Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 3,364 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 |
|---|---|---|---|---|---|---|---|
|
groq/openai/gpt-oss-20b
groq/openai/gpt-oss-20b
|
Groq | $0.0750 | $0.3000 | $0.0375 | — | 131,072 | text |
|
groq/openai/gpt-oss-safeguard-20b
groq/openai/gpt-oss-safeguard-20b
|
Groq | $0.0750 | $0.3000 | $0.0370 | — | 131,072 | text |
|
groq/qwen/qwen3-32b
groq/qwen/qwen3-32b
|
Groq | $0.2900 | $0.5900 | — | — | 131,000 | text |
|
groq/qwen/qwen3.6-27b
groq/qwen/qwen3.6-27b
|
Groq | $0.6000 | $3.00 | — | — | 131,072 | text |
|
groq/qwen/qwen3.8-27b
groq/qwen/qwen3.8-27b
|
Groq | $0.8000 | $4.00 | — | — | 131,042 | text |
|
hyperbolic/deepseek-ai/DeepSeek-R1
hyperbolic/deepseek-ai/DeepSeek-R1
|
Hyperbolic | $0.4000 | $0.4000 | — | — | 32,768 | text |
|
hyperbolic/deepseek-ai/DeepSeek-R1-0528
hyperbolic/deepseek-ai/DeepSeek-R1-0528
|
Hyperbolic | $0.2500 | $0.2500 | — | — | 131,072 | text |
|
hyperbolic/deepseek-ai/DeepSeek-V3
hyperbolic/deepseek-ai/DeepSeek-V3
|
Hyperbolic | $0.2000 | $0.2000 | — | — | 32,768 | text |
|
hyperbolic/deepseek-ai/DeepSeek-V3-0324
hyperbolic/deepseek-ai/DeepSeek-V3-0324
|
Hyperbolic | $0.4000 | $0.4000 | — | — | 32,768 | text |
|
hyperbolic/meta-llama/Llama-3.2-3B-Instruct
hyperbolic/meta-llama/Llama-3.2-3B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/meta-llama/Llama-3.3-70B-Instruct
hyperbolic/meta-llama/Llama-3.3-70B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct
hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct
hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct
hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct
hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/moonshotai/Kimi-K2-Instruct
hyperbolic/moonshotai/Kimi-K2-Instruct
|
Hyperbolic | $2.00 | $2.00 | — | — | 131,072 | text |
|
hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B
hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/Qwen/Qwen2.5-72B-Instruct
hyperbolic/Qwen/Qwen2.5-72B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct
hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct
|
Hyperbolic | $0.1200 | $0.3000 | — | — | 32,768 | text |
|
hyperbolic/Qwen/Qwen3-235B-A22B
hyperbolic/Qwen/Qwen3-235B-A22B
|
Hyperbolic | $2.00 | $2.00 | — | — | 131,072 | text |
|
hyperbolic/Qwen/QwQ-32B
hyperbolic/Qwen/QwQ-32B
|
Hyperbolic | $0.2000 | $0.2000 | — | — | 131,072 | text |
|
inception/mercury-2
inception/mercury-2
|
Inception | $0.2500 | $0.7500 | $0.0250 | — | 128,000 | text |
|
inception/mercury-2.5
inception/mercury-2.5
|
Inception | $0.2000 | $0.7500 | — | — | 260,000 | text |
|
jina-reranker-v2-base-multilingual
jina-reranker-v2-base-multilingual
|
Jina Ai | $0.0500 | $0.0000 | — | — | 1,024 | rerank |
|
lambda_ai/deepseek-llama3.3-70b
lambda_ai/deepseek-llama3.3-70b
|
Lambda Ai | $0.2000 | $0.6000 | — | — | 131,072 | text |
|
lambda_ai/deepseek-r1-0528
lambda_ai/deepseek-r1-0528
