_1m":0.5,"batch_output_per_1m":2.5},"benchmarks":{"reasoning":82,"coding":84,"math":80,"writing":83,"multilingual":80,"speed":95},"context_window":"200K tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2025-10-15","relationships":{"links":[],"related":[{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-opus-4.6","id":"claude-opus-4.6","type":"model","title":"Claude Opus 4.6","description":"Anthropic's most capable model and the first Opus-class model with a 1M token context window. Leads on coding benchmarks with 80.8% SWE-bench. Internal codename \"Fennec.\"","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-opus-4.6.md","html_url":"/models/claude-opus-4.6","api_url":"/api/v1/models/claude-opus-4.6.json","content_hash":"13f296a90d0cac19381aaedb208d033e57d9296e7093e0ce35be3b7c52487187","sha256":"13f296a90d0cac19381aaedb208d033e57d9296e7093e0ce35be3b7c52487187","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-opus-4-6","knowledge_cutoff":"2025-05","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","adaptive_thinking"],"availability_status":"legacy","deprecated":false,"superseded_by":"claude-opus-4.7","tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Anthropic Claude models overview","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"Anthropic API pricing","url":"https://platform.claude.com/docs/en/about-claude/pricing"},{"title":"Anthropic Transparency Hub","url":"https://www.anthropic.com/transparency/model-report"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$5.00 / 1M tokens","output":"$25.00 / 1M tokens","input_per_1m":5,"output_per_1m":25,"currency":"USD","cache_read_per_1m":0.5,"cache_write_5m_per_1m":6.25,"cache_write_1h_per_1m":10,"batch_input_per_1m":2.5,"batch_output_per_1m":12.5,"note":"Significantly cheaper than Opus 4.5"},"benchmarks":{"reasoning":96,"coding":97,"math":93,"writing":95,"multilingual":88,"speed":62},"context_window":"1M tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2026-02","relationships":{"links":[{"text":"Opus 4.8","href":"claude-opus-4.8.md","html_path":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","target_id":"claude-opus-4.8","target_type":"model","target_title":"Claude Opus 4.8"}],"related":[{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-opus-4.7","id":"claude-opus-4.7","type":"model","title":"Claude Opus 4.7","description":"Short-lived Opus generation between 4.6 and 4.8. Introduced the new tokenizer (~30% more tokens for the same text) and adaptive thinking. Superseded by Opus 4.8 after six weeks.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-opus-4.7.md","html_url":"/models/claude-opus-4.7","api_url":"/api/v1/models/claude-opus-4.7.json","content_hash":"93c27b75af9c5781cdb0951706a25b82707f44f629791a7346e7a83babeeb7c4","sha256":"93c27b75af9c5781cdb0951706a25b82707f44f629791a7346e7a83babeeb7c4","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-opus-4-7","knowledge_cutoff":"2026-01","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","adaptive_thinking"],"availability_status":"legacy","deprecated":false,"superseded_by":"claude-opus-4.8","tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Anthropic Claude models overview (legacy models)","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"Anthropic API pricing","url":"https://platform.claude.com/docs/en/about-claude/pricing"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$5.00 / 1M tokens","output":"$25.00 / 1M tokens","input_per_1m":5,"output_per_1m":25,"currency":"USD","note":"Same rate card as Opus 4.6 and 4.8, but the new tokenizer produces ~30% more tokens for the same text, raising effective costs by up to 35% versus Opus 4.6."},"benchmarks":{"reasoning":96,"coding":97,"math":93,"writing":95,"multilingual":88,"speed":62},"context_window":"1M tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image","legacy"],"website":"https://anthropic.com","release_date":"2026-04","relationships":{"links":[],"related":[{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-opus-4.8","id":"claude-opus-4.8","type":"model","title":"Claude Opus 4.8","description":"Anthropic's most capable Opus-tier model for complex reasoning and long-horizon agentic coding. 69.2% SWE-bench Pro, 1M context on by default, user-level effort control, adaptive thinking.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-opus-4.8.md","html_url":"/models/claude-opus-4.8","api_url":"/api/v1/models/claude-opus-4.8.json","content_hash":"431eef12425bd97d93c3ebeb8a01b57f09b4308252b133ef2251864f6a5d2078","sha256":"431eef12425bd97d93c3ebeb8a01b57f09b4308252b133ef2251864f6a5d2078","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-opus-4-8","knowledge_cutoff":"2026-01","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","adaptive_thinking"],"availability_status":"available","deprecated":false,"tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"low","sources":[{"title":"Anthropic Claude models overview","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"Anthropic API pricing","url":"https://platform.claude.com/docs/en/about-claude/pricing"},{"title":"Claude Opus 4.8","url":"https://www.anthropic.com/claude/opus"}],"benchmark_sources":[{"title":"Anthropic: Claude Fable 5 and Claude Mythos 5 (comparison table)","url":"https://www.anthropic.com/news/claude-fable-5-mythos-5"},{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$5.00 / 1M tokens","output":"$25.00 / 1M tokens","input_per_1m":5,"output_per_1m":25,"currency":"USD","cache_read_per_1m":0.5,"batch_input_per_1m":2.5,"batch_output_per_1m":12.5,"note":"Same rate card as Opus 4.5 through 4.7. Long-context input pricing applies over 200K tokens. Fast Mode (2.5x speed) is $10/$50. US-only inference is 1.1x. Minimum cacheable prompt is 1,024 tokens."},"benchmarks":{"reasoning":97,"coding":98,"math":94,"writing":96,"multilingual":89,"speed":65},"context_window":"1M tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2026-05-28","relationships":{"links":[],"related":[{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-sonnet-4.6","id":"claude-sonnet-4.6","type":"model","title":"Claude Sonnet 4.6","description":"The first Sonnet model preferred over a previous Opus in coding evaluations. Excellent balance of speed, quality, and cost with a full 1M token context window.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/claude-sonnet-4.6.md","html_url":"/models/claude-sonnet-4.6","api_url":"/api/v1/models/claude-sonnet-4.6.json","content_hash":"60288ca368e53486c5c918692401b592c6cb8bb5ccb2fda40296137b599a12cb","sha256":"60288ca368e53486c5c918692401b592c6cb8bb5ccb2fda40296137b599a12cb","provider":"Anthropic","model_type":"proprietary","api_model_id":"claude-sonnet-4-6","knowledge_cutoff":"2025-08","capabilities":["function_calling","vision","web_search","code_execution","structured_output","streaming","prompt_caching","tool_search","long_context","reasoning","extended_thinking","adaptive_thinking"],"availability_status":"available","deprecated":false,"tool_schema_format":"anthropic","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Anthropic Claude models overview","url":"https://platform.claude.com/docs/en/about-claude/models/overview"},{"title":"Anthropic API pricing","url":"https://platform.claude.com/docs/en/about-claude/pricing"},{"title":"Anthropic release notes","url":"https://platform.claude.com/docs/en/release-notes/overview"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$3.00 / 1M tokens","output":"$15.00 / 1M tokens","input_per_1m":3,"output_per_1m":15,"currency":"USD","cache_read_per_1m":0.3,"cache_write_5m_per_1m":3.75,"cache_write_1h_per_1m":6,"batch_input_per_1m":1.5,"batch_output_per_1m":7.5},"benchmarks":{"reasoning":91,"coding":93,"math":89,"writing":92,"multilingual":87,"speed":82},"context_window":"1M tokens","modality":["text","image"],"license":"Proprietary","tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2026-02-17","relationships":{"links":[],"related":[{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"cohere-tiny-aya","id":"cohere-tiny-aya","type":"model","title":"Cohere Tiny Aya 3.35B","description":"Multilingual specialist supporting 70+ languages at only 3.35B parameters. Designed for laptop and edge deployment. CC-BY-NC license.