Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 4,880 models across every major provider. Prices sync daily from the open LiteLLM dataset. Pick a model for details and a workload cost calculator.
| Model | Provider ↑ | Input /Mtok | Output /Mtok | Cache read | Cache write | Context | Modality |
|---|---|---|---|---|---|---|---|
|
cloudflare/@cf/meta/llama-3.2-11b-vision-instruct
cloudflare/@cf/meta/llama-3.2-11b-vision-instruct
|
Cloudflare | $0.0485 | $0.6760 | — | — | 128,000 | text |
|
cloudflare/@cf/meta/llama-3.2-1b-instruct
cloudflare/@cf/meta/llama-3.2-1b-instruct
|
Cloudflare | $0.0270 | $0.2010 | — | — | 60,000 | text |
|
cloudflare/@cf/meta/llama-3.2-3b-instruct
cloudflare/@cf/meta/llama-3.2-3b-instruct
|
Cloudflare | $0.0509 | $0.3350 | — | — | 80,000 | text |
|
cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast
cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast
|
Cloudflare | $0.2930 | $2.25 | — | — | 24,000 | text |
|
cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct
cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct
|
Cloudflare | $0.2700 | $0.8500 | — | — | 131,000 | text |
|
cloudflare/@cf/meta/llama-guard-3-8b
cloudflare/@cf/meta/llama-guard-3-8b
|
Cloudflare | $0.4840 | $0.0300 | — | — | 131,072 | text |
|
cloudflare/@cf/mistral/mistral-7b-instruct-v0.1
cloudflare/@cf/mistral/mistral-7b-instruct-v0.1
|
Cloudflare | $1.92 | $1.92 | — | — | 8,192 | text |
|
cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora
cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora
|
Cloudflare | $0.0000 | $0.0000 | — | — | 15,000 | text |
|
cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct
cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct
|
Cloudflare | $0.3510 | $0.5550 | — | — | 128,000 | text |
|
cloudflare/@cf/moonshotai/kimi-k2.6
cloudflare/@cf/moonshotai/kimi-k2.6
|
Cloudflare | $0.9500 | $4.00 | $0.1600 | — | 262,144 | text |
|
cloudflare/@cf/moonshotai/kimi-k2.7-code
cloudflare/@cf/moonshotai/kimi-k2.7-code
|
Cloudflare | $0.9500 | $4.00 | $0.1900 | — | 262,144 | text |
|
cloudflare/@cf/nvidia/nemotron-3-120b-a12b
cloudflare/@cf/nvidia/nemotron-3-120b-a12b
|
Cloudflare | $0.5000 | $1.50 | — | — | 256,000 | text |
|
cloudflare/@cf/openai/gpt-oss-120b
cloudflare/@cf/openai/gpt-oss-120b
|
Cloudflare | $0.3500 | $0.7500 | — | — | 128,000 | text |
|
cloudflare/@cf/openai/gpt-oss-20b
cloudflare/@cf/openai/gpt-oss-20b
|
Cloudflare | $0.2000 | $0.3000 | — | — | 128,000 | text |
|
cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct
cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct
|
Cloudflare | $0.6600 | $1.00 | — | — | 32,768 | text |
|
cloudflare/@cf/qwen/qwen3-30b-a3b-fp8
cloudflare/@cf/qwen/qwen3-30b-a3b-fp8
|
Cloudflare | $0.0509 | $0.3350 | — | — | 32,768 | text |
|
cloudflare/@cf/qwen/qwq-32b
cloudflare/@cf/qwen/qwq-32b
|
Cloudflare | $0.6600 | $1.00 | — | — | 24,000 | text |
|
cloudflare/@cf/zai-org/glm-4.7-flash
cloudflare/@cf/zai-org/glm-4.7-flash
|
Cloudflare | $0.0605 | $0.4000 | — | — | 131,072 | text |
|
cloudflare/@cf/zai-org/glm-5.2
