LLM API Pricing

Compare input, output and cache prices, context windows and release dates for 250 models from 21 providers. Claude prices come straight from Anthropic's official price list.

Updated Sep 24, 2026. Prices in USD per 1M tokens.

Cost calculator
Models compared
250
21 providers
Newest model
GLM 5.3 Prime
Z.ai, Sep 23, 2026
Recommended Claude model
Claude Opus 5.5
$4 input / $20 output
Lowest blended price
$0.032
Ling 3.0 Flash

Highlights: flagship models

Blended price

USD per 1M tokens, 3 input tokens per output token. Lower is cheaper.

  1. Claude Fable 5.1$20.00
  2. GPT-6 Astra$20.00
  3. Claude Opus 5.5$8.00
  4. Kimi K3$6.00
  5. Gemini 3.1 Pro Preview$4.50
  6. Claude Sonnet 5$4.00
  7. GPT-6 Sol$4.00
  8. Qwen3.8 Max (0902)$3.00
  9. Mistral Medium 3.5$3.00
  10. Grok 4.7$2.40
  11. GLM 5.3$2.15
  12. Claude Haiku 4.5$2.00
  13. Muse Spark 1.3$2.00
  14. Gemini 3.8 Flash$1.50
  15. DeepSeek V4 Pro 0813$0.69
  16. MiniMax M3$0.52

Context window

Maximum input tokens per request. Higher fits more code and documents.

  1. GLM 5.31.31M
  2. GPT-6 Astra1.05M
  3. GPT-6 Sol1.05M
  4. Gemini 3.1 Pro Preview1.05M
  5. Gemini 3.8 Flash1.05M
  6. Kimi K31.05M
  7. Muse Spark 1.31.05M
  8. DeepSeek V4 Pro 08131.05M
  9. MiniMax M31.05M
  10. Claude Fable 5.11M
  11. Claude Opus 5.51M
  12. Claude Sonnet 51M
  13. Qwen3.8 Max (0902)1M
  14. Grok 4.7500K
  15. Mistral Medium 3.5262K
  16. Claude Haiku 4.5200K

Price vs. release date

Blended price per 1M tokens on a log scale. Claude models are highlighted.

