Prices
AI API prices compared
US dollars per million tokens from each provider’s own API. “Typical call” is the cost of 1,000 calls with 2,000 tokens in and 500 out. Updated .
| Model | Input | Cached | Output | Context | Typical call ×1,000 |
|---|---|---|---|---|---|
| qwen-turbo Alibaba (Qwen) · tools · reasoning | $0.050 | — | $0.20 | 129k | $0.20 |
| glm-4-32b-0414-128k Zhipu (GLM) · tools | $0.10 | — | $0.10 | 128k | $0.25 |
| gpt-5-nano OpenAI · images · tools · reasoning · JSON schema | $0.050 | $0.005 | $0.40 | 272k | $0.30 |
| mistral-small Mistral · tools · reasoning · JSON schema | $0.10 | $0.010 | $0.30 | 32k | $0.35 |
| gemini-2.5-flash-lite Google · images · tools · reasoning · JSON schema | $0.10 | $0.010 | $0.40 | 1.0M | $0.40 |
| deepseek-coder DeepSeek · tools | $0.14 | $0.014 | $0.28 | 128k | $0.42 |
| claude-haiku-5-5 Anthropic · images · tools · reasoning · JSON schema | $0.10 | $0.010 | $0.50 | 1M | $0.45 |
| gpt-6-luna OpenAI · images · tools · reasoning · JSON schema | $0.10 | $0.010 | $0.50 | 922k | $0.45 |
| qwen3.8-flash Alibaba (Qwen) · images · tools · reasoning · JSON schema | $0.15 | $0.016 | $0.47 | 992k | $0.54 |
| qwen3.8-omni-flash Alibaba (Qwen) · images · tools · reasoning · JSON schema | $0.15 | $0.016 | $0.47 | 992k | $0.54 |
| glm-5.3-flash Zhipu (GLM) · images · tools · reasoning · JSON schema | $0.15 | $0.030 | $0.50 | 1.0M | $0.55 |
| zai-glm-5-3-flash Mistral · images · tools · reasoning · JSON schema | $0.15 | $0.030 | $0.50 | 1.0M | $0.55 |
| deepseek-v4-flash Alibaba (Qwen) · tools · reasoning · JSON schema | $0.20 | $0.040 | $0.40 | 1M | $0.60 |
| gpt-4o-mini OpenAI · images · tools · JSON schema | $0.15 | $0.075 | $0.60 | 128k | $0.60 |
| gpt-4o-mini-search-preview OpenAI · images · tools · JSON schema | $0.15 | $0.075 | $0.60 | 128k | $0.60 |
| mistral-vibe-cli-fast Mistral · images · tools · reasoning · JSON schema | $0.15 | $0.015 | $0.60 | 262k | $0.60 |
| qwen3-vl-32b-instruct Alibaba (Qwen) · images · tools | $0.16 | — | $0.64 | 131k | $0.64 |
| deepseek-v3.2 DeepSeek · tools · reasoning | $0.28 | $0.028 | $0.40 | 164k | $0.76 |
| qwen3-next-80b-a3b-instruct Alibaba (Qwen) · tools | $0.15 | — | $1.20 | 262k | $0.90 |
| qwen3-next-80b-a3b-thinking Alibaba (Qwen) · tools · reasoning | $0.15 | — | $1.20 | 262k | $0.90 |
| glm-4.5-air Zhipu (GLM) · tools | $0.20 | — | $1.10 | 128k | $0.95 |
| gpt-5.6-luna OpenAI · images · tools · reasoning · JSON schema | $0.20 | $0.020 | $1.20 | 922k | $1.00 |
| gpt-5.4-nano OpenAI · images · tools · reasoning · JSON schema | $0.20 | $0.020 | $1.25 | 272k | $1.02 |
| deepseek-v3 DeepSeek · tools | $0.27 | $0.070 | $1.10 | 66k | $1.09 |
| deepseek-flash DeepSeek · images · tools · reasoning · JSON schema | $0.30 | $0.006 | $1.20 | 1M | $1.20 |
| deepseek-v4-flash DeepSeek · images · tools · reasoning · JSON schema | $0.30 | $0.006 | $1.20 | 1M | $1.20 |
| deepseek-v4-flash-vision-exp DeepSeek · images · tools · reasoning · JSON schema | $0.30 | $0.006 | $1.20 | 1M | $1.20 |
| gemini-gemma-2-27b-it Google · images · tools | $0.35 | — | $1.05 | 8k | $1.23 |
