Cost per 1000 tokens
Model pricing normalized to cost per 1,000 tokens, sorted cheapest first.
| Model | Provider | Input / 1k | Cached / 1k | Output / 1k |
|---|---|---|---|---|
| North Mini Code cheapest input | Cohere | $0 | n/a | $0 |
| Lyria 3 Clip Preview | $0 | n/a | $0 | |
| Lyria 3 Pro Preview | $0 | n/a | $0 | |
| Devstral Small 2 | Mistral | $0 | n/a | $0 |
| GLM-4.5-Flash | Zhipu AI | $0 | $0 | $0 |
| GLM-4.7-Flash | Zhipu AI | $0 | $0 | $0 |
| text-embedding-3-small | OpenAI | $0.000020 | n/a | $0 |
| Qwen3-ASR Flash | Alibaba | $0.000035 | n/a | $0.000035 |
| Command R7B | Cohere | $0.000037 | n/a | $0.00015 |
| Command R7B Arabic | Cohere | $0.000037 | n/a | $0.00015 |
| Ministral 3B (latest) | Mistral | $0.000040 | n/a | $0.000040 |
| Qwen Flash | Alibaba | $0.000050 | n/a | $0.00040 |
| Qwen Turbo | Alibaba | $0.000050 | n/a | $0.00020 |
| GPT-5 Nano | OpenAI | $0.000050 | $0.0000050 | $0.00040 |
| Qwen-Omni Turbo | Alibaba | $0.000070 | n/a | $0.00027 |
| GLM-4.7-FlashX | Zhipu AI | $0.000070 | $0.000010 | $0.00040 |
| Gemini 2.0 Flash-Lite | $0.000075 | n/a | $0.00030 | |
| Qwen2.5-Omni 7B | Alibaba | $0.00010 | n/a | $0.00040 |
| Gemini 2.0 Flash | $0.00010 | $0.000025 | $0.00040 | |
| Gemini 2.5 Flash-Lite | $0.00010 | $0.000010 | $0.00040 | |
| Devstral Small | Mistral | $0.00010 | n/a | $0.00030 |
| Devstral Small 2505 | Mistral | $0.00010 | n/a | $0.00030 |
| Ministral 8B (latest) | Mistral | $0.00010 | n/a | $0.00010 |
| Mistral Embed | Mistral | $0.00010 | n/a | $0 |
| Mistral Small 3.2 | Mistral | $0.00010 | n/a | $0.00030 |
| Voxtral Small (latest) | Mistral | $0.00010 | n/a | $0.00030 |
| GPT-4.1 nano | OpenAI | $0.00010 | $0.000025 | $0.00040 |
| text-embedding-ada-002 | OpenAI | $0.00010 | n/a | $0 |
| text-embedding-3-large | OpenAI | $0.00013 | n/a | $0 |
| DeepSeek Chat | DeepSeek | $0.00014 | $0.0000028 | $0.00028 |
| DeepSeek Reasoner | DeepSeek | $0.00014 | $0.0000028 | $0.00028 |
| DeepSeek V4 Flash | DeepSeek | $0.00014 | $0.0000028 | $0.00028 |
| Command R | Cohere | $0.00015 | n/a | $0.00060 |
| Gemini Embedding 001 | $0.00015 | n/a | $0 | |
| Mistral Nemo | Mistral | $0.00015 | n/a | $0.00015 |
| Mistral Small (latest) | Mistral | $0.00015 | n/a | $0.00060 |
| Mistral Small 4 | Mistral | $0.00015 | n/a | $0.00060 |
| Open Mistral Nemo | Mistral | $0.00015 | n/a | $0.00015 |
| Pixtral 12B | Mistral | $0.00015 | n/a | $0.00015 |
| GPT-4o mini | OpenAI | $0.00015 | $0.000075 | $0.00060 |
| Qwen-MT Turbo | Alibaba | $0.00016 | n/a | $0.00049 |
| Qwen2.5 7B Instruct | Alibaba | $0.00017 | n/a | $0.00070 |
| Qwen3 8B | Alibaba | $0.00018 | n/a | $0.00070 |
| Qwen3.6 Flash | Alibaba | $0.00019 | n/a | $0.0011 |
| Qwen3-VL 30B-A3B | Alibaba | $0.00020 | n/a | $0.00080 |