|
Lambda Ai | $0.2000 | $0.6000 | — | — | 131,072 | text |
|
lambda_ai/deepseek-r1-671b
lambda_ai/deepseek-r1-671b
|
Lambda Ai | $0.8000 | $0.8000 | — | — | 131,072 | text |
|
lambda_ai/deepseek-v3-0324
lambda_ai/deepseek-v3-0324
|
Lambda Ai | $0.2000 | $0.6000 | — | — | 131,072 | text |
|
lambda_ai/hermes3-405b
lambda_ai/hermes3-405b
|
Lambda Ai | $0.8000 | $0.8000 | — | — | 131,072 | text |
|
lambda_ai/hermes3-70b
lambda_ai/hermes3-70b
|
Lambda Ai | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
lambda_ai/hermes3-8b
lambda_ai/hermes3-8b
|
Lambda Ai | $0.0250 | $0.0400 | — | — | 131,072 | text |
|
lambda_ai/lfm-40b
lambda_ai/lfm-40b
|
Lambda Ai | $0.1000 | $0.2000 | — | — | 131,072 | text |
|
lambda_ai/lfm-7b
lambda_ai/lfm-7b
|
Lambda Ai | $0.0250 | $0.0400 | — | — | 131,072 | text |
|
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
|
Lambda Ai | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
lambda_ai/llama-4-scout-17b-16e-instruct
lambda_ai/llama-4-scout-17b-16e-instruct
|
Lambda Ai | $0.0500 | $0.1000 | — | — | 16,384 | text |
|
lambda_ai/llama3.1-405b-instruct-fp8
lambda_ai/llama3.1-405b-instruct-fp8
|
Lambda Ai | $0.8000 | $0.8000 | — | — | 131,072 | text |
|
lambda_ai/llama3.1-70b-instruct-fp8
lambda_ai/llama3.1-70b-instruct-fp8
|
Lambda Ai | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
lambda_ai/llama3.1-8b-instruct
lambda_ai/llama3.1-8b-instruct
|
Lambda Ai | $0.0250 | $0.0400 | — | — | 131,072 | text |
|
lambda_ai/llama3.1-nemotron-70b-instruct-fp8
lambda_ai/llama3.1-nemotron-70b-instruct-fp8
|
Lambda Ai | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
lambda_ai/llama3.2-11b-vision-instruct
lambda_ai/llama3.2-11b-vision-instruct
|
Lambda Ai | $0.0150 | $0.0250 | — | — | 131,072 | text |
|
lambda_ai/llama3.2-3b-instruct
lambda_ai/llama3.2-3b-instruct
|
Lambda Ai | $0.0150 | $0.0250 | — | — | 131,072 | text |
|
lambda_ai/llama3.3-70b-instruct-fp8
lambda_ai/llama3.3-70b-instruct-fp8
|
Lambda Ai | $0.1200 | $0.3000 | — | — | 131,072 | text |
|
lambda_ai/qwen25-coder-32b-instruct
lambda_ai/qwen25-coder-32b-instruct
|
Lambda Ai | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
lambda_ai/qwen3-32b-fp8
lambda_ai/qwen3-32b-fp8
|
Lambda Ai | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
lemonade/Gemma-3-4b-it-GGUF
lemonade/Gemma-3-4b-it-GGUF
|
Lemonade | $0.0000 | $0.0000 | — | — | 128,000 | text |
|
lemonade/gpt-oss-120b-mxfp-GGUF
lemonade/gpt-oss-120b-mxfp-GGUF
|
Lemonade | $0.0000 | $0.0000 | — | — | 131,072 | text |
|
lemonade/gpt-oss-20b-mxfp4-GGUF
lemonade/gpt-oss-20b-mxfp4-GGUF
|
Lemonade | $0.0000 | $0.0000 | — | — | 131,072 | text |
|
lemonade/Qwen3-4B-Instruct-2507-GGUF
lemonade/Qwen3-4B-Instruct-2507-GGUF
|
Lemonade | $0.0000 | $0.0000 | — | — | 262,144 | text |
|
lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF
lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF
|
Lemonade | $0.0000 | $0.0000 | — | — | 262,144 | text |