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/cohere-tiny-aya.md","html_url":"/models/cohere-tiny-aya","api_url":"/api/v1/models/cohere-tiny-aya.json","content_hash":"4d93bfe7caf736887eee6356971547ea6d81970a5e75f8c96da6ac9c7f9ef788","sha256":"4d93bfe7caf736887eee6356971547ea6d81970a5e75f8c96da6ac9c7f9ef788","provider":"Cohere","model_type":"open-source","api_model_id":"tiny-aya-global","capabilities":["streaming"],"availability_status":"available","deprecated":false,"tool_schema_format":"cohere","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Cohere Tiny Aya documentation","url":"https://docs.cohere.com/docs/tiny-aya"},{"title":"Cohere Tiny Aya research page","url":"https://cohere.com/research/aya"},{"title":"Cohere Labs Tiny Aya Global model card","url":"https://huggingface.co/CohereLabs/tiny-aya-global"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (CC-BY-NC)","output":"Free (CC-BY-NC)","free":true},"benchmarks":{"reasoning":65,"coding":62,"math":60,"writing":68,"multilingual":85,"speed":96},"context_window":"8K tokens","modality":["text"],"license":"CC-BY-NC 4.0","tags":["cohere","open-source","text"],"website":"https://cohere.com","release_date":"2026-02-17","relationships":{"links":[],"related":[{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["cohere","open-source","text"],"score":7},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"command-r-plus","id":"command-r-plus","type":"model","title":"Command R+","description":"Cohere's flagship model purpose-built for enterprise RAG (Retrieval-Augmented Generation). Excels at grounded generation with citations, multi-step tool use, and structured outputs. Strong bilingual English/French support.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/command-r-plus.md","html_url":"/models/command-r-plus","api_url":"/api/v1/models/command-r-plus.json","content_hash":"2b67d368b05358ae99e371b30a70d479cafbdc9444978c984d925db91dc1244e","sha256":"2b67d368b05358ae99e371b30a70d479cafbdc9444978c984d925db91dc1244e","provider":"Cohere","model_type":"open-source","api_model_id":"command-r-plus-08-2024","knowledge_cutoff":"2024-06-01","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"legacy","deprecated":false,"tool_schema_format":"cohere","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Cohere Command R+ model documentation","url":"https://docs.cohere.com/v2/docs/command-r-plus"},{"title":"Cohere pricing documentation","url":"https://docs.cohere.com/docs/how-does-cohere-pricing-work"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$2.50 / 1M tokens","output":"$10.00 / 1M tokens","input_per_1m":2.5,"output_per_1m":10,"currency":"USD","note":"Also available as open weights (CC-BY-NC)"},"benchmarks":{"reasoning":82,"coding":78,"math":76,"writing":85,"multilingual":88,"speed":78},"context_window":"128K tokens","modality":["text"],"license":"CC-BY-NC 4.0","tags":["cohere","open-source","text"],"website":"https://cohere.com","release_date":"2024-08","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["cohere","open-source","text"],"score":7},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"deepseek-r1","id":"deepseek-r1","type":"model","title":"DeepSeek R1","description":"Powerful open-source reasoning model that exceeds OpenAI o1 on AIME and MATH benchmarks. Transparent chain-of-thought reasoning at extremely low cost. MIT license. Updated with R1-0528 in May 2025.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/deepseek-r1.md","html_url":"/models/deepseek-r1","api_url":"/api/v1/models/deepseek-r1.json","content_hash":"2b949428697850ede2e6719a1c489244162994919c64cb5d7e6d70eb3ec3489c","sha256":"2b949428697850ede2e6719a1c489244162994919c64cb5d7e6d70eb3ec3489c","provider":"DeepSeek","model_type":"open-source","capabilities":["streaming","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"low","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"DeepSeek R1 repository","url":"https://github.com/deepseek-ai/DeepSeek-R1"},{"title":"DeepSeek models and pricing","url":"https://api-docs.deepseek.com/quick_start/pricing"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$0.55 / 1M tokens","output":"$2.19 / 1M tokens","note":"Also available open-source (MIT)"},"benchmarks":{"reasoning":92,"coding":88,"math":94,"writing":72,"multilingual":70,"speed":55},"context_window":"128K tokens","modality":["text"],"license":"MIT","tags":["deepseek","open-source","text"],"website":"https://deepseek.com","release_date":"2025-01","relationships":{"links":[],"related":[{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["deepseek","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"provider-deepseek","title":"DeepSeek Provider Profile","type":"provider","html_url":"/providers/deepseek","markdown_url":"/content/providers/deepseek.md","shared_tags":["deepseek","open-source"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"deepseek-v3.2","id":"deepseek-v3.2","type":"model","title":"DeepSeek V3.2","description":"On par with GPT-5.1 and Gemini 3.0 Pro on benchmarks. Uses sparse attention for efficiency. MIT license. Dramatically cheaper than Western alternatives.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/deepseek-v3.2.md","html_url":"/models/deepseek-v3.2","api_url":"/api/v1/models/deepseek-v3.2.json","content_hash":"9f2b0e1a6f52d2f872e59076fed43d537eb26f9def7df539e548c8c065e6640e","sha256":"9f2b0e1a6f52d2f872e59076fed43d537eb26f9def7df539e548c8c065e6640e","provider":"DeepSeek","model_type":"open-source","api_model_id":"deepseek-chat","capabilities":["function_calling","structured_output","streaming","json_mode","prompt_caching","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"DeepSeek models and pricing","url":"https://api-docs.deepseek.com/quick_start/pricing"},{"title":"DeepSeek API model list","url":"https://api-docs.deepseek.com/api/list-models"},{"title":"DeepSeek V3.2 announcement","url":"https://api-docs.deepseek.com/news/news250929"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$0.28 / 1M tokens","output":"$0.42 / 1M tokens","input_per_1m":0.28,"output_per_1m":0.42,"currency":"USD","cache_read_per_1m":0.028,"free":true,"note":"MIT license for self-hosting"},"benchmarks":{"reasoning":88,"coding":88,"math":87,"writing":84,"multilingual":80,"speed":82},"context_window":"128K tokens","modality":["text"],"license":"MIT","tags":["deepseek","open-source","text"],"website":"https://deepseek.com","release_date":"2025-09","relationships":{"links":[],"related":[{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["deepseek","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"provider-deepseek","title":"DeepSeek Provider Profile","type":"provider","html_url":"/providers/deepseek","markdown_url":"/content/providers/deepseek.md","shared_tags":["deepseek","open-source"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"falcon-3","id":"falcon-3","type":"model","title":"Falcon 3","description":"Runs on regular (non-gaming) laptops. Designed for accessibility and low-resource deployment. From UAE-based Technology Innovation Institute.