| Qwen3-VL Plus | Alibaba | $0.00020 | n/a | $0.0016 |
| Gemini Embedding 2 | $0.00020 | n/a | $0 | |
| GPT-5.4 nano | OpenAI | $0.00020 | $0.000020 | $0.0013 |
| GPT-5.6 Luna | OpenAI | $0.00020 | $0.000020 | $0.0012 |
| GLM-4.5-Air | Zhipu AI | $0.00020 | $0.000030 | $0.0011 |
| Qwen-VL Plus | Alibaba | $0.00021 | n/a | $0.00063 |
| Qwen3.6 35B-A3B | Alibaba | $0.00025 | n/a | $0.0015 |
| Qwen3.5 35B-A3B | Alibaba | $0.00025 | n/a | $0.0020 |
| Gemini 3.1 Flash Lite | $0.00025 | $0.000025 | $0.0015 | |
| Gemini 3.1 Flash Lite Preview | $0.00025 | $0.000025 | $0.0015 | |
| Gemini Flash-Lite Latest | $0.00025 | $0.000025 | $0.0015 | |
| Nano Banana 2 Lite | $0.00025 | n/a | $0.030 | |
| Mistral 7B | Mistral | $0.00025 | n/a | $0.00025 |
| GPT-5 Mini | OpenAI | $0.00025 | $0.000025 | $0.0020 |
| Qwen-Omni Turbo Realtime | Alibaba | $0.00027 | n/a | $0.0011 |
| Qwen3 Coder Flash | Alibaba | $0.00030 | n/a | $0.0015 |
| Qwen3.5 27B | Alibaba | $0.00030 | n/a | $0.0024 |
| Gemini 2.5 Flash | $0.00030 | $0.000030 | $0.0025 | |
| Gemini 3.5 Flash Lite | $0.00030 | $0.000030 | $0.0025 | |
| Nano Banana | $0.00030 | $0.000075 | $0.030 | |
| MiniMax-M2 | MiniMax (minimax.io) | $0.00030 | n/a | $0.0012 |
| MiniMax-M2.1 | MiniMax (minimax.io) | $0.00030 | $0.000030 | $0.0012 |
| MiniMax-M2.5 | MiniMax (minimax.io) | $0.00030 | $0.000030 | $0.0012 |
| MiniMax-M2.7 | MiniMax (minimax.io) | $0.00030 | $0.000060 | $0.0012 |
| MiniMax-M3 | MiniMax (minimax.io) | $0.00030 | $0.000060 | $0.0012 |
| Codestral (latest) | Mistral | $0.00030 | n/a | $0.00090 |
| GLM-4.6V | Zhipu AI | $0.00030 | n/a | $0.00090 |
| Qwen2.5 14B Instruct | Alibaba | $0.00035 | n/a | $0.0014 |
| Qwen2.5-VL 7B Instruct | Alibaba | $0.00035 | n/a | $0.0011 |
| Qwen3 14B | Alibaba | $0.00035 | n/a | $0.0014 |
| Qwen Plus | Alibaba | $0.00040 | n/a | $0.0012 |
| Qwen3.5 122B-A10B | Alibaba | $0.00040 | n/a | $0.0032 |
| Qwen3.5 Plus | Alibaba | $0.00040 | n/a | $0.0024 |
| Devstral 2 | Mistral | $0.00040 | n/a | $0.0020 |
| Devstral 2 | Mistral | $0.00040 | n/a | $0.0020 |
| Devstral 2 (latest) | Mistral | $0.00040 | n/a | $0.0020 |
| Devstral Medium | Mistral | $0.00040 | n/a | $0.0020 |
| Mistral Medium 3 | Mistral | $0.00040 | n/a | $0.0020 |
| Mistral Medium 3.1 | Mistral | $0.00040 | n/a | $0.0020 |
| GPT-4.1 mini | OpenAI | $0.00040 | $0.00010 | $0.0016 |
| Qwen3-Omni Flash | Alibaba | $0.00043 | n/a | $0.0017 |
| DeepSeek V4 Pro | DeepSeek | $0.00044 | $0.0000036 | $0.00087 |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.00045 | n/a | $0.0022 |
| Qwen Plus Character (Japanese) | Alibaba | $0.00050 | n/a | $0.0014 |
| Qwen3-Next 80B-A3B (Thinking) | Alibaba | $0.00050 | n/a | $0.0060 |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.00050 | n/a | $0.0020 |
