{"name":"AI Coding Model Board","description":{"en":"Public list prices per 1M tokens, context windows, and published SWE-bench Verified and CursorBench scores. Blank fields are unpublished, not estimates.","zh":"公开标价（每百万 token）、上下文长度，以及已公布的 SWE-bench Verified 与 CursorBench 分数。空字段表示来源未公布，不是估算。"},"url":{"en":"https://evanlong.me/en/models","zh":"https://evanlong.me/zh/models"},"updatedAt":"2026-10-14","license":"https://creativecommons.org/licenses/by/4.0/","licenseNote":{"en":"This compilation is CC BY 4.0. The prices and scores remain the publishers'.","zh":"本汇编采用 CC BY 4.0。价格与分数仍归各发布方。"},"creator":{"@type":"Person","name":"Evan Long","url":"https://evanlong.me","sameAs":["https://x.com/evanlong_me","https://github.com/evanlong-me"]},"conclusion":{"en":"As of 2026-10-14, among models on this board with a published CursorBench 4.0 score, Claude Opus 5.5 leads at 57.8%, and Gemini 3.8 Flash has the lowest listed standard input price at $0.75 per 1M tokens.","zh":"截至 2026-10-14，本表已公布 CursorBench 4.0 分数的模型中，Claude Opus 5.5 最高，为 57.8%；已列出的标准输入价里，Gemini 3.8 Flash 最低，为每百万 token $0.75。"},"citations":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/models/overview","https://cursor.com/cursorbench","https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models","https://docs.x.ai/docs/models","https://docs.z.ai/guides/overview/pricing","https://docs.z.ai/guides/llm/glm-5.3","https://api-docs.deepseek.com/quick_start/pricing","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra"],"follow":"https://x.com/evanlong_me","models":[{"id":"claude-opus-5-5","provider":"Anthropic","name":"Claude Opus 5.5","apiId":"claude-opus-5-5","inputPerMillionUsd":{"value":4,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"outputPerMillionUsd":{"value":20,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://platform.claude.com/docs/en/models/overview","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":57.8,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"claude-sonnet-5-5","provider":"Anthropic","name":"Claude Sonnet 5.5","apiId":"claude-sonnet-5-5","inputPerMillionUsd":{"value":2,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"outputPerMillionUsd":{"value":10,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://platform.claude.com/docs/en/models/overview","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":55.5,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"gemini-4-argon","provider":"Google","name":"Gemini 4 Argon","apiId":"gemini-4-argon","inputPerMillionUsd":{"value":2,"sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","sourceDate":"2026-10-14","note":{"en":"Standard paid tier through November 30, 2026. The listed rate becomes $4 input and $20 output on December 1, 2026.","zh":"标准付费档价格截至 2026-11-30。2026-12-01 起标价改为输入 $4、输出 $20。"}},"outputPerMillionUsd":{"value":10,"sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":52.9,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, High effort.","zh":"CursorBench 4.0，High effort。"}}},{"id":"claude-fable-5-1","provider":"Anthropic","name":"Claude Fable 5.1","apiId":"claude-fable-5-1","inputPerMillionUsd":{"value":10,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"outputPerMillionUsd":{"value":50,"sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://platform.claude.com/docs/en/models/overview","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":51.8,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"grok-4-7","provider":"xAI","name":"Grok 4.7","apiId":"grok-4.7","inputPerMillionUsd":{"value":2,"sourceUrl":"https://docs.x.ai/docs/models","sourceDate":"2026-10-14","note":{"en":"Price for prompts under 200K tokens. A prompt of 200K tokens or more is billed at $4 input and $12 output per 1M tokens for the whole request.","zh":"提示少于 200K token 的价格。达到 200K token 及以上时，整次请求按输入 $4、输出 $12（每百万 token）计费。"