$0.1$1$10$10020252026GLM 5.3 Prime (Z.ai): $4.30 blended, released Sep 23, 2026Qwen3.8 Max Prime (Qwen): $6.00 blended, released Sep 23, 2026Command A+ (Cohere): $0.60 blended, released Sep 22, 2026GPT-6 Luna Pro (OpenAI): $0.20 blended, released Sep 22, 2026GPT-6 Luna (OpenAI): $0.20 blended, released Sep 22, 2026GPT-6 Sol Pro (OpenAI): $4.00 blended, released Sep 22, 2026GPT-6 Sol (OpenAI): $4.00 blended, released Sep 22, 2026MiMo-V2.6-Pro-UltraSpeed (Xiaomi): $5.44 blended, released Sep 21, 2026MiMo-V2.6-Flash (Xiaomi): $0.18 blended, released Sep 21, 2026MiMo-V2.6-Pro (Xiaomi): $0.54 blended, released Sep 21, 2026Grok 4.7 (xAI): $2.40 blended, released Sep 21, 2026Qwen3.8 Omni Flash (Qwen): $0.23 blended, released Sep 21, 2026GLM 5.3 FlashX (Z.ai): $0.59 blended, released Sep 18, 2026Ling 3.0 Flash VL (inclusionAI): $0.090 blended, released Sep 10, 2026DeepSeek V4.1 Flash (DeepSeek): $0.21 blended, released Sep 10, 2026GPT-6 Astra (OpenAI): $20.00 blended, released Sep 4, 2026GPT-6 Astra Pro (OpenAI): $20.00 blended, released Sep 4, 2026Qwen3.8 Max (0902) (Qwen): $3.00 blended, released Sep 3, 2026Muse Spark 1.3 Contributor (Meta): $0.13 blended, released Sep 2, 2026Muse Spark 1.3 (Meta): $2.00 blended, released Sep 2, 2026Gemini 3.8 Flash (Google): $1.50 blended, released Sep 2, 2026Hy4 preview (Tencent): $1.25 blended, released Aug 28, 2026Ling 3.0 Flash Fin (inclusionAI): $0.090 blended, released Aug 27, 2026Qwen3.8 Flash (Qwen): $0.23 blended, released Aug 26, 2026GLM 5.3 Flash (Z.ai): $0.24 blended, released Aug 26, 2026Muse Spark 1.2 Contributor (Meta): $0.13 blended, released Aug 21, 2026DeepSeek V4 Flash Vision Exp (DeepSeek): $0.33 blended, released Aug 21, 2026Hy-MT2-1.8B (Tencent): $0.077 blended, released Aug 20, 2026Hy-MT2-30B-A3B (Tencent): $0.13 blended, released Aug 20, 2026Hy-MT2-7B (Tencent): $0.13 blended, released Aug 19, 2026GLM 5.3 (Z.ai): $2.15 blended, released Aug 18, 2026Qwen3.8 27B (Qwen): $1.06 blended, released Aug 14, 2026Gemini 3.7 Flash (Google): $1.50 blended, released Aug 13, 2026Seed 2.1 Turbo (ByteDance): $1.00 blended, released Aug 12, 2026Qwen3.8 2.4T A95B (Qwen): $3.00 blended, released Aug 12, 2026Seed-2.0-Code (ByteDance): $1.13 blended, released Aug 12, 2026DeepSeek V4 Pro 0813 (DeepSeek): $0.69 blended, released Aug 12, 2026Grok 4.6 (xAI): $3.00 blended, released Aug 12, 2026Nemotron 3.5 Lightning (NVIDIA): $0.11 blended, released Aug 11, 2026Muse Glimmer 30B (Meta): $0.52 blended, released Aug 9, 2026Muse Spark 1.2 (Meta): $2.00 blended, released Aug 5, 2026DeepSeek V4 Flash 0731 (DeepSeek): $0.10 blended, released Jul 31, 2026Qwen3.7 Flash (Qwen): $0.055 blended, released Jul 27, 2026Ling 3.0 Flash (inclusionAI): $0.032 blended, released Jul 23, 2026Gemini 3.6 Flash (Google): $1.50 blended, released Jul 21, 2026Gemini 3.5 Flash Lite (Google): $0.85 blended, released Jul 21, 2026Kimi K3 (Moonshot AI): $6.00 blended, released Jul 16, 2026Muse Spark 1.1 (Meta): $2.00 blended, released Jul 16, 2026GPT-5.6 Luna Pro (OpenAI): $0.45 blended, released Jul 9, 2026GPT-5.6 Luna (OpenAI): $0.45 