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 |
|---|---|---|---|---|---|---|---|
|
replicate/ibm-granite/granite-3.0-2b-instruct
replicate/ibm-granite/granite-3.0-2b-instruct
|
Replicate | $0.0300 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-3.0-8b-instruct
replicate/ibm-granite/granite-3.0-8b-instruct
|
Replicate | $0.0500 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-3.1-2b-instruct
replicate/ibm-granite/granite-3.1-2b-instruct
|
Replicate | $0.0300 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-3.1-8b-instruct
replicate/ibm-granite/granite-3.1-8b-instruct
|
Replicate | $0.0300 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-3.2-8b-instruct
replicate/ibm-granite/granite-3.2-8b-instruct
|
Replicate | $0.0300 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-3.3-8b-instruct
replicate/ibm-granite/granite-3.3-8b-instruct
|
Replicate | $0.0300 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-4.0-h-small
replicate/ibm-granite/granite-4.0-h-small
|
Replicate | $0.0600 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-4.1-8b
replicate/ibm-granite/granite-4.1-8b
|
Replicate | $0.0600 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-4.2-8b
replicate/ibm-granite/granite-4.2-8b
|
Replicate | $0.0600 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-8b-code-instruct-128k
replicate/ibm-granite/granite-8b-code-instruct-128k
|
Replicate | $0.0500 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-speech-3.3-8b
replicate/ibm-granite/granite-speech-3.3-8b
|
Replicate | — | $4.90 | — | — | — | audio |
|
replicate/ibm-granite/granite-speech-4.1-2b
replicate/ibm-granite/granite-speech-4.1-2b
|
Replicate | $0.0300 | $0.2500 | — | — | — | audio |
|
replicate/ibm-granite/granite-vision-3.3-2b
replicate/ibm-granite/granite-vision-3.3-2b
|
Replicate | $0.0000 | $0.2500 | — | — | — | text |
|
replicate/ibm-granite/granite-vision-4.1-4b
replicate/ibm-granite/granite-vision-4.1-4b
|
Replicate | $0.0600 | $0.2500 | — | — | — | text |
|
replicate/meta/llama-2-13b
replicate/meta/llama-2-13b
|
Replicate | $0.1000 | $0.5000 | — | — | 4,096 | text |
|
replicate/meta/llama-2-13b-chat
replicate/meta/llama-2-13b-chat
|
Replicate | $0.1000 | $0.5000 | — | — | 4,096 | text |
|
replicate/meta/llama-2-70b
replicate/meta/llama-2-70b
|
Replicate | $0.6500 | $2.75 | — | — | 4,096 | text |
|
replicate/meta/llama-2-70b-chat
replicate/meta/llama-2-70b-chat
|
Replicate | $0.6500 | $2.75 | — | — | 4,096 | text |
|
replicate/meta/llama-2-7b
replicate/meta/llama-2-7b
|
Replicate | $0.0500 | $0.2500 | — | — | 4,096 | text |
|
replicate/meta/llama-2-7b-chat
replicate/meta/llama-2-7b-chat
|
Replicate | $0.0500 | $0.2500 | — | — | 4,096 | text |
|
replicate/meta/llama-3-70b
replicate/meta/llama-3-70b
|
Replicate | $0.6500 | $2.75 | — | — | 8,192 | text |
|
replicate/meta/llama-3-70b-instruct
replicate/meta/llama-3-70b-instruct
|
Replicate | $0.6500 | $2.75 | — | — | 8,192 | text |
|
replicate/meta/llama-3-8b