cloudflare/@cf/zai-org/glm-5.2
|
Cloudflare | $1.40 | $4.40 | $0.2600 | — | 262,144 | text |
|
cloudflare/@hf/thebloke/codellama-7b-instruct-awq
cloudflare/@hf/thebloke/codellama-7b-instruct-awq
|
Cloudflare | $1.92 | $1.92 | — | — | 4,096 | text |
|
cloudflare/clairic
cloudflare/clairic
|
Cloudflare | $0.1000 | $0.0000 | — | — | 65,536 | text |
|
cloudflare/clef
cloudflare/clef
|
Cloudflare | $0.2400 | $0.0000 | — | — | 65,536 | text |
|
cloudflare/clef-flash
cloudflare/clef-flash
|
Cloudflare | $0.0900 | $0.0000 | — | — | 65,536 | text |
|
cloudflare/clef-omni
cloudflare/clef-omni
|
Cloudflare | $0.1500 | $0.0000 | — | — | 64,000 | text |
|
codestral/codestral-2405
codestral/codestral-2405
|
Codestral | $0.0000 | $0.0000 | — | — | 32,000 | text |
|
codestral/codestral-latest
codestral/codestral-latest
|
Codestral | $0.0000 | $0.0000 | — | — | 32,000 | text |
|
cognition/swe-1.6
cognition/swe-1.6
|
Cognition | $0.5000 | $2.50 | $0.2000 | — | — | text |
|
cognition/swe-1.7
cognition/swe-1.7
|
Cognition | $0.5000 | $2.50 | $0.2000 | — | — | text |
|
cognition/swe-1.7-lightning
cognition/swe-1.7-lightning
|
Cognition | $2.50 | $12.50 | $1.00 | — | — | text |
|
c4ai-aya-expanse-32b
c4ai-aya-expanse-32b
|
Cohere | $0.5000 | $1.50 | — | — | 128,000 | text |
|
cohere/embed-v4.0
cohere/embed-v4.0
|
Cohere | $0.1200 | $0.0000 | — | — | 128,000 | embedding |
|
cohere/embed-v5.0-fast
cohere/embed-v5.0-fast
|
Cohere | $0.0800 | $0.0000 | — | — | 128,000 | embedding |
|
cohere/embed-v5.0-pro
cohere/embed-v5.0-pro
|
Cohere | $0.1200 | $0.0000 | — | — | 128,000 | embedding |
|
command
command
|
Cohere | $1.00 | $2.00 | — | — | 4,096 | text |
|
command-a-03-2025
command-a-03-2025
|
Cohere | $2.50 | $10.00 | — | — | 256,000 | text |
|
command-a-plus-05-2026
command-a-plus-05-2026
|
Cohere | $0.0000 | $0.0000 | — | — | 128,000 | text |
|
command-light
command-light
|
Cohere | $0.3000 | $0.6000 | — | — | 4,096 | text |
|
command-nightly
command-nightly
|
Cohere | $1.00 | $2.00 | — | — | 4,096 | text |
|
command-r
command-r
|
Cohere | $0.1500 | $0.6000 | — | — | 128,000 | text |
|
command-r-08-2024
command-r-08-2024
|
Cohere | $0.1500 | $0.6000 | — | — | 128,000 | text |
|
command-r-plus
command-r-plus
|
Cohere | $2.50 | $10.00 | — | — | 128,000 | text |
|
command-r-plus-08-2024
command-r-plus-08-2024
|
Cohere | $2.50 | $10.00 | — | — | 128,000 | text |
|
command-r7b-12-2024
command-r7b-12-2024
|
Cohere | $0.0375 | $0.1500 | — | — | 128,000 | text |
|
embed-english-light-v2.0
embed-english-light-v2.0
|
Cohere | $0.1000 | $0.0000 | — | — | 1,024 | embedding |
|
embed-english-light-v3.0
embed-english-light-v3.0
|
Cohere | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
embed-english-v2.0
embed-english-v2.0
|
Cohere | $0.1000 | $0.0000 | — | — | 4,096 | embedding |
|
embed-english-v3.0
embed-english-v3.0
|
Cohere | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
embed-multilingual-light-v3.0
embed-multilingual-light-v3.0
|
Cohere | $100.00 | $0.0000 | — | — | 512 | embedding |
|
embed-multilingual-v2.0
embed-multilingual-v2.0