blended, released Jul 9, 2026GPT-5.6 Terra Pro (OpenAI): $4.50 blended, released Jul 9, 2026GPT-5.6 Terra (OpenAI): $4.50 blended, released Jul 9, 2026GPT-5.6 Sol Pro (OpenAI): $4.00 blended, released Jul 9, 2026GPT-5.6 Sol (OpenAI): $4.00 blended, released Jul 9, 2026Grok 4.5 (xAI): $3.00 blended, released Jul 8, 2026Hy3 (Tencent): $0.23 blended, released Jul 6, 2026GLM 5.2 (Z.ai): $1.00 blended, released Jun 16, 2026Kimi K2.7 Code (Moonshot AI): $1.32 blended, released Jun 12, 2026Nemotron 3.5 Content Safety (NVIDIA): $0.20 blended, released Jun 4, 2026Nemotron 3 Ultra (NVIDIA): $1.05 blended, released Jun 4, 2026Qwen3.7 Plus (Qwen): $0.56 blended, released Jun 3, 2026MiniMax M3 (MiniMax): $0.52 blended, released May 31, 2026Qwen3.7 Max (Qwen): $2.21 blended, released May 21, 2026Grok Build 0.1 (xAI): $1.25 blended, released May 20, 2026Gemini 3.5 Flash (Google): $3.38 blended, released May 19, 2026Gemini 3.1 Flash Lite (Google): $0.56 blended, released May 7, 2026GPT Chat Latest (OpenAI): $11.25 blended, released May 5, 2026Grok 4.3 (xAI): $1.56 blended, released Apr 30, 2026Mistral Medium 3.5 (Mistral): $3.00 blended, released Apr 30, 2026Qwen3.5 Plus 2026-04-20 (Qwen): $0.68 blended, released Apr 27, 2026Qwen3.6 Flash (Qwen): $0.42 blended, released Apr 27, 2026Qwen3.6 35B A3B (Qwen): $0.36 blended, released Apr 27, 2026Qwen3.6 Max Preview (Qwen): $2.31 blended, released Apr 27, 2026Qwen3.6 27B (Qwen): $0.92 blended, released Apr 27, 2026GPT-5.5 Pro (OpenAI): $67.50 blended, released Apr 24, 2026GPT-5.5 (OpenAI): $11.25 blended, released Apr 24, 2026DeepSeek V4 Pro 0423 (DeepSeek): $1.17 blended, released Apr 24, 2026DeepSeek V4 Flash 0423 (DeepSeek): $0.11 blended, released Apr 24, 2026Hy3 preview (Tencent): $0.29 blended, released Apr 22, 2026MiMo-V2.5-Pro (Xiaomi): $0.54 blended, released Apr 22, 2026MiMo-V2.5 (Xiaomi): $0.18 blended, released Apr 22, 2026Kimi K2.6 (Moonshot AI): $1.71 blended, released Apr 20, 2026GLM 5.1 (Z.ai): $1.48 blended, released Apr 7, 2026Gemma 4 26B A4B (Google): $0.14 blended, released Apr 3, 2026Gemma 4 31B (Google): $0.15 blended, released Apr 2, 2026Qwen3.6 Plus (Qwen): $0.73 blended, released Apr 2, 2026GLM 5V Turbo (Z.ai): $1.90 blended, released Apr 1, 2026Grok 4.20 Multi-Agent (xAI): $1.56 blended, released Mar 31, 2026Grok 4.20 (xAI): $1.56 blended, released Mar 31, 2026MiniMax M2.7 (MiniMax): $0.52 blended, released Mar 18, 2026GPT-5.4 Nano (OpenAI): $0.46 blended, released Mar 17, 2026GPT-5.4 Mini (OpenAI): $1.69 blended, released Mar 17, 2026Mistral Small 4 (Mistral): $0.26 blended, released Mar 16, 2026GLM 5 Turbo (Z.ai): $1.90 blended, released Mar 15, 2026Nemotron 3 Super (NVIDIA): $0.17 blended, released Mar 11, 2026Seed-2.0-Lite (ByteDance): $0.69 blended, released Mar 10, 2026Qwen3.5-9B (Qwen): $0.11 blended, released Mar 10, 2026GPT-5.4 Pro (OpenAI): $67.50 blended, released Mar 5, 2026GPT-5.4 (OpenAI): $5.63 blended, released Mar 5, 2026Gemini 3.1 Flash Lite Preview (Google): $0.56 blended, released Mar 3, 2026Seed-2.0-Mini (ByteDance): $0.18 blended, released Feb 26, 