replicate/meta/llama-3-8b
|
Replicate | $0.0500 | $0.2500 | — | — | 8,086 | text |
|
replicate/meta/llama-3-8b-instruct
replicate/meta/llama-3-8b-instruct
|
Replicate | $0.0500 | $0.2500 | — | — | 8,086 | text |
|
replicate/meta/llama-4-maverick-instruct
replicate/meta/llama-4-maverick-instruct
|
Replicate | $0.2500 | $0.9500 | — | — | — | text |
|
replicate/meta/llama-4-scout-instruct
replicate/meta/llama-4-scout-instruct
|
Replicate | $0.1700 | $0.6500 | — | — | — | text |
|
replicate/meta/llama-guard-4-12b
replicate/meta/llama-guard-4-12b
|
Replicate | $0.2000 | $0.2000 | — | — | — | text |
|
replicate/meta/meta-llama-3-70b
replicate/meta/meta-llama-3-70b
|
Replicate | $0.6500 | $2.75 | — | — | — | text |
|
replicate/meta/meta-llama-3-70b-instruct
replicate/meta/meta-llama-3-70b-instruct
|
Replicate | $0.6500 | $2.75 | — | — | — | text |
|
replicate/meta/meta-llama-3-8b
replicate/meta/meta-llama-3-8b
|
Replicate | $0.0500 | $0.2500 | — | — | — | text |
|
replicate/meta/meta-llama-3-8b-instruct
replicate/meta/meta-llama-3-8b-instruct
|
Replicate | $0.0500 | $0.2500 | — | — | — | text |
|
replicate/minimax/speech-02-hd
replicate/minimax/speech-02-hd
|
Replicate | $100.00 | — | — | — | — | audio |
|
replicate/minimax/speech-02-turbo
replicate/minimax/speech-02-turbo
|
Replicate | $60.00 | — | — | — | — | audio |
|
replicate/minimax/speech-2.6-hd
replicate/minimax/speech-2.6-hd
|
Replicate | $100.00 | — | — | — | — | audio |
|
replicate/minimax/speech-2.6-turbo
replicate/minimax/speech-2.6-turbo
|
Replicate | $60.00 | — | — | — | — | audio |
|
replicate/minimax/speech-2.8-hd
replicate/minimax/speech-2.8-hd
|
Replicate | $100.00 | — | — | — | — | audio |
|
replicate/minimax/speech-2.8-turbo
replicate/minimax/speech-2.8-turbo
|
Replicate | $60.00 | — | — | — | — | audio |
|
replicate/mistralai/mistral-7b-instruct-v0.2
replicate/mistralai/mistral-7b-instruct-v0.2
|
Replicate | $0.0500 | $0.2500 | — | — | 4,096 | text |
|
replicate/mistralai/mistral-7b-v0.1
replicate/mistralai/mistral-7b-v0.1
|
Replicate | $0.0500 | $0.2500 | — | — | 4,096 | text |
|
replicate/mistralai/mixtral-8x7b-instruct-v0.1
replicate/mistralai/mixtral-8x7b-instruct-v0.1
|
Replicate | $0.3000 | $1.00 | — | — | 4,096 | text |
|
replicate/moonshotai/kimi-k2-thinking
replicate/moonshotai/kimi-k2-thinking
|
Replicate | $0.6600 | $2.70 | — | — | — | text |
|
replicate/moonshotai/kimi-k2.5
replicate/moonshotai/kimi-k2.5
|
Replicate | $0.7200 | $3.60 | — | — | — | text |
|
replicate/moonshotai/kimi-k2.6
replicate/moonshotai/kimi-k2.6
|
Replicate | $0.9500 | $4.00 | — | — | — | text |
|
replicate/openai/gpt-4.1
replicate/openai/gpt-4.1
|
Replicate | $2.00 | $8.00 | — | — | — | text |
|
replicate/openai/gpt-4.1-mini
replicate/openai/gpt-4.1-mini
|
Replicate | $0.4000 | $1.60 | — | — | — | text |
|
replicate/openai/gpt-4.1-nano
replicate/openai/gpt-4.1-nano
|
Replicate | $0.1000 | $0.4000 | — | — | — | text |
|
replicate/openai/gpt-4o