| gemini-gemma-2-9b-it Google · images · tools | $0.35 | — | $1.05 | 8k | $1.23 |
| gemini-3.1-flash-lite Google · images · tools · reasoning · JSON schema | $0.25 | $0.025 | $1.50 | 1.0M | $1.25 |
| qwen-coder Alibaba (Qwen) · tools · reasoning | $0.30 | — | $1.50 | 1M | $1.35 |
| qwen-plus Alibaba (Qwen) · tools · reasoning | $0.40 | — | $1.20 | 129k | $1.40 |
| gpt-5-mini OpenAI · images · tools · reasoning · JSON schema | $0.25 | $0.025 | $2.00 | 272k | $1.50 |
| gpt-4.1-mini OpenAI · images · tools · JSON schema | $0.40 | $0.10 | $1.60 | 1.0M | $1.60 |
| qwen3-vl-235b-a22b-instruct Alibaba (Qwen) · images · tools | $0.40 | — | $1.60 | 131k | $1.60 |
| mistral-large-3 Mistral · images · tools · JSON schema | $0.50 | $0.050 | $1.50 | 262k | $1.75 |
| qwen3-vl-32b-thinking Alibaba (Qwen) · images · tools · reasoning | $0.16 | — | $2.87 | 131k | $1.75 |
| gemini-2.5-flash Google · images · tools · reasoning · JSON schema | $0.30 | $0.030 | $2.50 | 1.0M | $1.85 |
| gemini-3.5-flash-lite Google · images · tools · reasoning · JSON schema | $0.30 | $0.030 | $2.50 | 1.0M | $1.85 |
| glm-4.5v Zhipu (GLM) · images · tools | $0.60 | — | $1.80 | 128k | $2.10 |
| deepseek-r1 DeepSeek · tools · reasoning | $0.55 | $0.14 | $2.19 | 66k | $2.19 |
| glm-4.5 Zhipu (GLM) · tools | $0.60 | — | $2.20 | 128k | $2.30 |
| glm-4.6 Zhipu (GLM) · tools · reasoning | $0.60 | $0.11 | $2.20 | 200k | $2.30 |
| glm-4.7 Zhipu (GLM) · tools · reasoning | $0.60 | $0.11 | $2.20 | 200k | $2.30 |
| gpt-audio-mini OpenAI · tools | $0.60 | — | $2.40 | 128k | $2.40 |
| mistral-large-4 Mistral · images · tools · reasoning · JSON schema | $0.70 | $0.070 | $2.10 | 1.0M | $2.45 |
| mistral-large-4-0 Mistral · images · tools · reasoning · JSON schema | $0.70 | $0.070 | $2.10 | 1.0M | $2.45 |
| gemini-3-flash-preview Google · images · tools · reasoning · JSON schema | $0.50 | $0.050 | $3.00 | 1.0M | $2.50 |
| qwen3-vl-235b-a22b-thinking Alibaba (Qwen) · images · tools · reasoning | $0.40 | — | $4.00 | 131k | $2.80 |
| qwq-plus Alibaba (Qwen) · tools · reasoning | $0.80 | — | $2.40 | 98k | $2.80 |
| grok-build-0.1 xAI · images · tools · reasoning · JSON schema | $1.00 | $0.20 | $2.00 | 256k | $3.00 |
| grok-code-fast xAI · images · tools · reasoning · JSON schema | $1.00 | $0.20 | $2.00 | 256k | $3.00 |
| gemini-3.6-flash Google · images · tools · reasoning · JSON schema | $0.75 | $0.075 | $3.75 | 1.0M | $3.38 |
| gemini-3.7-flash Google · images · tools · reasoning · JSON schema | $0.75 | $0.075 | $3.75 | 1.0M | $3.38 |
| gemini-3.8-flash Google · images · tools · reasoning · JSON schema | $0.75 | $0.075 | $3.75 | 1.0M | $3.38 |
| glm-5 Zhipu (GLM) · tools · reasoning | $1.00 | $0.20 | $3.20 | 200k | $3.60 |
| gpt-5.4-mini OpenAI · images · tools · reasoning · JSON schema | $0.75 | $0.075 | $4.50 | 272k | $3.75 |