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/falcon-3.md","html_url":"/models/falcon-3","api_url":"/api/v1/models/falcon-3.json","content_hash":"846c20df74186725d77c7ed89fbcbab57550051a86e17357444f8aeb16cc5ed6","sha256":"846c20df74186725d77c7ed89fbcbab57550051a86e17357444f8aeb16cc5ed6","provider":"Technology Innovation Institute","model_type":"open-source","api_model_id":"tiiuae/Falcon3-10B-Instruct","capabilities":["function_calling","streaming"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Falcon3 10B Instruct model card","url":"https://huggingface.co/tiiuae/Falcon3-10B-Instruct"}],"benchmark_sources":[{"title":"Falcon3 10B Instruct model card","url":"https://huggingface.co/tiiuae/Falcon3-10B-Instruct"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true},"benchmarks":{"reasoning":70,"coding":68,"math":67,"writing":72,"multilingual":70,"speed":94},"context_window":"32K tokens","modality":["text"],"license":"TII Falcon-LLM License 2.0","tags":["technology innovation institute","open-source","text"],"website":"https://falconllm.tii.ae","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"gemini-3-flash","id":"gemini-3-flash","type":"model","title":"Gemini 3 Flash","description":"Google's fast, cost-efficient model replacing Gemini 2.5 Flash. Designed for high-throughput applications with up to 1M token context at an extremely low price.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/gemini-3-flash.md","html_url":"/models/gemini-3-flash","api_url":"/api/v1/models/gemini-3-flash.json","content_hash":"bc2caf0a0b4750d7b0c168fdc26a493b440ccaf409353f4508d431183c55120c","sha256":"bc2caf0a0b4750d7b0c168fdc26a493b440ccaf409353f4508d431183c55120c","provider":"Google","model_type":"proprietary","api_model_id":"gemini-3-flash-preview","capabilities":["function_calling","vision","audio_input","video","web_search","file_search","code_execution","structured_output","streaming","prompt_caching","long_context","reasoning"],"availability_status":"preview","deprecated":false,"tool_schema_format":"gemini","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Google Gemini API pricing","url":"https://ai.google.dev/gemini-api/docs/pricing"},{"title":"Google Gemini 3 API documentation","url":"https://ai.google.dev/gemini-api/docs/models/gemini-3"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$0.50 / 1M tokens","output":"$3.00 / 1M tokens","input_per_1m":0.5,"output_per_1m":3,"currency":"USD","cache_read_per_1m":0.05,"batch_input_per_1m":0.25,"batch_output_per_1m":1.5,"note":"Free tier available; audio input is priced separately."},"benchmarks":{"reasoning":82,"coding":80,"math":79,"writing":83,"multilingual":85,"speed":95},"context_window":"1M tokens","modality":["text","image","video","audio"],"license":"Proprietary","tags":["google","proprietary","text","image","video","audio"],"website":"https://deepmind.google","release_date":"2025-12","relationships":{"links":[],"related":[{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","proprietary","text","image","video","audio"],"score":10},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","text","image"],"score":7},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gemini-3.1-pro","id":"gemini-3.1-pro","type":"model","title":"Gemini 3.1 Pro","description":"Google's most capable model, building on the Gemini 3 series with improved reasoning, multimodal, and agentic capabilities. Native multimodal across text, images, video, and audio.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/gemini-3.1-pro.md","html_url":"/models/gemini-3.1-pro","api_url":"/api/v1/models/gemini-3.1-pro.json","content_hash":"26d4eaa9f58e0d9b2393f5dfd34a902692b2933877744eb52a08dcb3082fcbfb","sha256":"26d4eaa9f58e0d9b2393f5dfd34a902692b2933877744eb52a08dcb3082fcbfb","provider":"Google","model_type":"proprietary","api_model_id":"gemini-3.1-pro-preview","knowledge_cutoff":"2025-01","capabilities":["function_calling","vision","audio_input","video","web_search","file_search","code_execution","structured_output","streaming","prompt_caching","long_context","reasoning"],"availability_status":"preview","deprecated":false,"tool_schema_format":"gemini","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Gemini 3.1 Pro announcement","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/"},{"title":"Gemini 3.1 Pro model card","url":"https://deepmind.google/models/model-cards/gemini-3-1-pro/"},{"title":"Gemini Developer API pricing","url":"https://ai.google.dev/pricing"}],"benchmark_sources":[{"title":"Gemini 3.1 Pro model card","url":"https://deepmind.google/models/model-cards/gemini-3-1-pro/"}],"pricing":{"input":"$2.00 / 1M tokens","output":"$12.00 / 1M tokens","input_per_1m":2,"output_per_1m":12,"currency":"USD","cache_read_per_1m":0.2,"long_context_input_per_1m":4,"long_context_output_per_1m":18,"note":"Preview pricing; prompts over 200K tokens use higher input/output rates."},"benchmarks":{"reasoning":93,"coding":91,"math":92,"writing":89,"multilingual":93,"speed":78},"context_window":"1M tokens","modality":["text","image","video","audio"],"license":"Proprietary","tags":["google","proprietary","text","image","video","audio"],"website":"https://deepmind.google","release_date":"2026-02-19","relationships":{"links":[],"related":[{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","proprietary","text","image","video","audio"],"score":10},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","text","image"],"score":7},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gemma-3","id":"gemma-3","type":"model","title":"Gemma 3","description":"Google's open model family optimized for on-device and edge deployment. Multimodal from 4B parameters. Sizes from 1B to 27B.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/gemma-3.md","html_url":"/models/gemma-3","api_url":"/api/v1/models/gemma-3.json","content_hash":"3e6d0b597db32d9377669482a0d4a179602cf2b4d9edf670cf1430c001b55694","sha256":"3e6d0b597db32d9377669482a0d4a179602cf2b4d9edf670cf1430c001b55694","provider":"Google","model_type":"open-source","capabilities":["vision","streaming","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Google Gemma 3 model card","url":"https://ai.google.dev/gemma/docs/core/model_card_3"},{"title":"Google Gemma documentation","url":"https://ai.google.dev/gemma"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true},"benchmarks":{"reasoning":75,"coding":73,"math":72,"writing":76,"multilingual":78,"speed":93},"context_window":"128K tokens","modality":["text","image"],"license":"Gemma Terms of Use","tags":["google","open-source","text","image"],"website":"https://ai.google.dev/gemma","release_date":"2025","relationships":{"links":[],"related":[{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","open-source","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","text","image"],"score":7},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","text","image"],"score":7},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"gemma-4","id":"gemma-4","type":"model","title":"Gemma 4","description":"Google's most capable open model, built from the same research as Gemini 3. The 31B dense variant ranks #3 on Arena AI (1,452 Elo). First Gemma release under Apache 2.0. Four variants from edge (E2B) to workstation (31B). Natively multimodal with 140+ language support.","last_updated":"2026-04-30","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gemma-4.md","html_url":"/models/gemma-4","api_url":"/api/v1/models/gemma-4.json","content_hash":"08ca103eb133e1b67b7e5f089607a5299907e50c02fffefbafcf7ae1d0bb5ea0","sha256":"08ca103eb133e1b67b7e5f089607a5299907e50c02fffefbafcf7ae1d0bb5ea0","provider":"Google","model_type":"open-source","capabilities":["vision","audio_input","video","streaming","long_context","reasoning"],"availability_status":"unverified","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"low","model_listing_confidence":"low","benchmark_confidence":"low","sources":[{"title":"Google Gemma documentation","url":"https://ai.google.dev/gemma"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":84,"coding":83,"math":89,"writing":83,"multilingual":90,"speed":85},"context_window":"256K tokens","modality":["text","image","video","audio"],"license":"Apache 2.0","tags":["google","open-source","text","image","video","audio"],"website":"https://ai.google.dev/gemma","release_date":"2026-04","relationships":{"links":[],"related":[{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","open-source","text","image"],"score":8},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"glm-5","id":"glm-5","type":"model","title":"GLM-5","description":"Large MoE model with strongest coding benchmark among open models (77.8% SWE-bench). 