| Qwen3.6 Plus | Alibaba | $0.00050 | $0.000050 | $0.0030 |
| Qwen3.7 Plus | Alibaba | $0.00050 | $0.000050 | $0.0030 |
| Gemini 3 Flash Preview | $0.00050 | $0.000050 | $0.0030 | |
| Nano Banana 2 | $0.00050 | n/a | $0.060 | |
| Nano Banana 2 | $0.00050 | n/a | $0.060 | |
| Magistral Small | Mistral | $0.00050 | n/a | $0.0015 |
| Mistral Large (latest) | Mistral | $0.00050 | n/a | $0.0015 |
| Mistral Large 3 | Mistral | $0.00050 | n/a | $0.0015 |
| GPT-3.5-turbo | OpenAI | $0.00050 | $0 | $0.0015 |
| Qwen3-Omni Flash Realtime | Alibaba | $0.00052 | n/a | $0.0020 |
| Qwen3.5 397B-A17B | Alibaba | $0.00060 | n/a | $0.0036 |
| Qwen3.6 27B | Alibaba | $0.00060 | n/a | $0.0036 |
| MiniMax-M2.5-highspeed | MiniMax (minimax.io) | $0.00060 | $0.000060 | $0.0024 |
| MiniMax-M2.7-highspeed | MiniMax (minimax.io) | $0.00060 | $0.000060 | $0.0024 |
| Kimi K2 0711 | Moonshot AI | $0.00060 | $0.00015 | $0.0025 |
| Kimi K2 0905 | Moonshot AI | $0.00060 | $0.00015 | $0.0025 |
| Kimi K2 Thinking | Moonshot AI | $0.00060 | $0.00015 | $0.0025 |
| Kimi K2.5 | Moonshot AI | $0.00060 | $0.00010 | $0.0030 |
| GLM-4.5 | Zhipu AI | $0.00060 | $0.00011 | $0.0022 |
| GLM-4.5V | Zhipu AI | $0.00060 | n/a | $0.0018 |
| GLM-4.6 | Zhipu AI | $0.00060 | $0.00011 | $0.0022 |
| GLM-4.7 | Zhipu AI | $0.00060 | $0.00011 | $0.0022 |
| Qwen2.5 32B Instruct | Alibaba | $0.00070 | n/a | $0.0028 |
| Qwen3 235B-A22B | Alibaba | $0.00070 | n/a | $0.0028 |
| Qwen3 32B | Alibaba | $0.00070 | n/a | $0.0028 |
| Qwen3-VL 235B-A22B | Alibaba | $0.00070 | n/a | $0.0028 |
| Mixtral 8x7B | Mistral | $0.00070 | n/a | $0.00070 |
| Qwen-VL OCR | Alibaba | $0.00072 | n/a | $0.00072 |
| Gemini 3.1 Flash Live Preview | $0.00075 | n/a | $0.0045 | |
| GPT-5.4 mini | OpenAI | $0.00075 | $0.000075 | $0.0045 |
| Qwen-VL Max | Alibaba | $0.00080 | n/a | $0.0032 |
| QwQ Plus | Alibaba | $0.00080 | n/a | $0.0024 |
| Kimi K2.6 | Moonshot AI | $0.00095 | $0.00016 | $0.0040 |
| Kimi K2.7 Code | Moonshot AI | $0.00095 | $0.00019 | $0.0040 |
| Qwen3 Coder Plus | Alibaba | $0.0010 | n/a | $0.0050 |
| Claude Haiku 4.5 | Anthropic | $0.0010 | $0.00010 | $0.0050 |
| Claude Haiku 4.5 (latest) | Anthropic | $0.0010 | $0.00010 | $0.0050 |
| Gemini Robotics-ER 1.6 Preview | $0.0010 | n/a | $0.0050 | |
| Grok Build 0.1 | xAI | $0.0010 | $0.00020 | $0.0020 |
| GLM-5 | Zhipu AI | $0.0010 | $0.00020 | $0.0032 |
| o3-mini | OpenAI | $0.0011 | $0.00055 | $0.0044 |
| o4-mini | OpenAI | $0.0011 | $0.00028 | $0.0044 |
| Kimi K2 Thinking Turbo | Moonshot AI | $0.0011 | $0.00015 | $0.0080 |
| QVQ Max | Alibaba | $0.0012 | n/a | $0.0048 |
| Qwen3 Max | Alibaba | $0.0012 | n/a | $0.0060 |
| Gemini 2.5 Computer Use Preview 10-2025 | $0.0013 | n/a | $0.010 | |
| Gemini 2.5 Pro | $0.0013 | $0.00013 | $0.010 | |