| grok-4.20 xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-0309-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-0309-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-0309-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-0309-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-latest-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-latest-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-beta-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-experimental-beta-0304-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-experimental-beta-0304-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-non-reasoning xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-non-reasoning-gv2 xAI · images · tools · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-reasoning xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.20-reasoning-gv2 xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| grok-4.3 xAI · images · tools · reasoning · JSON schema | $1.25 | $0.20 | $2.50 | 1M | $3.75 |
| kimi-k2.6 Moonshot (Kimi) · images · tools · reasoning · JSON schema | $0.95 | $0.16 | $4.00 | 262k | $3.90 |
| kimi-k2.7-code Alibaba (Qwen) · images · tools · reasoning · JSON schema | $0.95 | $0.19 | $4.00 | 229k | $3.90 |
| kimi-k2.7-code Moonshot (Kimi) · images · tools · reasoning · JSON schema | $0.95 | $0.19 | $4.00 | 262k | $3.90 |
| glm-5v-turbo Zhipu (GLM) · images · tools · reasoning | $1.20 | $0.24 | $4.00 | 200k | $4.40 |
| glm-4.5-airx Zhipu (GLM) · tools | $1.10 | — | $4.50 | 128k | $4.45 |
| claude-haiku-4-5 Anthropic · images · tools · reasoning · JSON schema | $1.00 | $0.10 | $5.00 | 200k | $4.50 |
| gemini-robotics-er-2-preview Google · images · tools · reasoning · JSON schema | $1.00 | $0.10 | $5.00 | 131k | $4.50 |
| gemini-robotics-er-2-streaming-preview Google · images · tools · reasoning | $1.00 | — | $5.00 | 131k | $4.50 |
| gpt-6.1-terra OpenAI · images · tools · reasoning · JSON schema | $1.00 | $0.050 | $5.00 | 922k | $4.50 |
| deepseek-v4-pro DeepSeek · tools · reasoning · JSON schema | $1.32 | $0.044 | $3.96 | 1M | $4.62 |
| glm-5-code Zhipu (GLM) · tools · reasoning | $1.20 | $0.30 | $5.00 | 200k | $4.90 |
| glm-5-2 Mistral · tools · reasoning · JSON schema | $1.40 | $0.14 | $4.40 | 1.0M | $5.00 |
| glm-5.1 Alibaba (Qwen) · tools · reasoning · JSON schema | $1.40 | $0.26 | $4.40 | 203k | $5.00 |
| glm-5.1 Zhipu (GLM) · tools · reasoning | $1.40 | $0.26 | $4.40 | 200k | $5.00 |
| glm-5.2 Alibaba (Qwen) · tools · reasoning · JSON schema | $1.40 | $0.28 | $4.40 | 1.0M | $5.00 |
| glm-5.2 Zhipu (GLM) · tools · reasoning | $1.40 | $0.26 | $4.40 | 1M | $5.00 |
| glm-5.3 Zhipu (GLM) · tools · reasoning · JSON schema | $1.40 | $0.26 | $4.40 | 1M | $5.00 |
| zai-glm-5 Mistral · tools · reasoning · JSON schema | $1.40 | $0.14 | $4.40 | 1.0M | $5.00 |
| zai-glm-5-3 Mistral · tools · reasoning · JSON schema | $1.40 | $0.14 | $4.40 | 1.0M | $5.00 |
| qwen-max Alibaba (Qwen) · tools · reasoning | $1.60 | — | $6.40 | 31k | $6.40 |
| mistral-medium Mistral · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $7.50 | 262k | $6.75 |
| mistral-medium-3 Mistral · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $7.50 | 262k | $6.75 |