}},"outputPerMillionUsd":{"value":6,"sourceUrl":"https://docs.x.ai/docs/models","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":500000,"sourceUrl":"https://docs.x.ai/docs/models","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":46.3,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Extra High effort.","zh":"CursorBench 4.0，Extra High effort。"}}},{"id":"glm-5-3","provider":"Z.ai","name":"GLM-5.3","apiId":"glm-5.3","inputPerMillionUsd":{"value":1.4,"sourceUrl":"https://docs.z.ai/guides/overview/pricing","sourceDate":"2026-10-14","note":null},"outputPerMillionUsd":{"value":4.4,"sourceUrl":"https://docs.z.ai/guides/overview/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://docs.z.ai/guides/llm/glm-5.3","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":42.6,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"deepseek-v4-pro","provider":"DeepSeek","name":"DeepSeek V4 Pro","apiId":"deepseek-v4-pro","inputPerMillionUsd":{"value":1.32,"sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceDate":"2026-10-14","note":{"en":"Cache-miss price during peak hours (01:00–04:00 and 06:00–10:00 UTC, Monday–Friday, excluding Chinese public holidays). Off-peak is half. The docs list the model version as DeepSeek-V4-Pro-0813.","zh":"高峰时段缓存未命中价格（UTC 周一至周五 01:00–04:00 与 06:00–10:00，不含中国法定节假日）。非高峰为半价。文档中的模型版本是 DeepSeek-V4-Pro-0813。"}},"outputPerMillionUsd":{"value":3.96,"sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1000000,"sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":null},{"id":"gpt-5-6-sol","provider":"OpenAI","name":"GPT-5.6 Sol","apiId":"gpt-5.6-sol","inputPerMillionUsd":{"value":4,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol","sourceDate":"2026-10-14","note":{"en":"Prompts over 272K input tokens are billed at 2× input and 1.5× output for the whole request. OpenAI lists this rate as promotional at least through November 21, 2026.","zh":"输入超过 272K token 时，整次请求按输入 2 倍、输出 1.5 倍计费。 OpenAI 称此价格至少优惠到 2026-11-21。"}},"outputPerMillionUsd":{"value":20,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1050000,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":41.7,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"gpt-5-6-terra","provider":"OpenAI","name":"GPT-5.6 Terra","apiId":"gpt-5.6-terra","inputPerMillionUsd":{"value":2,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","sourceDate":"2026-10-14","note":{"en":"Prompts over 272K input tokens are billed at 2× input and 1.5× output for the whole request.","zh":"输入超过 272K token 时，整次请求按输入 2 倍、输出 1.5 倍计费。"}},"outputPerMillionUsd":{"value":12,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","sourceDate":"2026-10-14","note":null},"contextTokens":{"value":1050000,"sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","sourceDate":"2026-10-14","note":null},"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":41.3,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, Max effort.","zh":"CursorBench 4.0，Max effort。"}}},{"id":"gemini-3-8-flash","provider":"Google","name":"Gemini 3.8 Flash","apiId":"gemini-3.8-flash","inputPerMillionUsd":{"value":0.75,"sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","sourceDate":"2026-10-14","note":{"en":"Standard paid tier through December 31, 2026. The listed rate becomes $1.50 input and $7.50 output on January 1, 2027.","zh":"标准付费档价格截至 2026-12-31。2027-01-01 起标价改为输入 $1.50、输出 $7.50。"}},"outputPerMillionUsd":{"value":3.75,"sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","sourceDate":"2026-10-14","note":null},"contextTokens":null,"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":39.6,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0, High effort.","zh":"CursorBench 4.0，High effort。"}}},{"id":"composer-2-5","provider":"Cursor","name":"Composer 2.5","apiId":null,"inputPerMillionUsd":null,"outputPerMillionUsd":null,"contextTokens":null,"sweBenchVerifiedPercent":null,"cursorBenchPercent":{"value":27.7,"sourceUrl":"https://cursor.com/cursorbench","sourceDate":"2026-10-14","note":{"en":"CursorBench 4.0. The published row does not name an effort level.","zh":"CursorBench 4.0。公布的这一行没有标注 effort。"}}}]}