|
Cohere | $0.1000 | $0.0000 | — | — | 768 | embedding |
|
embed-multilingual-v3.0
embed-multilingual-v3.0
|
Cohere | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
rerank-english-v2.0
rerank-english-v2.0
|
Cohere | $0.0000 | $0.0000 | — | — | 4,096 | rerank |
|
rerank-english-v3.0
rerank-english-v3.0
|
Cohere | $0.0000 | $0.0000 | — | — | 4,096 | rerank |
|
rerank-multilingual-v2.0
rerank-multilingual-v2.0
|
Cohere | $0.0000 | $0.0000 | — | — | 4,096 | rerank |
|
rerank-multilingual-v3.0
rerank-multilingual-v3.0
|
Cohere | $0.0000 | $0.0000 | — | — | 4,096 | rerank |
|
rerank-v3.5
rerank-v3.5
|
Cohere | $0.0000 | $0.0000 | — | — | 4,096 | rerank |
|
rerank-v4.0-fast
rerank-v4.0-fast
|
Cohere | $0.0000 | $0.0000 | — | — | 32,768 | rerank |
|
rerank-v4.0-pro
rerank-v4.0-pro
|
Cohere | $0.0000 | $0.0000 | — | — | 32,768 | rerank |
|
rerank-v5.0-fast
rerank-v5.0-fast
|
Cohere | $0.0200 | $0.0000 | — | — | 32,768 | rerank |
|
rerank-v5.0-pro
rerank-v5.0-pro
|
Cohere | $0.0500 | $0.0000 | — | — | 32,768 | rerank |
|
coralbricks/deepseek-v4.1-flash
coralbricks/deepseek-v4.1-flash
|
Coralbricks | $0.0100 | $1.20 | $0.0000 | $0.0900 | 1,048,576 | text |
|
coralbricks/deepseek-v4.1-flash-fast
coralbricks/deepseek-v4.1-flash-fast
|
Coralbricks | $0.0100 | $1.20 | $0.0000 | $0.0900 | 1,048,576 | text |
|
coralbricks/deepseek-v4.1-flash-fast-fp4
coralbricks/deepseek-v4.1-flash-fast-fp4
|
Coralbricks | $0.0100 | $1.20 | $0.0000 | $0.0900 | 1,048,576 | text |
|
coralbricks/glm-5.3
coralbricks/glm-5.3
|
Coralbricks | $1.12 | $4.40 | $0.0000 | $1.68 | 1,048,576 | text |
|
coralbricks/glm-5.3-fast
coralbricks/glm-5.3-fast
|
Coralbricks | $1.12 | $4.40 | $0.0000 | $1.68 | 1,048,576 | text |
|
coralbricks/glm-5.3-fp4
coralbricks/glm-5.3-fp4
|
Coralbricks | $1.12 | $4.40 | $0.0000 | $1.68 | 1,048,576 | text |
|
crusoe/deepseek-ai/DeepSeek-R1-0528
crusoe/deepseek-ai/DeepSeek-R1-0528
|
Crusoe | $3.00 | $7.00 | — | — | 163,840 | text |
|
crusoe/deepseek-ai/DeepSeek-V3-0324
crusoe/deepseek-ai/DeepSeek-V3-0324
|
Crusoe | $1.50 | $1.50 | — | — | 163,840 | text |
|
crusoe/google/gemma-3-12b-it
crusoe/google/gemma-3-12b-it
|
Crusoe | $0.1000 | $0.1000 | — | — | 131,072 | text |
|
crusoe/meta-llama/Llama-3.3-70B-Instruct
crusoe/meta-llama/Llama-3.3-70B-Instruct
|
Crusoe | $0.2000 | $0.2000 | — | — | 131,072 | text |
|
crusoe/moonshotai/Kimi-K2-Thinking
crusoe/moonshotai/Kimi-K2-Thinking
|
Crusoe | $2.50 | $2.50 | — | — | 262,144 | text |
|
crusoe/openai/gpt-oss-120b
crusoe/openai/gpt-oss-120b
|
Crusoe | $0.8000 | $0.8000 | — | — | 131,072 | text |
|
crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
|
Crusoe | $3.00 | $3.00 | — | — | 262,144 | text |
|
darkbloom/gemma-4-26b
darkbloom/gemma-4-26b
|
Darkbloom | $0.0300 | $0.1650 | — | — | 131,072 | text |
|
darkbloom/gpt-oss-20b
darkbloom/gpt-oss-20b
|
Darkbloom | $0.0145 | $0.0700 | — | — | 131,072 | text |
|
dashscope/deepseek-v4-flash
dashscope/deepseek-v4-flash
|
Dashscope | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
dashscope/deepseek-v4-flash-0731
dashscope/deepseek-v4-flash-0731