2026Qwen3.5-35B-A3B (Qwen): $0.55 blended, released Feb 25, 2026Qwen3.5-27B (Qwen): $0.54 blended, released Feb 25, 2026Qwen3.5-122B-A10B (Qwen): $0.72 blended, released Feb 25, 2026Qwen3.5-Flash (Qwen): $0.11 blended, released Feb 25, 2026Gemini 3.1 Pro Preview Custom Tools (Google): $4.50 blended, released Feb 25, 2026GPT-5.3-Codex (OpenAI): $4.81 blended, released Feb 24, 2026Gemini 3.1 Pro Preview (Google): $4.50 blended, released Feb 19, 2026Qwen3.5 Plus 2026-02-15 (Qwen): $0.58 blended, released Feb 16, 2026Qwen3.5 397B A17B (Qwen): $1.29 blended, released Feb 16, 2026MiniMax M2.5 (MiniMax): $0.47 blended, released Feb 12, 2026GLM 5 (Z.ai): $0.93 blended, released Feb 11, 2026Qwen3 Max Thinking (Qwen): $1.56 blended, released Feb 9, 2026Qwen3 Coder Next (Qwen): $0.29 blended, released Feb 4, 2026Kimi K2.5 (Moonshot AI): $0.90 blended, released Jan 27, 2026MiniMax M2-her (MiniMax): $0.52 blended, released Jan 23, 2026GLM 4.7 Flash (Z.ai): $0.15 blended, released Jan 19, 2026GPT-5.2-Codex (OpenAI): $4.81 blended, released Jan 14, 2026Seed 1.6 Flash (ByteDance): $0.13 blended, released Dec 23, 2025Seed 1.6 (ByteDance): $0.69 blended, released Dec 23, 2025MiniMax M2.1 (MiniMax): $0.52 blended, released Dec 23, 2025GLM 4.7 (Z.ai): $0.74 blended, released Dec 22, 2025Gemini 3 Flash Preview (Google): $1.13 blended, released Dec 17, 2025Nemotron 3 Nano 30B A3B (NVIDIA): $0.088 blended, released Dec 14, 2025GPT-5.2 Chat (OpenAI): $4.81 blended, released Dec 10, 2025GPT-5.2 Pro (OpenAI): $57.75 blended, released Dec 10, 2025GPT-5.2 (OpenAI): $4.81 blended, released Dec 10, 2025GLM 4.6V (Z.ai): $0.45 blended, released Dec 8, 2025GPT-5.1-Codex-Max (OpenAI): $3.44 blended, released Dec 4, 2025Nova 2 Lite (Amazon): $0.85 blended, released Dec 2, 2025Ministral 3 14B 2512 (Mistral): $0.20 blended, released Dec 2, 2025Ministral 3 8B 2512 (Mistral): $0.15 blended, released Dec 2, 2025Ministral 3 3B 2512 (Mistral): $0.10 blended, released Dec 2, 2025DeepSeek V3.2 (DeepSeek): $0.30 blended, released Dec 1, 2025GPT-5.1 (OpenAI): $3.44 blended, released Nov 13, 2025GPT-5.1-Codex (OpenAI): $3.44 blended, released Nov 13, 2025GPT-5.1-Codex-Mini (OpenAI): $0.69 blended, released Nov 13, 2025Kimi K2 Thinking (Moonshot AI): $1.07 blended, released Nov 6, 2025Nova Premier 1.0 (Amazon): $5.00 blended, released Oct 31, 2025Sonar Pro Search (Perplexity): $6.00 blended, released Oct 30, 2025Voxtral Small 24B 2507 (Mistral): $0.15 blended, released Oct 30, 2025gpt-oss-safeguard-20b (OpenAI): $0.13 blended, released Oct 29, 2025MiniMax M2 (MiniMax): $0.52 blended, released Oct 23, 2025Qwen3 VL 32B Instruct (Qwen): $0.18 blended, released Oct 23, 2025Qwen3 VL 8B Thinking (Qwen): $0.66 blended, released Oct 14, 2025Qwen3 VL 8B Instruct (Qwen): $0.20 blended, released Oct 14, 2025Qwen3 VL 30B A3B Thinking (Qwen): $0.75 blended, released Oct 6, 2025Qwen3 VL 30B A3B Instruct (Qwen): $0.23 blended, released Oct 6, 2025GPT-5 Pro (OpenAI): $41.25 blended, released Oct 6, 2025GLM 4.6 (Z.ai): $0.76 blended, released Sep 30, 2025DeepSeek V3.2 Exp (DeepSeek): $0.30 