50.4% on Humanity's Last Exam. MIT license with no usage restrictions.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/glm-5.md","html_url":"/models/glm-5","api_url":"/api/v1/models/glm-5.json","content_hash":"42999d283c36305031bc9466f60f0318e100331fb7448960a09789859db6b6c5","sha256":"42999d283c36305031bc9466f60f0318e100331fb7448960a09789859db6b6c5","provider":"Zhipu AI","model_type":"open-source","api_model_id":"zai-org/GLM-5","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"high","sources":[{"title":"GLM-5 model card","url":"https://huggingface.co/zai-org/GLM-5"},{"title":"GLM-5 NVIDIA NIM model card","url":"https://build.nvidia.com/z-ai/glm5/modelcard"}],"benchmark_sources":[{"title":"GLM-5 benchmark table","url":"https://huggingface.co/zai-org/GLM-5"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Also via Zhipu API"},"benchmarks":{"reasoning":90,"coding":93,"math":88,"writing":82,"multilingual":83,"speed":70},"context_window":"202K tokens","modality":["text"],"license":"MIT","tags":["zhipu ai","open-source","text"],"website":"https://www.zhipuai.cn","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"gpt-5.4","id":"gpt-5.4","type":"model","title":"GPT-5.4","description":"OpenAI's flagship model combining frontier reasoning, coding, computer-use, and agentic capabilities. Unifies the best of GPT-5.3-Codex into a single model with stronger factuality than GPT-5.2.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/gpt-5.4.md","html_url":"/models/gpt-5.4","api_url":"/api/v1/models/gpt-5.4.json","content_hash":"40882911812f28563bf0879feda8c34d880deff51a86995670b321b331713908","sha256":"40882911812f28563bf0879feda8c34d880deff51a86995670b321b331713908","provider":"OpenAI","model_type":"proprietary","api_model_id":"gpt-5.4","knowledge_cutoff":"2025-08-31","capabilities":["function_calling","vision","web_search","file_search","code_execution","computer_use","structured_output","streaming","prompt_caching","tool_search","mcp","long_context","reasoning"],"availability_status":"available","deprecated":false,"superseded_by":"gpt-5.5","tool_schema_format":"openai","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"OpenAI GPT-5.4 model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.4"},{"title":"Introducing GPT-5.4","url":"https://openai.com/index/introducing-gpt-5-4/"},{"title":"OpenAI API pricing","url":"https://developers.openai.com/api/docs/pricing"}],"benchmark_sources":[{"title":"Introducing GPT-5.4 evaluations","url":"https://openai.com/index/introducing-gpt-5-4/"}],"pricing":{"input":"$2.50 / 1M tokens","output":"$15.00 / 1M tokens","input_per_1m":2.5,"output_per_1m":15,"currency":"USD","cache_read_per_1m":0.25,"long_context_input_per_1m":5,"long_context_output_per_1m":22.5,"note":"Prompts over 272K input tokens are priced at 2x input and 1.5x output for the full session."},"benchmarks":{"reasoning":95,"coding":92,"math":95,"writing":93,"multilingual":90,"speed":80},"context_window":"1.05M tokens","modality":["text","image"],"license":"Proprietary","tags":["openai","proprietary","text","image"],"website":"https://openai.com","release_date":"2026-03-05","relationships":{"links":[{"text":"GPT-5.5","href":"gpt-5.5.md","html_path":"/models/gpt-5.5","markdown_url":"/content/models/gpt-5.5.md","target_id":"gpt-5.5","target_type":"model","target_title":"GPT-5.5"}],"related":[{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-5.5","title":"GPT-5.5","type":"model","html_url":"/models/gpt-5.5","markdown_url":"/content/models/gpt-5.5.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-oss-120b","title":"GPT-OSS-120B","type":"model","html_url":"/models/gpt-oss-120b","markdown_url":"/content/models/gpt-oss-120b.md","shared_tags":["openai","text"],"score":6},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gpt-5.4-thinking","id":"gpt-5.4-thinking","type":"model","title":"GPT-5.4 Thinking","description":"Extended reasoning use of GPT-5.4 for the hardest problems. In the API, use the GPT-5.4 model with higher reasoning effort; in ChatGPT this is exposed as GPT-5.4 Thinking.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/gpt-5.4-thinking.md","html_url":"/models/gpt-5.4-thinking","api_url":"/api/v1/models/gpt-5.4-thinking.json","content_hash":"0de31075d3cff18617f39d8a56b2d4269505fab7d7d91f1d834b605bd4467316","sha256":"0de31075d3cff18617f39d8a56b2d4269505fab7d7d91f1d834b605bd4467316","provider":"OpenAI","model_type":"proprietary","api_model_id":"gpt-5.4","knowledge_cutoff":"2025-08-31","capabilities":["function_calling","vision","web_search","file_search","code_execution","computer_use","structured_output","streaming","prompt_caching","tool_search","mcp","long_context","reasoning"],"availability_status":"available","deprecated":false,"superseded_by":"gpt-5.5","variant_of":"gpt-5.4","tool_schema_format":"openai","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"OpenAI GPT-5.4 model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.4"},{"title":"Introducing GPT-5.4","url":"https://openai.com/index/introducing-gpt-5-4/"},{"title":"OpenAI API pricing","url":"https://developers.openai.com/api/docs/pricing"}],"benchmark_sources":[{"title":"Introducing GPT-5.4 evaluations","url":"https://openai.com/index/introducing-gpt-5-4/"}],"pricing":{"input":"$2.50 / 1M tokens","output":"$15.00 / 1M tokens","input_per_1m":2.5,"output_per_1m":15,"currency":"USD","cache_read_per_1m":0.25,"long_context_input_per_1m":5,"long_context_output_per_1m":22.5,"note":"Higher reasoning effort is billed as output tokens; prompts over 272K input tokens use long-context pricing."},"benchmarks":{"reasoning":98,"coding":93,"math":97,"writing":85,"multilingual":88,"speed":45},"context_window":"1.05M tokens","modality":["text","image"],"license":"Proprietary","tags":["openai","proprietary","text","image"],"website":"https://openai.com","release_date":"2026-03-05","relationships":{"links":[],"related":[{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-5.5","title":"GPT-5.5","type":"model","html_url":"/models/gpt-5.5","markdown_url":"/content/models/gpt-5.5.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-oss-120b","title":"GPT-OSS-120B","type":"model","html_url":"/models/gpt-oss-120b","markdown_url":"/content/models/gpt-oss-120b.md","shared_tags":["openai","text"],"score":6},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gpt-5.5","id":"gpt-5.5","type":"model","title":"GPT-5.5","description":"OpenAI's flagship model (codename Spud). Strong agentic coding, computer use, and frontier math. 1.05M context, 128K max output. $5/$30 per 1M tokens.","last_updated":"2026-06-10","last_verified":"2026-06-10","verification_status":"verified","markdown_url":"/content/models/gpt-5.5.md","html_url":"/models/gpt-5.5","api_url":"/api/v1/models/gpt-5.5.json","content_hash":"c3b49f99ad6a640bf818789885dd2fa56c6ffc3f0c6b5664cbc1d038462322fb","sha256":"c3b49f99ad6a640bf818789885dd2fa56c6ffc3f0c6b5664cbc1d038462322fb","provider":"OpenAI","model_type":"proprietary","api_model_id":"gpt-5.5","knowledge_cutoff":"2025-12","capabilities":["function_calling","vision","web_search","file_search","code_execution","computer_use","structured_output","streaming","prompt_caching","mcp","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"low","sources":[{"title":"Introducing GPT-5.5","url":"https://openai.com/index/introducing-gpt-5-5/"},{"title":"OpenAI GPT-5.5 model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.5"},{"title":"OpenAI API pricing","url":"https://developers.openai.com/api/docs/pricing"}],"benchmark_sources":[{"title":"Introducing GPT-5.5 evaluations","url":"https://openai.com/index/introducing-gpt-5-5/"},{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$5.00 / 1M tokens","output":"$30.00 / 1M tokens","input_per_1m":5,"output_per_1m":30,"currency":"USD","cache_read_per_1m":0.5,"long_context_input_per_1m":10,"long_context_output_per_1m":45,"note":"Long-context requests are billed at $10/$45. GPT-5.5 Pro is $30/$180. GPT-5.5 Instant serves ChatGPT as chat-latest at $5/$30."