| Muse Spark 1.1 | Meta | $0.0013 | $0.00015 | $0.0043 |
| GPT-5 | OpenAI | $0.0013 | $0.00013 | $0.010 |
| GPT-5.1 | OpenAI | $0.0013 | $0.00013 | $0.010 |
| Grok 4.20 (Non-Reasoning) | xAI | $0.0013 | $0.00020 | $0.0025 |
| Grok 4.20 (Reasoning) | xAI | $0.0013 | $0.00020 | $0.0025 |
| Grok 4.20 Multi-Agent | xAI | $0.0013 | $0.00020 | $0.0025 |
| Grok 4.3 | xAI | $0.0013 | $0.00020 | $0.0025 |
| Qwen3.6 Max Preview | Alibaba | $0.0013 | $0.00013 | $0.0078 |
| Qwen2.5 72B Instruct | Alibaba | $0.0014 | n/a | $0.0056 |
| GLM-5.1 | Zhipu AI | $0.0014 | $0.00026 | $0.0044 |
| GLM-5.2 | Zhipu AI | $0.0014 | $0.00026 | $0.0044 |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $0.0015 | n/a | $0.0075 |
| Gemini 3.5 Flash | $0.0015 | $0.00015 | $0.0090 | |
| Gemini 3.6 Flash | $0.0015 | $0.00015 | $0.0075 | |
| Gemini Flash Latest | $0.0015 | $0.00015 | $0.0090 | |
| Mistral Medium (latest) | Mistral | $0.0015 | n/a | $0.0075 |
| Mistral Medium 3.5 | Mistral | $0.0015 | n/a | $0.0075 |
| Qwen Max | Alibaba | $0.0016 | n/a | $0.0064 |
| GPT-5.2 | OpenAI | $0.0018 | $0.00017 | $0.014 |
| GPT-5.2 Chat | OpenAI | $0.0018 | $0.00017 | $0.014 |
| GPT-5.3 Chat (latest) | OpenAI | $0.0018 | $0.00017 | $0.014 |
| GPT-5.3 Codex | OpenAI | $0.0018 | $0.00017 | $0.014 |
| GPT-5.3 Codex Spark | OpenAI | $0.0018 | $0.00017 | $0.014 |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.0019 | $0.00038 | $0.0080 |
| Qwen3.8 Max | Alibaba | $0.0020 | $0.00025 | $0.0060 |
| Claude Sonnet 5 | Anthropic | $0.0020 | $0.00020 | $0.010 |
| Deep Research Max Preview (Apr-21-2026) | $0.0020 | $0.00020 | $0.012 | |
| Deep Research Preview (Apr-21-2026) | $0.0020 | $0.00020 | $0.012 | |
| Gemini 3 Pro Preview | $0.0020 | $0.00020 | $0.012 | |
| Gemini 3.1 Pro Preview | $0.0020 | $0.00020 | $0.012 | |
| Gemini 3.1 Pro Preview Custom Tools | $0.0020 | $0.00020 | $0.012 | |
| Nano Banana Pro | $0.0020 | n/a | $0.12 | |
| Nano Banana Pro | $0.0020 | n/a | $0.12 | |
| Magistral Medium (latest) | Mistral | $0.0020 | n/a | $0.0050 |
| Mistral Large 2.1 | Mistral | $0.0020 | n/a | $0.0060 |
| Mixtral 8x22B | Mistral | $0.0020 | n/a | $0.0060 |
| Pixtral Large (latest) | Mistral | $0.0020 | n/a | $0.0060 |
| GPT-4.1 | OpenAI | $0.0020 | $0.00050 | $0.0080 |
| GPT-5.6 Terra | OpenAI | $0.0020 | $0.00020 | $0.012 |
| o3 | OpenAI | $0.0020 | $0.00050 | $0.0080 |
| Grok 4.5 | xAI | $0.0020 | $0.00030 | $0.0060 |
| Kimi K2 Turbo | Moonshot AI | $0.0024 | $0.00060 | $0.010 |
| Qwen-MT Plus | Alibaba | $0.0025 | n/a | $0.0074 |
| Qwen3.7 Max | Alibaba | $0.0025 | $0.00050 | $0.0075 |
| Command A | Cohere | $0.0025 | n/a | $0.010 |
| Command A Plus | Cohere | $0.0025 | n/a | $0.010 |
| Command A Reasoning | Cohere | $0.0025 | n/a | $0.010 |