|
libertai/bge-m3
libertai/bge-m3
|
Libertai | $0.0100 | $0.0000 | — | — | 8,192 | embedding |
|
libertai/deepseek-v4-flash
libertai/deepseek-v4-flash
|
Libertai | $0.2500 | $1.75 | — | — | 200,000 | text |
|
libertai/deepseek-v4-flash-thinking
libertai/deepseek-v4-flash-thinking
|
Libertai | $0.2500 | $1.75 | — | — | 200,000 | text |
|
libertai/gemma-4-31b-it
libertai/gemma-4-31b-it
|
Libertai | $0.1500 | $0.4000 | — | — | 262,144 | text |
|
libertai/gemma-4-31b-it-thinking
libertai/gemma-4-31b-it-thinking
|
Libertai | $0.1500 | $0.4000 | — | — | 262,144 | text |
|
libertai/hermes-3-8b-tee
libertai/hermes-3-8b-tee
|
Libertai | $0.1500 | $0.6000 | — | — | 16,000 | text |
|
libertai/qwen3.5-122b-a10b
libertai/qwen3.5-122b-a10b
|
Libertai | $0.2500 | $1.75 | — | — | 262,144 | text |
|
libertai/qwen3.5-122b-a10b-thinking
libertai/qwen3.5-122b-a10b-thinking
|
Libertai | $0.2500 | $1.75 | — | — | 262,144 | text |
|
libertai/qwen3.6-27b
libertai/qwen3.6-27b
|
Libertai | $0.1500 | $0.5000 | — | — | 262,144 | text |
|
libertai/qwen3.6-27b-thinking
libertai/qwen3.6-27b-thinking
|
Libertai | $0.1500 | $0.5000 | — | — | 262,144 | text |
|
libertai/qwen3.6-35b-a3b
libertai/qwen3.6-35b-a3b
|
Libertai | $0.1500 | $0.5000 | — | — | 262,144 | text |
|
libertai/qwen3.6-35b-a3b-thinking
libertai/qwen3.6-35b-a3b-thinking
|
Libertai | $0.1500 | $0.5000 | — | — | 262,144 | text |
|
llamagate/codellama-7b
llamagate/codellama-7b
|
Llamagate | $0.0600 | $0.1200 | — | — | 16,384 | text |
|
llamagate/deepseek-coder-6.7b
llamagate/deepseek-coder-6.7b
|
Llamagate | $0.0600 | $0.1200 | — | — | 16,384 | text |
|
llamagate/deepseek-r1-7b-qwen
llamagate/deepseek-r1-7b-qwen
|
Llamagate | $0.0800 | $0.1500 | — | — | 131,072 | text |
|
llamagate/deepseek-r1-8b
llamagate/deepseek-r1-8b
|
Llamagate | $0.1000 | $0.2000 | — | — | 65,536 | text |
|
llamagate/dolphin3-8b
llamagate/dolphin3-8b
|
Llamagate | $0.0800 | $0.1500 | — | — | 128,000 | text |
|
llamagate/gemma3-4b
llamagate/gemma3-4b
|
Llamagate | $0.0300 | $0.0800 | — | — | 128,000 | text |
|
llamagate/llama-3.1-8b
llamagate/llama-3.1-8b
|
Llamagate | $0.0300 | $0.0500 | — | — | 131,072 | text |
|
llamagate/llama-3.2-3b
llamagate/llama-3.2-3b
|
Llamagate | $0.0400 | $0.0800 | — | — | 131,072 | text |
|
llamagate/llava-7b
llamagate/llava-7b
|
Llamagate | $0.1000 | $0.2000 | — | — | 4,096 | text |
|
llamagate/mistral-7b-v0.3
llamagate/mistral-7b-v0.3
|
Llamagate | $0.1000 | $0.1500 | — | — | 32,768 | text |
|
llamagate/nomic-embed-text
llamagate/nomic-embed-text
|
Llamagate | $0.0200 | $0.0000 | — | — | 8,192 | embedding |
|
llamagate/openthinker-7b
llamagate/openthinker-7b
|
Llamagate | $0.0800 | $0.1500 | — | — | 32,768 | text |
|
llamagate/qwen2.5-coder-7b
llamagate/qwen2.5-coder-7b
|
Llamagate | $0.0600 | $0.1200 | — | — | 32,768 | text |
|
llamagate/qwen3-8b
llamagate/qwen3-8b
|
Llamagate | $0.0400 | $0.1400 | — | — | 32,768 | text |