},"benchmarks":{"reasoning":97,"coding":95,"math":97,"writing":94,"multilingual":91,"speed":72},"context_window":"1.05M tokens","modality":["text","image"],"license":"Proprietary","tags":["openai","proprietary","text","image"],"website":"https://openai.com","release_date":"2026-04-23","relationships":{"links":[],"related":[{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["openai","proprietary","text","image"],"score":8},{"id":"gpt-oss-120b","title":"GPT-OSS-120B","type":"model","html_url":"/models/gpt-oss-120b","markdown_url":"/content/models/gpt-oss-120b.md","shared_tags":["openai","text"],"score":6},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gpt-oss-120b","id":"gpt-oss-120b","type":"model","title":"GPT-OSS-120B","description":"OpenAI's first fully open-weight LLMs since GPT-2. Matches or surpasses o4-mini on core benchmarks. Can run on a single 80GB GPU. Optimized for vLLM, llama.cpp, and Ollama.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/gpt-oss-120b.md","html_url":"/models/gpt-oss-120b","api_url":"/api/v1/models/gpt-oss-120b.json","content_hash":"b219e22ba43fac84fc6a0df539abc82ff819fccc1dd96b89d676a894203e9f7d","sha256":"b219e22ba43fac84fc6a0df539abc82ff819fccc1dd96b89d676a894203e9f7d","provider":"OpenAI","model_type":"open-source","api_model_id":"gpt-oss-120b","capabilities":["function_calling","web_search","code_execution","structured_output","streaming","json_mode","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"OpenAI gpt-oss-120b model documentation","url":"https://platform.openai.com/docs/models/gpt-oss-120b"},{"title":"OpenAI gpt-oss model card","url":"https://openai.com/research/gpt-oss-model-card/"},{"title":"OpenAI gpt-oss-120b Hugging Face model card","url":"https://huggingface.co/openai/gpt-oss-120b"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true},"benchmarks":{"reasoning":85,"coding":86,"math":85,"writing":87,"multilingual":86,"speed":75},"context_window":"128K tokens","modality":["text"],"license":"Apache 2.0","tags":["openai","open-source","text"],"website":"https://openai.com","release_date":"2025-08-05","relationships":{"links":[],"related":[{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["openai","text"],"score":6},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["openai","text"],"score":6},{"id":"gpt-5.5","title":"GPT-5.5","type":"model","html_url":"/models/gpt-5.5","markdown_url":"/content/models/gpt-5.5.md","shared_tags":["openai","text"],"score":6},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"grok-4.1","id":"grok-4.1","type":"model","title":"Grok 4.1","description":"xAI's flagship model with 65% fewer hallucinations than its predecessor (down to 4.22%). Available in both Thinking and Non-thinking configurations.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/grok-4.1.md","html_url":"/models/grok-4.1","api_url":"/api/v1/models/grok-4.1.json","content_hash":"7fd46b17e1c75f4bb648be33d69d560e35e8fcaa134fbc0d646cf95f33cc0312","sha256":"7fd46b17e1c75f4bb648be33d69d560e35e8fcaa134fbc0d646cf95f33cc0312","provider":"xAI","model_type":"proprietary","capabilities":["function_calling","vision","structured_output","streaming","long_context","reasoning"],"availability_status":"unverified","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"medium","model_listing_confidence":"low","benchmark_confidence":"low","sources":[{"title":"xAI models and pricing","url":"https://docs.x.ai/docs/models"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$3.00 / 1M tokens","output":"$15.00 / 1M tokens","input_per_1m":3,"output_per_1m":15,"currency":"USD","note":"Available via xAI API"},"benchmarks":{"reasoning":91,"coding":90,"math":91,"writing":87,"multilingual":80,"speed":76},"context_window":"128K tokens","modality":["text","image"],"license":"Proprietary","tags":["xai","proprietary","text","image"],"website":"https://x.ai","release_date":"2025-11","relationships":{"links":[],"related":[{"id":"grok-4.20","title":"Grok 4.20","type":"model","html_url":"/models/grok-4.20","markdown_url":"/content/models/grok-4.20.md","shared_tags":["xai","proprietary","text","image"],"score":8},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"grok-4.20","id":"grok-4.20","type":"model","title":"Grok 4.20","description":"xAI's latest flagship with the lowest hallucination rate of any model (78% Omniscience) and #1 instruction following (83% IFBench). Features a novel multi-agent architecture and 2M token context window. 248 tokens/second output speed.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/grok-4.20.md","html_url":"/models/grok-4.20","api_url":"/api/v1/models/grok-4.20.json","content_hash":"1852da8eda288ecb050eb779bae1adfad0365e2db19d34287dab0ce0ce108002","sha256":"1852da8eda288ecb050eb779bae1adfad0365e2db19d34287dab0ce0ce108002","provider":"xAI","model_type":"proprietary","api_model_id":"x-ai/grok-4.20","knowledge_cutoff":"2025-09-01","capabilities":["vision","web_search","structured_output","streaming","long_context","reasoning"],"availability_status":"preview","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"medium","model_listing_confidence":"medium","benchmark_confidence":"low","sources":[{"title":"xAI models and pricing","url":"https://docs.x.ai/docs/models"},{"title":"OpenRouter Grok 4.20 model page","url":"https://openrouter.ai/x-ai/grok-4.20"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$2.00 / 1M tokens","output":"$6.00 / 1M tokens","input_per_1m":2,"output_per_1m":6,"currency":"USD","note":"Fast tier; Standard tier $20/$60"},"benchmarks":{"reasoning":85,"coding":88,"math":83,"writing":87,"multilingual":82,"speed":90},"context_window":"2M tokens","modality":["text","image"],"license":"Proprietary","tags":["xai","proprietary","text","image"],"website":"https://x.ai","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"grok-4.1","title":"Grok 4.1","type":"model","html_url":"/models/grok-4.1","markdown_url":"/content/models/grok-4.1.md","shared_tags":["xai","proprietary","text","image"],"score":8},{"id":"claude-fable-5","title":"Claude Fable 5","type":"model","html_url":"/models/claude-fable-5","markdown_url":"/content/models/claude-fable-5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.7","title":"Claude Opus 4.7","type":"model","html_url":"/models/claude-opus-4.7","markdown_url":"/content/models/claude-opus-4.7.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.8","title":"Claude Opus 4.8","type":"model","html_url":"/models/claude-opus-4.8","markdown_url":"/content/models/claude-opus-4.8.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"hermes-4-405b","id":"hermes-4-405b","type":"model","title":"Hermes 4 405B","description":"Nous Research's flagship open-weight model with hybrid reasoning (toggle between standard and explicit chain-of-thought with think tags). Based on Llama 3.1, trained with rejection sampling via 1,000+ task verifiers. Known for minimal content restrictions and user-directed behavior.