| Command A Translate | Cohere | $0.0025 | n/a | $0.010 |
| Command A Vision | Cohere | $0.0025 | n/a | $0.010 |
| Command R+ | Cohere | $0.0025 | n/a | $0.010 |
| GPT-4o | OpenAI | $0.0025 | $0.0013 | $0.010 |
| GPT-4o (2024-08-06) | OpenAI | $0.0025 | $0.0013 | $0.010 |
| GPT-4o (2024-11-20) | OpenAI | $0.0025 | $0.0013 | $0.010 |
| GPT-5.4 | OpenAI | $0.0025 | $0.00025 | $0.015 |
| Qwen2.5-VL 72B Instruct | Alibaba | $0.0028 | n/a | $0.0084 |
| Claude Sonnet 4.5 | Anthropic | $0.0030 | $0.00030 | $0.015 |
| Claude Sonnet 4.5 (latest) | Anthropic | $0.0030 | $0.00030 | $0.015 |
| Claude Sonnet 4.6 | Anthropic | $0.0030 | $0.00030 | $0.015 |
| Kimi K3 | Moonshot AI | $0.0030 | $0.00030 | $0.015 |
| Gemini 3.5 Live Translate Preview | $0.0035 | n/a | $0.021 | |
| GPT-Realtime-2.1 | OpenAI | $0.0040 | $0.00040 | $0.024 |
| Claude Opus 4.5 | Anthropic | $0.0050 | $0.00050 | $0.025 |
| Claude Opus 4.5 (latest) | Anthropic | $0.0050 | $0.00050 | $0.025 |
| Claude Opus 4.6 | Anthropic | $0.0050 | $0.00050 | $0.025 |
| Claude Opus 4.7 | Anthropic | $0.0050 | $0.00050 | $0.025 |
| Claude Opus 4.8 | Anthropic | $0.0050 | $0.00050 | $0.025 |
| Claude Opus 5 | Anthropic | $0.0050 | $0.00050 | $0.025 |
| GPT-4o (2024-05-13) | OpenAI | $0.0050 | n/a | $0.015 |
| GPT-5.5 | OpenAI | $0.0050 | $0.00050 | $0.030 |
| GPT-5.6 | OpenAI | $0.0050 | $0.00050 | $0.030 |
| GPT-5.6 Sol | OpenAI | $0.0050 | $0.00050 | $0.030 |
| GLM-5V-Turbo | Zhipu AI | $0.0050 | $0.0012 | $0.022 |
| Qwen3-LiveTranslate Flash Realtime | Alibaba | $0.010 | n/a | $0.010 |
| Claude Fable 5 | Anthropic | $0.010 | $0.0010 | $0.050 |
| GPT-4 Turbo | OpenAI | $0.010 | n/a | $0.030 |
| Claude Opus 4.1 | Anthropic | $0.015 | $0.0015 | $0.075 |
| Claude Opus 4.1 (latest) | Anthropic | $0.015 | $0.0015 | $0.075 |
| GPT-5 Pro | OpenAI | $0.015 | n/a | $0.12 |
| o1 | OpenAI | $0.015 | $0.0075 | $0.060 |
| o3-pro | OpenAI | $0.020 | n/a | $0.080 |
| GPT-5.2 Pro | OpenAI | $0.021 | n/a | $0.17 |
| GPT-4 | OpenAI | $0.030 | n/a | $0.060 |
| GPT-5.4 Pro | OpenAI | $0.030 | n/a | $0.18 |
| GPT-5.5 Pro | OpenAI | $0.030 | n/a | $0.18 |
| o1-pro | OpenAI | $0.15 | n/a | $0.60 |
Prices per 1k tokens (USD), sorted by input price. Each model links to its official source. See the full pricing table and methodology.
Per 1K versus per 1M pricing
Older pricing pages quoted cost per 1,000 tokens; most now use per million. They are the same number scaled by 1,000, so cost per 1K is simply the per-million price divided by a thousand. This page shows the per-1K figure directly so you can compare against docs that still use it.
FAQ
How do I convert per-1K to per-1M pricing?
Multiply the per-1,000-token price by 1,000. A model at $0.003 per 1K tokens is $3 per 1M tokens.