| mistral-medium-3-5 Mistral · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $7.50 | 262k | $6.75 |
| mistral-medium-3.5 Mistral · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $7.50 | 262k | $6.75 |
| mistral-vibe-cli-with-tools Mistral · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $7.50 | 262k | $6.75 |
| grok-4.5 xAI · images · tools · reasoning · JSON schema | $2.00 | $0.30 | $6.00 | 500k | $7.00 |
| grok-4.6 xAI · images · tools · reasoning · JSON schema | $2.00 | $0.50 | $6.00 | 500k | $7.00 |
| grok-4.7 xAI · images · tools · reasoning · JSON schema | $2.00 | $0.50 | $6.00 | 500k | $7.00 |
| qwen3.8-max Alibaba (Qwen) · images · tools · reasoning · JSON schema | $2.00 | $0.25 | $6.00 | 992k | $7.00 |
| deepseek-v4-pro Alibaba (Qwen) · tools · reasoning · JSON schema | $2.40 | $0.20 | $4.80 | 1M | $7.20 |
| gemini-2.5-pro Google · images · tools · reasoning · JSON schema | $1.25 | $0.13 | $10.0 | 1.0M | $7.50 |
| gemini-3.5-flash Google · images · tools · reasoning · JSON schema | $1.50 | $0.15 | $9.00 | 1.0M | $7.50 |
| gpt-5 OpenAI · images · tools · reasoning · JSON schema | $1.25 | $0.13 | $10.0 | 272k | $7.50 |
| gpt-5-search-api OpenAI · images · tools · JSON schema | $1.25 | $0.13 | $10.0 | 272k | $7.50 |
| gpt-5.1 OpenAI · images · tools · reasoning · JSON schema | $1.25 | $0.13 | $10.0 | 272k | $7.50 |
| gpt-4.1 OpenAI · images · tools · JSON schema | $2.00 | $0.50 | $8.00 | 1.0M | $8.00 |
| o3 OpenAI · images · tools · reasoning · JSON schema | $2.00 | $0.50 | $8.00 | 200k | $8.00 |
| qwen3.7-max Alibaba (Qwen) · tools · reasoning · JSON schema | $2.50 | $0.50 | $7.50 | 992k | $8.75 |
| glm-4.5-x Zhipu (GLM) · tools | $2.20 | — | $8.90 | 128k | $8.85 |
| claude-sonnet-5 Anthropic · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $10.0 | 1M | $9.00 |
| claude-sonnet-5-5 Anthropic · images · tools · reasoning · JSON schema | $2.00 | $0.10 | $10.0 | 1M | $9.00 |
| gemini-4-argon Google · images · tools · reasoning · JSON schema | $2.00 | $0.10 | $10.0 | 1.0M | $9.00 |
| gemini-4-carbon Google · images · tools · reasoning · JSON schema | $2.00 | $0.10 | $10.0 | 1.0M | $9.00 |
| gpt-6-sol OpenAI · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $10.0 | 922k | $9.00 |
| gpt-6.1-sol OpenAI · images · tools · reasoning · JSON schema | $2.00 | $0.10 | $10.0 | 922k | $9.00 |
| kimi-k3.1-pro Moonshot (Kimi) · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $10.0 | 1.0M | $9.00 |
| gemini-3.1-pro-preview Google · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $12.0 | 1.0M | $10.0 |
| gemini-3.1-pro-preview-customtools Google · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $12.0 | 1.0M | $10.0 |
| gpt-4o OpenAI · images · tools · JSON schema | $2.50 | $1.25 | $10.0 | 128k | $10.0 |
| gpt-4o-search-preview OpenAI · images · tools · JSON schema | $2.50 | $1.25 | $10.0 | 128k | $10.0 |
| gpt-5.6-terra OpenAI · images · tools · reasoning · JSON schema | $2.00 | $0.20 | $12.0 | 922k | $10.0 |
| gpt-audio OpenAI · tools | $2.50 | — | $10.0 | 128k | $10.0 |
| gpt-audio-1.5 OpenAI · tools | $2.50 | — | $10.0 | 128k | $10.0 |