|
llamagate/qwen3-embedding-8b
llamagate/qwen3-embedding-8b
|
Llamagate | $0.0200 | $0.0000 | — | — | 40,960 | embedding |
|
llamagate/qwen3-vl-8b
llamagate/qwen3-vl-8b
|
Llamagate | $0.1500 | $0.5500 | — | — | 32,768 | text |
|
meta/muse-spark-1.1
meta/muse-spark-1.1
|
Meta | $1.25 | $4.25 | $0.1500 | — | 1,048,576 | text |
|
meta/muse-spark-1.2
meta/muse-spark-1.2
|
Meta | $1.25 | $4.25 | $0.1500 | — | 1,048,576 | text |
|
meta/muse-spark-1.2-contributor
meta/muse-spark-1.2-contributor
|
Meta | $0.1000 | $0.2000 | $0.0020 | — | 1,048,576 | text |
|
meta/muse-spark-1.3
meta/muse-spark-1.3
|
Meta | $1.25 | $4.25 | $0.1500 | — | 1,048,576 | text |
|
meta/muse-spark-1.3-contributor
meta/muse-spark-1.3-contributor
|
Meta | $0.1000 | $0.2000 | $0.0020 | — | 1,048,576 | text |
|
minimax/MiniMax-M2
minimax/MiniMax-M2
|
Minimax | $0.3000 | $1.20 | $0.0300 | $0.3750 | 200,000 | text |
|
minimax/MiniMax-M2.1
minimax/MiniMax-M2.1
|
Minimax | $0.3000 | $1.20 | $0.0300 | $0.3750 | 1,000,000 | text |
|
minimax/MiniMax-M2.1-lightning
minimax/MiniMax-M2.1-lightning
|
Minimax | $0.3000 | $2.40 | $0.0300 | $0.3750 | 1,000,000 | text |
|
minimax/MiniMax-M2.5
minimax/MiniMax-M2.5
|
Minimax | $0.3000 | $1.20 | $0.0300 | $0.3750 | 1,000,000 | text |
|
minimax/MiniMax-M2.5-lightning
minimax/MiniMax-M2.5-lightning
|
Minimax | $0.3000 | $2.40 | $0.0300 | $0.3750 | 1,000,000 | text |
|
minimax/MiniMax-M3
minimax/MiniMax-M3
|
Minimax | $0.3000 | $1.20 | $0.0600 | — | 1,000,000 | text |
|
mistral/codestral-2405
mistral/codestral-2405
|
Mistral AI | $1.00 | $3.00 | — | — | 32,000 | text |
|
mistral/codestral-2508
mistral/codestral-2508
|
Mistral AI | $0.3000 | $0.9000 | $0.0300 | — | 128,000 | text |
|
mistral/codestral-embed
mistral/codestral-embed
|
Mistral AI | $0.1500 | — | $0.0150 | — | 8,192 | embedding |
|
mistral/codestral-embed-2505
mistral/codestral-embed-2505
|
Mistral AI | $0.1500 | — | $0.0150 | — | 8,192 | embedding |
|
mistral/codestral-latest
mistral/codestral-latest
|
Mistral AI | $0.3000 | $0.9000 | $0.0300 | — | 128,000 | text |
|
mistral/codestral-mamba-latest
mistral/codestral-mamba-latest
|
Mistral AI | $0.2500 | $0.2500 | — | — | 256,000 | text |
|
mistral/devstral-2512
mistral/devstral-2512
|
Mistral AI | $0.4000 | $2.00 | — | — | 256,000 | text |
|
mistral/devstral-latest
mistral/devstral-latest
|
Mistral AI | $0.4000 | $2.00 | — | — | 256,000 | text |
|
mistral/devstral-medium-2507
mistral/devstral-medium-2507
|
Mistral AI | $0.4000 | $2.00 | — | — | 128,000 | text |
|
mistral/devstral-medium-latest
mistral/devstral-medium-latest
|
Mistral AI | $0.4000 | $2.00 | — | — | 256,000 | text |
|
mistral/devstral-small-2505
mistral/devstral-small-2505
|
Mistral AI | $0.1000 | $0.3000 | — | — | 128,000 | text |
|
mistral/devstral-small-2507
mistral/devstral-small-2507
|
Mistral AI | $0.1000 | $0.3000 | — | — | 128,000 | 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.