{"type":"models-filter","generated_at":"2026-07-03","source":"/api/v1/models.json","total":37,"count":21,"query":{"capability":["vision"],"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":"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":"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":"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":"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":"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-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":"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":{}}}]}