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/hermes-4-405b.md","html_url":"/models/hermes-4-405b","api_url":"/api/v1/models/hermes-4-405b.json","content_hash":"ae5a2a140e552eb97514626b4cbd56e9c08afcbc7998d0fd993f7760ea938246","sha256":"ae5a2a140e552eb97514626b4cbd56e9c08afcbc7998d0fd993f7760ea938246","provider":"Nous Research","model_type":"open-source","api_model_id":"NousResearch/Hermes-4-405B","capabilities":["function_calling","structured_output","streaming","json_mode","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"hermes","pricing_confidence":"low","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Hermes 4 405B Hugging Face model card","url":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"title":"Nous Portal models","url":"https://portal.nousresearch.com/models"}],"benchmark_sources":[{"title":"Hermes 4 405B Hugging Face model card","url":"https://huggingface.co/NousResearch/Hermes-4-405B"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Or via Nous Portal / OpenRouter"},"benchmarks":{"reasoning":88,"coding":84,"math":90,"writing":85,"multilingual":78,"speed":55},"context_window":"128K tokens","modality":["text"],"license":"Llama Community License","tags":["nous research","open-source","text"],"website":"https://nousresearch.com","release_date":"2025-08","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"kimi-k2.5","id":"kimi-k2.5","type":"model","title":"Kimi K2.5","description":"Open multimodal agentic model from Moonshot AI achieving 96% on AIME 2025, outperforming most proprietary models on math. Strong reasoning and mathematical capabilities.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/kimi-k2.5.md","html_url":"/models/kimi-k2.5","api_url":"/api/v1/models/kimi-k2.5.json","content_hash":"4d9dfb45efde560e1ce42b79b8e90fa9eeddd35ed25d806de1f34ce61241e126","sha256":"4d9dfb45efde560e1ce42b79b8e90fa9eeddd35ed25d806de1f34ce61241e126","provider":"Moonshot AI","model_type":"open-source","api_model_id":"moonshotai/Kimi-K2.5","capabilities":["function_calling","vision","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"low","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Kimi K2.5 model card","url":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"title":"Kimi K2.5 NVIDIA NIM model card","url":"https://build.nvidia.com/moonshotai/kimi-k2.5/modelcard"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Kimi API available"},"benchmarks":{"reasoning":93,"coding":85,"math":97,"writing":78,"multilingual":80,"speed":72},"context_window":"128K tokens","modality":["text","image"],"license":"Modified MIT","tags":["moonshot ai","open-source","text","image"],"website":"https://www.moonshot.cn","release_date":"2025","relationships":{"links":[],"related":[{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"llama-4-maverick","id":"llama-4-maverick","type":"model","title":"Llama 4 Maverick","description":"Meta's flagship open-source MoE model with 400B total parameters (17B active). Scored #2 on LMArena leaderboard (ELO 1,417). Native multimodal capabilities.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/llama-4-maverick.md","html_url":"/models/llama-4-maverick","api_url":"/api/v1/models/llama-4-maverick.json","content_hash":"6741c0404aa96766f0426f335fb257e868849585cd7b152407e4fa4dda8b60e6","sha256":"6741c0404aa96766f0426f335fb257e868849585cd7b152407e4fa4dda8b60e6","provider":"Meta","model_type":"open-source","api_model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","capabilities":["vision","streaming","structured_output","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"medium","benchmark_confidence":"low","sources":[{"title":"Meta Llama models","url":"https://www.llama.com/models/llama-4/"},{"title":"NVIDIA Llama 4 Scout and Maverick technical blog","url":"https://developer.nvidia.com/blog/nvidia-accelerates-inference-on-meta-llama-4-scout-and-maverick/"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Or use via third-party APIs"},"benchmarks":{"reasoning":87,"coding":82,"math":84,"writing":86,"multilingual":84,"speed":80},"context_window":"1M tokens","modality":["text","image"],"license":"Llama Community License","tags":["meta","open-source","text","image"],"website":"https://llama.meta.com","release_date":"2025-04","relationships":{"links":[],"related":[{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["meta","open-source","text","image"],"score":8},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"llama-4-scout","id":"llama-4-scout","type":"model","title":"Llama 4 Scout","description":"Meta's efficient open-source MoE model with 109B total parameters (17B active). Features the largest context window of any model at 10M tokens.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/llama-4-scout.md","html_url":"/models/llama-4-scout","api_url":"/api/v1/models/llama-4-scout.json","content_hash":"290038e9efb6811314b71da9f54e493963bea50d5443d63ae25b7d4947c78a98","sha256":"290038e9efb6811314b71da9f54e493963bea50d5443d63ae25b7d4947c78a98","provider":"Meta","model_type":"open-source","api_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","capabilities":["vision","streaming","structured_output","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"medium","benchmark_confidence":"low","sources":[{"title":"Meta Llama models","url":"https://www.llama.com/models/llama-4/"},{"title":"NVIDIA Llama 4 Scout and Maverick technical blog","url":"https://developer.nvidia.com/blog/nvidia-accelerates-inference-on-meta-llama-4-scout-and-maverick/"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true},"benchmarks":{"reasoning":80,"coding":79,"math":77,"writing":81,"multilingual":79,"speed":88},"context_window":"10M tokens","modality":["text","image"],"license":"Llama Community License","tags":["meta","open-source","text","image"],"website":"https://llama.meta.com","release_date":"2025-04","relationships":{"links":[],"related":[{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["meta","open-source","text","image"],"score":8},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"minimax-m2.7","id":"minimax-m2.7","type":"model","title":"MiniMax M2.7","description":"Third iteration of MiniMax's M2 line with tighter factual accuracy and lower cost. Intelligence index of 49.62 places it near frontier models at a fraction of the price. Open weights.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/minimax-m2.7.md","html_url":"/models/minimax-m2.7","api_url":"/api/v1/models/minimax-m2.7.json","content_hash":"804bc4962e988452216cf170dfdc69af683fc7501d0c8dc158bfd9f0313f0e63","sha256":"804bc4962e988452216cf170dfdc69af683fc7501d0c8dc158bfd9f0313f0e63","provider":"MiniMax","model_type":"open-source","api_model_id":"MiniMaxAI/MiniMax-M2.7","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"low","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"MiniMax M2.7 model page","url":"https://www.minimax.io/models/text/m27"},{"title":"MiniMax M2.7 Hugging Face model card","url":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"title":"MiniMax M2.7 GitHub repository","url":"https://github.com/MiniMax-AI/MiniMax-M2.7"}],"benchmark_sources":[{"title":"MiniMax M2.7 Hugging Face model card","url":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"}],"pricing":{"input":"$0.53 / 1M tokens","output":"$0.53 / 1M tokens","free":true,"note":"Also free self-hosted"},"benchmarks":{"reasoning":90,"coding":95,"math":88,"writing":82,"multilingual":83,"speed":85},"context_window":"205K tokens","modality":["text"],"license":"Modified MIT","tags":["minimax","open-source","text"],"website":"https://minimax.io","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"mistral-3","id":"mistral-3","type":"model","title":"Mistral 3","description":"Mistral's flagship model suite with Apache 2.0 license. A European alternative focused on enterprise compliance, adopting a DeepSeek-style MoE architecture for efficiency.