|
Dashscope | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
dashscope/deepseek-v4-pro
dashscope/deepseek-v4-pro
|
Dashscope | $2.40 | $4.80 | $0.2000 | — | 1,000,000 | text |
|
dashscope/glm-5.1
dashscope/glm-5.1
|
Dashscope | $1.40 | $4.40 | $0.2600 | — | 202,745 | text |
|
dashscope/glm-5.2
dashscope/glm-5.2
|
Dashscope | $1.40 | $4.40 | $0.2800 | — | 1,048,576 | text |
|
dashscope/kimi-k2.7-code
dashscope/kimi-k2.7-code
|
Dashscope | $0.9500 | $4.00 | $0.1900 | — | 229,376 | text |
|
dashscope/qwen-audio-3.1-tts-flash
dashscope/qwen-audio-3.1-tts-flash
|
Dashscope | $0.2300 | $1.87 | — | — | — | audio |
|
dashscope/qwen-coder
dashscope/qwen-coder
|
Dashscope | $0.3000 | $1.50 | — | — | 1,000,000 | text |
|
dashscope/qwen-max
dashscope/qwen-max
|
Dashscope | $1.60 | $6.40 | — | — | 30,720 | text |
|
dashscope/qwen-plus
dashscope/qwen-plus
|
Dashscope | $0.4000 | $1.20 | — | — | 129,024 | text |
|
dashscope/qwen-plus-2025-01-25
dashscope/qwen-plus-2025-01-25
|
Dashscope | $0.4000 | $1.20 | — | — | 129,024 | text |
|
dashscope/qwen-plus-2025-04-28
dashscope/qwen-plus-2025-04-28
|
Dashscope | $0.4000 | $1.20 | — | — | 129,024 | text |
|
dashscope/qwen-plus-2025-07-14
dashscope/qwen-plus-2025-07-14
|
Dashscope | $0.4000 | $1.20 | — | — | 129,024 | text |
|
dashscope/qwen-turbo
dashscope/qwen-turbo
|
Dashscope | $0.0500 | $0.2000 | — | — | 129,024 | text |
|
dashscope/qwen-turbo-2024-11-01
dashscope/qwen-turbo-2024-11-01
|
Dashscope | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
dashscope/qwen-turbo-2025-04-28
dashscope/qwen-turbo-2025-04-28
|
Dashscope | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
dashscope/qwen-turbo-latest
dashscope/qwen-turbo-latest
|
Dashscope | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
dashscope/qwen3-next-80b-a3b-instruct
dashscope/qwen3-next-80b-a3b-instruct
|
Dashscope | $0.1500 | $1.20 | — | — | 262,144 | text |
|
dashscope/qwen3-next-80b-a3b-thinking
dashscope/qwen3-next-80b-a3b-thinking
|
Dashscope | $0.1500 | $1.20 | — | — | 262,144 | text |
|
dashscope/qwen3-vl-235b-a22b-instruct
dashscope/qwen3-vl-235b-a22b-instruct
|
Dashscope | $0.4000 | $1.60 | — | — | 131,072 | text |
|
dashscope/qwen3-vl-235b-a22b-thinking
dashscope/qwen3-vl-235b-a22b-thinking
|
Dashscope | $0.4000 | $4.00 | — | — | 131,072 | text |
|
dashscope/qwen3-vl-32b-instruct
dashscope/qwen3-vl-32b-instruct
|
Dashscope | $0.1600 | $0.6400 | — | — | 131,072 | text |
|
dashscope/qwen3-vl-32b-thinking
dashscope/qwen3-vl-32b-thinking
|
Dashscope | $0.1600 | $2.87 | — | — | 131,072 | text |
|
dashscope/qwen3.7-max
dashscope/qwen3.7-max
|
Dashscope | $2.50 | $7.50 | $0.5000 | $3.13 | 991,808 | text |
|
dashscope/qwen3.8-flash
dashscope/qwen3.8-flash
|
Dashscope | $0.1500 | $0.4700 | $0.0160 | $0.2000 | 991,808 | text |
|
dashscope/qwen3.8-max
dashscope/qwen3.8-max
|
Dashscope | $2.00 | $6.00 | $0.2500 | — | 991,808 | text |
Prices are sourced from the open LiteLLM dataset and may lag provider changes. Always confirm against the provider's official pricing before relying on a figure.