| gpt-5.2 OpenAI · images · tools · reasoning · JSON schema | $1.75 | $0.17 | $14.0 | 272k | $10.5 |
| gpt-5.4 OpenAI · images · tools · reasoning · JSON schema | $2.50 | $0.25 | $15.0 | 1.1M | $12.5 |
| claude-sonnet-4-5 Anthropic · images · tools · reasoning · JSON schema | $3.00 | $0.30 | $15.0 | 200k | $13.5 |
| claude-sonnet-4-6 Anthropic · images · tools · reasoning · JSON schema | $3.00 | $0.30 | $15.0 | 1M | $13.5 |
| kimi-k3 Moonshot (Kimi) · images · tools · reasoning · JSON schema | $3.00 | $0.30 | $15.0 | 1.0M | $13.5 |
| claude-opus-5-5 Anthropic · images · tools · reasoning · JSON schema | $4.00 | $0.20 | $20.0 | 1M | $18.0 |
| gpt-5.6 OpenAI · images · tools · reasoning · JSON schema | $4.00 | $0.40 | $20.0 | 922k | $18.0 |
| gpt-5.6-sol OpenAI · images · tools · reasoning · JSON schema | $4.00 | $0.40 | $20.0 | 922k | $18.0 |
| kimi-k3.1-pro-highspeed Moonshot (Kimi) · images · tools · reasoning · JSON schema | $4.00 | $0.20 | $20.0 | 1.0M | $18.0 |
| claude-opus-4-5 Anthropic · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $25.0 | 200k | $22.5 |
| claude-opus-4-6 Anthropic · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $25.0 | 1M | $22.5 |
| claude-opus-4-7 Anthropic · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $25.0 | 1M | $22.5 |
| claude-opus-4-8 Anthropic · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $25.0 | 1M | $22.5 |
| claude-opus-5 Anthropic · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $25.0 | 1M | $22.5 |
| gpt-5.5 OpenAI · images · tools · reasoning · JSON schema | $5.00 | $0.50 | $30.0 | 1.1M | $25.0 |
| claude-fable-5-2 Anthropic · images · tools · reasoning · JSON schema | $8.00 | $0.20 | $40.0 | 1M | $36.0 |
| claude-mythos-5-2 Anthropic · images · tools · reasoning · JSON schema | $8.00 | $0.20 | $40.0 | 1M | $36.0 |
| claude-fable-5 Anthropic · images · tools · reasoning · JSON schema | $10.0 | $1.00 | $50.0 | 1M | $45.0 |
| claude-fable-5-1 Anthropic · images · tools · reasoning · JSON schema | $10.0 | $0.25 | $50.0 | 1M | $45.0 |
| claude-mythos-5 Anthropic · images · tools · reasoning · JSON schema | $10.0 | $1.00 | $50.0 | 1M | $45.0 |
| claude-mythos-5-1 Anthropic · images · tools · reasoning · JSON schema | $10.0 | $0.25 | $50.0 | 1M | $45.0 |
| gpt-6-astra OpenAI · images · tools · reasoning · JSON schema | $10.0 | $1.00 | $50.0 | 922k | $45.0 |
| gpt-6-astra-law OpenAI · images · tools · reasoning · JSON schema | $10.0 | $1.00 | $50.0 | 922k | $45.0 |
| gpt-5.6-cyber OpenAI · images · tools · reasoning · JSON schema | $12.5 | $1.25 | $75.0 | 272k | $62.5 |
| gpt-6-rosalind OpenAI · images · tools · reasoning · JSON schema | $15.0 | $1.50 | $75.0 | 922k | $67.5 |
| gpt-6-cyber OpenAI · images · tools · reasoning · JSON schema | $20.0 | $2.00 | $100.0 | 922k | $90.0 |
Source: the open LiteLLM model price map (MIT), checked daily. Batch, long-context and regional prices differ; always check the provider’s own pricing page before you commit. Spotted a wrong price? Tell us with “Report an error” on any post.