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/mistral-3.md","html_url":"/models/mistral-3","api_url":"/api/v1/models/mistral-3.json","content_hash":"c97fda453dbf0419cca931acf332e4c85ded53aa51ae33a33c9d3fa88e59a562","sha256":"c97fda453dbf0419cca931acf332e4c85ded53aa51ae33a33c9d3fa88e59a562","provider":"Mistral AI","model_type":"open-source","capabilities":["function_calling","vision","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"mistral","pricing_confidence":"low","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Introducing Mistral 3","url":"https://mistral.ai/news/mistral-3"},{"title":"Mistral models overview","url":"https://mistral.ai/models"},{"title":"Mistral pricing","url":"https://mistral.ai/pricing"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$2.00 / 1M tokens","output":"$6.00 / 1M tokens","input_per_1m":2,"output_per_1m":6,"currency":"USD"},"benchmarks":{"reasoning":86,"coding":87,"math":84,"writing":86,"multilingual":92,"speed":78},"context_window":"256K tokens","modality":["text","image"],"license":"Apache 2.0","tags":["mistral ai","open-source","text","image"],"website":"https://mistral.ai","release_date":"2025-12","relationships":{"links":[],"related":[{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["mistral ai","open-source","text","image"],"score":8},{"id":"mistral-small-3","title":"Mistral Small 3 24B","type":"model","html_url":"/models/mistral-small-3","markdown_url":"/content/models/mistral-small-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"mistral-small-3","id":"mistral-small-3","type":"model","title":"Mistral Small 3 24B","description":"Efficient 24B model that competes with models 2-3x its size. Apache 2.0 license. Strong for real-time applications.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/mistral-small-3.md","html_url":"/models/mistral-small-3","api_url":"/api/v1/models/mistral-small-3.json","content_hash":"c7dfd18249c41bd9f8f3ebfec44589a32d09619018a12b3345a8e437574e5ad1","sha256":"c7dfd18249c41bd9f8f3ebfec44589a32d09619018a12b3345a8e437574e5ad1","provider":"Mistral AI","model_type":"open-source","api_model_id":"mistral-small-2501","capabilities":["function_calling","structured_output","streaming","tool_search"],"availability_status":"retired","deprecated":true,"superseded_by":"mistral-small-4","tool_schema_format":"mistral","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Mistral Small 3.0 model card","url":"https://docs.mistral.ai/models/model-cards/mistral-small-3-0-25-01"},{"title":"Mistral Small 3 announcement","url":"https://mistral.ai/news/mistral-small-3"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":79,"coding":80,"math":77,"writing":80,"multilingual":85,"speed":90},"context_window":"32K tokens","modality":["text"],"license":"Apache 2.0","tags":["mistral ai","open-source","text"],"website":"https://mistral.ai","release_date":"2025-01-30","relationships":{"links":[],"related":[{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"mistral-small-4","id":"mistral-small-4","type":"model","title":"Mistral Small 4","description":"Efficient MoE model with 119B total parameters but only 6.5B active — the knowledge capacity of a large model at the inference cost of a small one. Multimodal with hybrid reasoning. Apache 2.0 license.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/mistral-small-4.md","html_url":"/models/mistral-small-4","api_url":"/api/v1/models/mistral-small-4.json","content_hash":"2c0263bb4c8aab7e710b72485e4f35f64bc6f8065916c07adbee5c539cd13e0e","sha256":"2c0263bb4c8aab7e710b72485e4f35f64bc6f8065916c07adbee5c539cd13e0e","provider":"Mistral AI","model_type":"open-source","api_model_id":"mistral-small-2603","capabilities":["function_calling","vision","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"mistral","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Mistral Small 4 model card","url":"https://docs.mistral.ai/models/mistral-small-4-0-26-03"},{"title":"Mistral Small 4 lifecycle documentation","url":"https://legal.mistral.ai/ai-governance/models/mistral-small-4"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"$0.15 / 1M tokens","output":"$0.60 / 1M tokens","input_per_1m":0.15,"output_per_1m":0.6,"currency":"USD","free":true,"note":"Also available as Apache 2.0 open weights."},"benchmarks":{"reasoning":76,"coding":78,"math":74,"writing":78,"multilingual":86,"speed":92},"context_window":"256K tokens","modality":["text","image"],"license":"Apache 2.0","tags":["mistral ai","open-source","text","image"],"website":"https://mistral.ai","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["mistral ai","open-source","text","image"],"score":8},{"id":"mistral-small-3","title":"Mistral Small 3 24B","type":"model","html_url":"/models/mistral-small-3","markdown_url":"/content/models/mistral-small-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"nemotron-3-super","id":"nemotron-3-super","type":"model","title":"Nemotron 3 Super","description":"NVIDIA's open-weight MoE model with 120B total parameters and 12B active. Designed to fit on hardware most companies already own. Serves as the anchor for NVIDIA's agent toolkit strategy, optimized for TensorRT-LLM and NIM.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/nemotron-3-super.md","html_url":"/models/nemotron-3-super","api_url":"/api/v1/models/nemotron-3-super.json","content_hash":"1c246e3bb6b1a17346933619ef964eec18f5e2fa429222ee8870609cc0d21796","sha256":"1c246e3bb6b1a17346933619ef964eec18f5e2fa429222ee8870609cc0d21796","provider":"NVIDIA","model_type":"open-source","api_model_id":"nvidia/nemotron-3-super-120b-a12b","knowledge_cutoff":"2026-02","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"high","sources":[{"title":"NVIDIA Nemotron 3 Super model card","url":"https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard"},{"title":"NVIDIA Nemotron 3 Super Hugging Face model card","url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"}],"benchmark_sources":[{"title":"NVIDIA Nemotron 3 Super model card","url":"https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"Also via NVIDIA NIM API"},"benchmarks":{"reasoning":80,"coding":82,"math":78,"writing":79,"multilingual":78,"speed":88},"context_window":"1M tokens","modality":["text"],"license":"NVIDIA Open Model License","tags":["nvidia","open-source","text"],"website":"https://build.nvidia.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"nemotron-cascade-2","title":"Nemotron-Cascade 2","type":"model","html_url":"/models/nemotron-cascade-2","markdown_url":"/content/models/nemotron-cascade-2.md","shared_tags":["nvidia","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"nemotron-cascade-2","id":"nemotron-cascade-2","type":"model","title":"Nemotron-Cascade 2","description":"NVIDIA's 30B MoE with only 3B active parameters that achieves gold-medal performance on IMO, IOI, and ICPC. Beats the larger Nemotron 3 Super 120B on coding and instruction following. Fits on a single RTX 4090 (24GB VRAM with Q4). Hybrid Mamba-2 + Transformer architecture enables a 1M token context window.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/nemotron-cascade-2.md","html_url":"/models/nemotron-cascade-2","api_url":"/api/v1/models/nemotron-cascade-2.json","content_hash":"b282f6494b7dbf3e5571415846c2ab254b6bc1be776f6c2c3d5d8c98975fdfbe","sha256":"b282f6494b7dbf3e5571415846c2ab254b6bc1be776f6c2c3d5d8c98975fdfbe","provider":"NVIDIA","model_type":"open-source","api_model_id":"nvidia/Nemotron-Cascade-2","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"high","sources":[{"title":"NVIDIA Nemotron-Cascade 2 research page","url":"https://research.nvidia.com/labs/nemotron/nemotron-cascade-2/"}],"benchmark_sources":[{"title":"NVIDIA Nemotron-Cascade 2 research page","url":"https://research.nvidia.com/labs/nemotron/nemotron-cascade-2/"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"Also via Ollama, NVIDIA NIM"},"benchmarks":{"reasoning":88,"coding":90,"math":92,"writing":78,"multilingual":75,"speed":92},"context_window":"1M tokens","modality":["text"],"license":"NVIDIA Open Model License","tags":["nvidia","open-source","text"],"website":"https://build.nvidia.