blended, released Sep 29, 2025Qwen3 VL 235B A22B Thinking (Qwen): $1.30 blended, released Sep 23, 2025Qwen3 VL 235B A22B Instruct (Qwen): $0.63 blended, released Sep 23, 2025Qwen3 Max (Qwen): $1.56 blended, released Sep 23, 2025Qwen3 Coder Plus (Qwen): $1.30 blended, released Sep 23, 2025DeepSeek V3.1 Terminus (DeepSeek): $0.45 blended, released Sep 22, 2025Qwen3 Coder Flash (Qwen): $0.39 blended, released Sep 17, 2025Qwen3 Next 80B A3B Thinking (Qwen): $0.41 blended, released Sep 11, 2025Qwen3 Next 80B A3B Instruct (Qwen): $0.35 blended, released Sep 11, 2025Qwen Plus 0728 (Qwen): $0.39 blended, released Sep 8, 2025Kimi K2 0905 (Moonshot AI): $1.07 blended, released Sep 4, 2025Qwen3 30B A3B Thinking 2507 (Qwen): $0.75 blended, released Aug 28, 2025DeepSeek V3.1 (DeepSeek): $0.42 blended, released Aug 21, 2025Mistral Medium 3.1 (Mistral): $0.80 blended, released Aug 13, 2025GLM 4.5V (Z.ai): $0.90 blended, released Aug 11, 2025GPT-5 (OpenAI): $3.44 blended, released Aug 7, 2025GPT-5 Mini (OpenAI): $0.69 blended, released Aug 7, 2025GPT-5 Nano (OpenAI): $0.14 blended, released Aug 7, 2025gpt-oss-120b (OpenAI): $0.26 blended, released Aug 5, 2025gpt-oss-20b (OpenAI): $0.036 blended, released Aug 5, 2025Codestral 2508 (Mistral): $0.45 blended, released Aug 1, 2025Qwen3 Coder 30B A3B Instruct (Qwen): $0.12 blended, released Jul 31, 2025Qwen3 30B A3B Instruct 2507 (Qwen): $0.15 blended, released Jul 29, 2025GLM 4.5 (Z.ai): $1.00 blended, released Jul 25, 2025GLM 4.5 Air (Z.ai): $0.31 blended, released Jul 25, 2025Qwen3 235B A22B Thinking 2507 (Qwen): $0.75 blended, released Jul 25, 2025Qwen3 Coder 480B A35B (Qwen): $0.47 blended, released Jul 23, 2025Gemini 2.5 Flash Lite (Google): $0.18 blended, released Jul 22, 2025Qwen3 235B A22B Instruct 2507 (Qwen): $0.15 blended, released Jul 21, 2025Kimi K2 0711 (Moonshot AI): $1.00 blended, released Jul 11, 2025Hunyuan A13B Instruct (Tencent): $0.25 blended, released Jul 8, 2025ERNIE 4.5 VL 424B A47B (Baidu): $0.63 blended, released Jun 30, 2025Mistral Small 3.2 24B (Mistral): $0.13 blended, released Jun 20, 2025MiniMax M1 (MiniMax): $0.85 blended, released Jun 17, 2025Gemini 2.5 Flash (Google): $0.85 blended, released Jun 17, 2025Gemini 2.5 Pro (Google): $3.44 blended, released Jun 17, 2025o3 Pro (OpenAI): $35.00 blended, released Jun 10, 2025Gemini 2.5 Pro Preview 06-05 (Google): $3.44 blended, released Jun 5, 2025R1 0528 (DeepSeek): $0.91 blended, released May 28, 2025Mistral Medium 3 (Mistral): $0.80 blended, released May 7, 2025Llama Guard 4 12B (Meta): $0.18 blended, released Apr 30, 2025Qwen3 30B A3B (Qwen): $0.21 blended, released Apr 28, 2025Qwen3 8B (Qwen): $0.20 blended, released Apr 28, 2025Qwen3 14B (Qwen): $0.15 blended, released Apr 28, 2025Qwen3 32B (Qwen): $0.13 blended, released Apr 28, 2025Qwen3 235B A22B (Qwen): $0.80 blended, released Apr 28, 2025o4 Mini High (OpenAI): $1.93 blended, released Apr 16, 2025o3 (OpenAI): $3.50 blended, released Apr 16, 2025o4 Mini (OpenAI): $1.93 blended, released Apr 16, 2025GPT-4.1 (OpenAI): $3.50 blended, released Apr 14, 2025GPT-4.1 Mini (OpenAI): $0.70 blended, released Apr 14, 2025GPT-4.1 Nano (OpenAI): $0.18 blended, released Apr 14, 2025Llama 4 Maverick (Meta): $0.30 blended, released Apr 5, 2025Llama 4 Scout (Meta): $0.15 blended, released Apr 5, 2025DeepSeek V3 0324 (DeepSeek): $0.44 blended, released Mar 24, 2025o1-pro (OpenAI): $262.50 blended, released Mar 19, 2025Mistral Small 3.1 24B (Mistral): $0.40 blended, released Mar 17, 2025Gemma 3 4B (Google): $0.063 blended, released Mar 13, 2025Gemma 3 12B (Google): $0.075 blended, released Mar 13, 2025Command A (Cohere): $4.38 blended, released Mar 13, 2025Gemma 3 27B (Google): $0.17 blended, released Mar 12, 2025Sonar Reasoning Pro (Perplexity): $3.50 blended, released Mar 7, 2025Sonar Pro (Perplexity): $6.00 blended, released Mar 7, 2025Sonar Deep Research (Perplexity): $3.50 blended, released Mar 7, 2025Saba (Mistral): $0.30 blended, released Feb 17, 2025o3 Mini High (OpenAI): $1.93 blended, released Feb 12, 2025Qwen2.5 VL 72B Instruct (Qwen): $0.85 blended, released Feb 1, 2025Qwen-Plus (Qwen): $0.39 blended, released Feb 1, 2025o3 Mini (OpenAI): $1.93 blended, released Jan 31, 2025Mistral Small 3 (Mistral): $0.058 blended, released Jan 30, 2025Sonar (Perplexity): $1.00 blended, released Jan 27, 2025R1 Distill Llama 70B (DeepSeek): $0.80 blended, released Jan 23, 2025R1 (DeepSeek): $1.15 blended, released Jan 20, 2025MiniMax-01 (MiniMax): $0.43 blended, released Jan 15, 2025Phi 4 (Microsoft): $0.088 blended, released Jan 10, 2025DeepSeek V3 (DeepSeek): $0.46 blended, released Dec 26, 2024o1 (OpenAI): $26.25 blended, released Dec 17, 2024Command R7B (12-2024) (Cohere): $0.066 blended, released Dec 14, 2024Llama 3.3 70B Instruct (Meta): $0.16 blended, released Dec 6, 2024Nova Lite 1.0 (Amazon): $0.10 blended, released Dec 5, 2024Nova Micro 1.0 (Amazon): $0.061 blended, released Dec 5, 2024Nova Pro 1.0 (Amazon): $1.40 blended, released Dec 5, 2024GPT-4o (2024-11-20) (OpenAI): $4.38 blended, released Nov 20, 2024Mistral Large 2407 (Mistral): $3.00 blended, released Nov 19, 2024Qwen2.5 Coder 32B Instruct (Qwen): $0.74 blended, released Nov 11, 2024Qwen2.5 7B Instruct (Qwen): $0.13 blended, released Oct 16, 2024Llama 3.2 1B Instruct (Meta): $0.071 blended, released Sep 25, 2024Llama 3.2 3B Instruct (Meta): $0.12 blended, released Sep 25, 2024Claude Opus 5.5 (Anthropic): $8.00 blended, released Sep 22, 2026Claude Fable 5.1 (Anthropic): $20.00 blended, released Sep 1, 2026Claude Opus 5 (Anthropic): $10.00 blended, released Jul 24, 2026Claude Sonnet 5 (Anthropic): $4.00 blended, released Jun 30, 2026Claude Fable 5 (Anthropic): $20.00 blended, released Jun 9, 2026Claude Opus 4.8 (Anthropic): $10.00 blended, released May 27, 2026Claude Opus 4.7 (Anthropic): $10.00 blended, released Apr 16, 2026Claude Sonnet 4.6 (Anthropic): $6.00 blended, released Feb 17, 2026Claude Opus 4.6 (Anthropic): $10.00 blended, released Feb 4, 2026Claude Opus 4.5 (Anthropic): $10.00 blended, released Nov 24, 2025Claude Haiku 4.5 (Anthropic): $2.00 blended, released Oct 15, 2025Claude Sonnet 4.5 (Anthropic): $6.00 blended, released Sep 29, 2025

Claude API pricing

Official first-party rates from Anthropic. Batch requests are 50% off. Cache reads cost 10% of the base input price (2.5% on Fable 5.1, 5% on Opus 5.5).

Claude Fable 5.1

Slower

For demanding reasoning and long-horizon agentic work

$10.00in$50.00out
Context
1M
Max output
128K
Knowledge
Jun 2026
Thinking
Adaptive (always on)
claude-fable-5-1

Claude Opus 5.5

Moderate

For long-running agentic coding and knowledge work

$4.00in$20.00out
Context
1M
Max output
128K
Knowledge
Jun 2026
Thinking
Adaptive (always on)
claude-opus-5-5

Claude Sonnet 5

Fast

The best combination of speed and intelligence

$2.00in$10.00out
Context
1M
Max output
128K
Knowledge
Jan 2026
Thinking
Adaptive
claude-sonnet-5

Claude Haiku 4.5

Fastest

The fastest model with near-frontier intelligence

$1.00in$5.00out
Context
200K
Max output
64K
Knowledge
Feb 2025
Thinking
Extended
claude-haiku-4-5
Claude API prices per million tokens
ModelInputOutput5m cache write1h cache writeCache readBatch in / outContext
Claude Fable 5.1
claude-fable-5-1
$10.00$50.00$12.50$20.00$0.25$5.00 / $25.001M
Claude Opus 5.5
claude-opus-5-5
$4.00$20.00$5.00$8.00$0.20$2.00 / $10.001M
Claude Sonnet 5
claude-sonnet-5
$2.00$10.00$2.50$4.00$0.20$1.00 / $5.001M
Claude Haiku 4.5
claude-haiku-4-5
$1.00$5.00$1.25$2.00$0.10$0.50 / $2.50200K
Claude Fable 5Legacy
claude-fable-5
$10.00$50.00$12.50$20.00$1.00$5.00 / $25.001M
Claude Opus 5Legacy
claude-opus-5
$5.00$25.00$6.25$10.00$0.50$2.50 / $12.501M
Claude Opus 4.8Legacy
claude-opus-4-8
$5.00$25.00$6.25$10.00$0.50$2.50 / $12.501M
Claude Opus 4.7Legacy
claude-opus-4-7
$5.00$25.00$6.25$10.00$0.50$2.50 / $12.501M
Claude Opus 4.6Legacy
claude-opus-4-6
$5.00$25.00$6.25$10.00$0.50$2.50 / $12.501M
Claude Sonnet 4.6Legacy
claude-sonnet-4-6
$3.00$15.00$3.75$6.00$0.30$1.50 / $7.501M
Claude Opus 4.5Legacy
claude-opus-4-5
$5.00$25.00$6.25$10.00$0.50$2.50 / $12.50200K
Claude Sonnet 4.5Legacy
claude-sonnet-4-5
$3.00$15.00$3.75$6.00$0.30$1.50 / $7.50200K

Source: Anthropic pricing docs, checked Sep 24, 2026. US-only inference adds 10%. Amazon Bedrock and Google Cloud set their own prices.