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"nemotron-3-super","title":"Nemotron 3 Super","type":"model","html_url":"/models/nemotron-3-super","markdown_url":"/content/models/nemotron-3-super.md","shared_tags":["nvidia","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"phi-4","id":"phi-4","type":"model","title":"Phi-4","description":"Microsoft's small-but-capable model using state-of-the-art training techniques and high-quality data. Punches well above its weight class despite small parameter count.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/phi-4.md","html_url":"/models/phi-4","api_url":"/api/v1/models/phi-4.json","content_hash":"926f457ed3243df647409e27141202f3e1bdb3ee480208209b7e0660ed56d536","sha256":"926f457ed3243df647409e27141202f3e1bdb3ee480208209b7e0660ed56d536","provider":"Microsoft","model_type":"open-source","api_model_id":"microsoft/phi-4","capabilities":["streaming","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Microsoft Phi-4 model card","url":"https://huggingface.co/microsoft/phi-4-gguf"},{"title":"Microsoft Phi-4 reasoning model card","url":"https://huggingface.co/microsoft/Phi-4-reasoning"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"MIT license"},"benchmarks":{"reasoning":78,"coding":80,"math":79,"writing":77,"multilingual":72,"speed":92},"context_window":"16K tokens","modality":["text"],"license":"MIT","tags":["microsoft","open-source","text"],"website":"https://azure.microsoft.com/en-us/products/phi","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"qwen-3","id":"qwen-3","type":"model","title":"Qwen 3","description":"Alibaba's flagship open model family. Overtook Llama as the most-downloaded model family on HuggingFace in late 2025. Hybrid reasoning with think/non-think modes. 119 languages supported.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/qwen-3.md","html_url":"/models/qwen-3","api_url":"/api/v1/models/qwen-3.json","content_hash":"1fd5bb4362516ee856a4212e07853c97555f3265c7d666e510e3df1371a84d2b","sha256":"1fd5bb4362516ee856a4212e07853c97555f3265c7d666e510e3df1371a84d2b","provider":"Alibaba","model_type":"open-source","api_model_id":"Qwen/Qwen3-235B-A22B","capabilities":["function_calling","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Qwen3 235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B"},{"title":"Amazon Bedrock Qwen3 model card","url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Also via Alibaba Cloud API"},"benchmarks":{"reasoning":88,"coding":90,"math":92,"writing":82,"multilingual":95,"speed":80},"context_window":"128K tokens","modality":["text"],"license":"Apache 2.0","tags":["alibaba","open-source","text"],"website":"https://qwenlm.github.io","release_date":"2025-06","relationships":{"links":[],"related":[{"id":"qwen-3.5","title":"Qwen 3.5 397B-A17B","type":"model","html_url":"/models/qwen-3.5","markdown_url":"/content/models/qwen-3.5.md","shared_tags":["alibaba","open-source","text"],"score":7},{"id":"provider-qwen","title":"Alibaba Qwen Provider Profile","type":"provider","html_url":"/providers/qwen","markdown_url":"/content/providers/qwen.md","shared_tags":["alibaba","open-source"],"score":4},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"qwen-3.5","id":"qwen-3.5","type":"model","title":"Qwen 3.5 397B-A17B","description":"Alibaba's generational leap. Natively multimodal, 256K context, 201 languages. The flagship 397B-A17B MoE model activates only 17B parameters per token. Apache 2.0. Most downloaded model family on HuggingFace.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/qwen-3.5.md","html_url":"/models/qwen-3.5","api_url":"/api/v1/models/qwen-3.5.json","content_hash":"32b8c3daf6f4496c37ba8e9c857b003a69c5080631ab2ef33d3c6eb1b9803b4a","sha256":"32b8c3daf6f4496c37ba8e9c857b003a69c5080631ab2ef33d3c6eb1b9803b4a","provider":"Alibaba","model_type":"open-source","api_model_id":"Qwen/Qwen3.5-397B-A17B","capabilities":["function_calling","vision","structured_output","streaming","tool_search","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Qwen3.5 397B-A17B model card","url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Alibaba Cloud API available"},"benchmarks":{"reasoning":91,"coding":92,"math":94,"writing":84,"multilingual":97,"speed":82},"context_window":"256K tokens","modality":["text","image"],"license":"Apache 2.0","tags":["alibaba","open-source","text","image"],"website":"https://qwenlm.github.io","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"qwen-3","title":"Qwen 3","type":"model","html_url":"/models/qwen-3","markdown_url":"/content/models/qwen-3.md","shared_tags":["alibaba","open-source","text"],"score":7},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"kimi-k2.5","title":"Kimi K2.5","type":"model","html_url":"/models/kimi-k2.5","markdown_url":"/content/models/kimi-k2.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"smollm3-3b","id":"smollm3-3b","type":"model","title":"SmolLM3 3B","description":"Fully open instruct and reasoning model with unprecedented transparency — Hugging Face published the complete engineering blueprint. Outperforms Llama-3.2-3B and Qwen2.5-3B at the 3B scale.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/smollm3-3b.md","html_url":"/models/smollm3-3b","api_url":"/api/v1/models/smollm3-3b.json","content_hash":"8ce81d95dd97392e9843163f2cec2740d255d47cc54fecb2afa81e7625f9447e","sha256":"8ce81d95dd97392e9843163f2cec2740d255d47cc54fecb2afa81e7625f9447e","provider":"Hugging Face","model_type":"open-source","api_model_id":"HuggingFaceTB/SmolLM3-3B","capabilities":["streaming","long_context","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"SmolLM3 3B model card","url":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B"}],"benchmark_sources":[{"title":"SmolLM3 3B model card","url":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B"}],"pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":68,"coding":70,"math":66,"writing":70,"multilingual":65,"speed":96},"context_window":"64K native, 128K with YaRN","modality":["text"],"license":"Apache 2.0","tags":["hugging face","open-source","text"],"website":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B","release_date":"2026","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"yi-1.5-34b","id":"yi-1.5-34b","type":"model","title":"Yi-1.5 34B","description":"Strong bilingual (English/Chinese) model from 01.AI that competes with much larger models on benchmarks. Excellent reasoning and code generation at a deployable 34B size. Apache 2.0 license.","last_updated":"2026-04-30","last_verified":"2026-04-30","verification_status":"verified","markdown_url":"/content/models/yi-1.5-34b.md","html_url":"/models/yi-1.5-34b","api_url":"/api/v1/models/yi-1.5-34b.json","content_hash":"eeb1a7c68f464b3ef3defad7934d758819ae11cf40d5a27b5838a9700a4f6762","sha256":"eeb1a7c68f464b3ef3defad7934d758819ae11cf40d5a27b5838a9700a4f6762","provider":"01.AI","model_type":"open-source","api_model_id":"01-ai/Yi-1.5-34B","capabilities":["streaming","reasoning"],"availability_status":"available","deprecated":false,"tool_schema_format":"openai-compatible","pricing_confidence":"high","model_listing_confidence":"high","benchmark_confidence":"medium","sources":[{"title":"Yi-1.5 34B model card","url":"https://huggingface.co/01-ai/Yi-1.5-34B"},{"title":"Yi 34B model card","url":"https://huggingface.co/01-ai/Yi-34B"}],"benchmark_sources":[{"title":"AI Future Ready benchmark methodology","url":"https://ai-future-ready.com/guides/benchmark-methodology"}],"pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":80,"coding":79,"math":78,"writing":80,"multilingual":82,"speed":85},"context_window":"32K tokens","modality":["text"],"license":"Apache 2.0","tags":["01.ai","open-source","text"],"website":"https://01.ai","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}}]}