All models

GLM 5.3 Prime
Z.ai
$2.80$8.80$4.30$0.561MSep 23, 2026
Qwen3.8 Max Prime
Qwen
$4.00$12.00$6.00$0.501MSep 23, 2026
Claude Opus 5.5
Anthropic
$4.00$20.00$8.00$0.201MSep 22, 2026
Command A+
Cohere
$0.30$1.50$0.60$0.15192KSep 22, 2026
GPT-6 Luna Pro
OpenAI
$0.10$0.50$0.20$0.0101.05MSep 22, 2026
GPT-6 Luna
OpenAI
$0.10$0.50$0.20$0.0101.05MSep 22, 2026
GPT-6 Sol Pro
OpenAI
$2.00$10.00$4.00$0.201.05MSep 22, 2026
GPT-6 Sol
OpenAI
$2.00$10.00$4.00$0.201.05MSep 22, 2026
MiMo-V2.6-Pro-UltraSpeed
Xiaomi
$4.35$8.70$5.44$0.0361.05MSep 21, 2026
MiMo-V2.6-FlashOpen
Xiaomi
$0.14$0.28$0.18$0.0031.05MSep 21, 2026
MiMo-V2.6-ProOpen
Xiaomi
$0.43$0.87$0.54$0.0041.05MSep 21, 2026
Grok 4.7
xAI
$1.60$4.80$2.40$0.40500KSep 21, 2026
Qwen3.8 Omni Flash
Qwen
$0.15$0.47$0.23$0.0161MSep 21, 2026
GLM 5.3 FlashX
Z.ai
$0.37$1.25$0.59$0.0901.05MSep 18, 2026
Ling 3.0 Flash VLOpen
inclusionAI
$0.060$0.18$0.090$0.012262KSep 10, 2026
DeepSeek V4.1 FlashOpen
DeepSeek
$0.14$0.42$0.21$0.0041.05MSep 10, 2026
GPT-6 Astra
OpenAI
$10.00$50.00$20.00$1.001.05MSep 4, 2026
GPT-6 Astra Pro
OpenAI
$10.00$50.00$20.00$1.001.05MSep 4, 2026
Qwen3.8 Max (0902)
Qwen
$2.00$6.00$3.00$0.251MSep 3, 2026
Muse Spark 1.3 Contributor
Meta
$0.10$0.20$0.13$0.0021.05MSep 2, 2026
Muse Spark 1.3
Meta
$1.25$4.25$2.00$0.151.05MSep 2, 2026
Gemini 3.8 Flash
Google
$0.75$3.75$1.50$0.0751.05MSep 2, 2026
Claude Fable 5.1
Anthropic
$10.00$50.00$20.00$0.251MSep 1, 2026
Hy4 previewOpen
Tencent
$0.83$2.50$1.25$0.0421.05MAug 28, 2026
Ling 3.0 Flash Fin
inclusionAI
$0.060$0.18$0.090$0.012262KAug 27, 2026
Qwen3.8 FlashOpen
Qwen
$0.15$0.47$0.23$0.0161MAug 26, 2026
GLM 5.3 FlashOpen
Z.ai
$0.15$0.50$0.24$0.0501.31MAug 26, 2026
Muse Spark 1.2 Contributor
Meta
$0.10$0.20$0.13$0.0021.05MAug 21, 2026
DeepSeek V4 Flash Vision ExpOpen
DeepSeek
$0.22$0.66$0.33$0.0071.05MAug 21, 2026
Hy-MT2-1.8BOpen
Tencent
$0.044$0.18$0.077-8KAug 20, 2026
Hy-MT2-30B-A3BOpen
Tencent
$0.074$0.29$0.13-8KAug 20, 2026
Hy-MT2-7BOpen
Tencent
$0.074$0.29$0.13-8KAug 19, 2026
GLM 5.3Open
Z.ai
$1.40$4.40$2.15$0.261.31MAug 18, 2026
Qwen3.8 27BOpen
Qwen
$0.42$3.00$1.06$0.0851MAug 14, 2026
Gemini 3.7 Flash
Google
$0.75$3.75$1.50$0.0751.05MAug 13, 2026
Seed 2.1 Turbo
ByteDance
$0.50$2.50$1.00-262KAug 12, 2026
Qwen3.8 2.4T A95BOpen
Qwen
$2.00$6.00$3.00$0.251.05MAug 12, 2026
Seed-2.0-Code
ByteDance
$0.50$3.00$1.13-262KAug 12, 2026
DeepSeek V4 Pro 0813Open
DeepSeek
$0.46$1.39$0.69$0.0151.05MAug 12, 2026
Grok 4.6
xAI
$2.00$6.00$3.00$0.50500KAug 12, 2026
Showing 40 of 250 models. Prices in USD per 1M tokens.

Questions about LLM API pricing

How much does the Claude API cost?

Claude Opus 5.5 costs $4 per million input tokens and $20 per million output tokens. Claude Sonnet 5 costs $2 and $10, Claude Haiku 4.5 costs $1 and $5, and Claude Fable 5.1 costs $10 and $50. The Batch API halves these prices, and cached input is billed at a fraction of the base input price.

What is the blended price?

The blended price assumes 3 input tokens for every output token, which is close to a typical chat or coding workload. It gives one number per model so you can compare them quickly. Use the cost calculator for your own mix of input and output.

Where does this data come from?

Claude prices come from Anthropic's official pricing page (checked Sep 24, 2026). Prices for other providers come from the public OpenRouter model catalog, which lists each provider's pay-as-you-go rate. Direct contracts, regional endpoints and cloud marketplaces can be priced differently.

Why can the same prompt cost more on a newer model with the same price?

Tokenizers differ between models. Anthropic notes that Claude 4.7 and later use a newer tokenizer that produces roughly 30% more tokens for the same text, so compare the cost of real requests, not only the per-token price.