replicate/openai/gpt-4o
|
Replicate | $2.50 | $10.00 | — | — | — | text |
|
replicate/openai/gpt-4o-mini
replicate/openai/gpt-4o-mini
|
Replicate | $0.1500 | $0.6000 | — | — | — | text |
|
replicate/openai/gpt-4o-mini-transcribe
replicate/openai/gpt-4o-mini-transcribe
|
Replicate | $3.00 | $5.00 | — | — | — | audio |
|
replicate/openai/gpt-4o-transcribe
replicate/openai/gpt-4o-transcribe
|
Replicate | $6.00 | $10.00 | — | — | — | audio |
|
replicate/openai/gpt-5
replicate/openai/gpt-5
|
Replicate | $1.25 | $10.00 | — | — | — | text |
|
replicate/openai/gpt-5-mini
replicate/openai/gpt-5-mini
|
Replicate | $0.2500 | $2.00 | — | — | — | text |
|
replicate/openai/gpt-5-nano
replicate/openai/gpt-5-nano
|
Replicate | $0.0500 | $0.4000 | — | — | — | text |
|
replicate/openai/gpt-5-pro
replicate/openai/gpt-5-pro
|
Replicate | $15.00 | $120.00 | — | — | — | text |
|
replicate/openai/gpt-5.1
replicate/openai/gpt-5.1
|
Replicate | $1.25 | $10.00 | — | — | — | text |
|
replicate/openai/gpt-5.2
replicate/openai/gpt-5.2
|
Replicate | $1.75 | $14.00 | — | — | — | text |
|
replicate/openai/gpt-5.4
replicate/openai/gpt-5.4
|
Replicate | $2.50 | $15.00 | — | — | — | text |
|
replicate/openai/gpt-5.6-luna
replicate/openai/gpt-5.6-luna
|
Replicate | $1.00 | $6.00 | — | — | — | text |
|
replicate/openai/gpt-5.6-sol
replicate/openai/gpt-5.6-sol
|
Replicate | $2.00 | $10.00 | — | — | — | text |
|
replicate/openai/gpt-5.6-terra
replicate/openai/gpt-5.6-terra
|
Replicate | $2.50 | $15.00 | — | — | — | text |
|
replicate/openai/gpt-oss-120b
replicate/openai/gpt-oss-120b
|
Replicate | $0.1800 | $0.7200 | — | — | — | text |
|
replicate/openai/gpt-oss-20b
replicate/openai/gpt-oss-20b
|
Replicate | $0.0900 | $0.3600 | — | — | — | text |
|
replicate/openai/o1
replicate/openai/o1
|
Replicate | $15.00 | $60.00 | — | — | — | text |
|
replicate/openai/o1-mini
replicate/openai/o1-mini
|
Replicate | $1.10 | $4.40 | — | — | — | text |
|
replicate/openai/o4-mini
replicate/openai/o4-mini
|
Replicate | $1.00 | $4.00 | — | — | — | text |
|
replicate/perceptron-ai-inc/isaac-0.1
replicate/perceptron-ai-inc/isaac-0.1
|
Replicate | $0.2600 | $2.17 | — | — | — | text |
|
replicate/qwen/qwen3-235b-a22b-instruct-2507
replicate/qwen/qwen3-235b-a22b-instruct-2507
|
Replicate | $0.2640 | $1.06 | — | — | — | text |
|
replicate/qwen/qwen3-7-plus
replicate/qwen/qwen3-7-plus
|
Replicate | $0.2760 | $1.10 | — | — | — | text |
|
replicate/snowflake/snowflake-arctic-instruct
replicate/snowflake/snowflake-arctic-instruct
|
Replicate | $20.00 | $20.00 | — | — | — | text |
|
replicate/xai/grok-4
replicate/xai/grok-4
|
Replicate | $7.20 | $36.00 | — | — | — | text |
|
replicateopenai/gpt-oss-20b
replicateopenai/gpt-oss-20b
|
Replicate | $0.0900 | $0.3600 | — | — | — | text |
|
sagemaker/meta-textgeneration-llama-2-13b
sagemaker/meta-textgeneration-llama-2-13b
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sagemaker/meta-textgeneration-llama-2-13b-f
sagemaker/meta-textgeneration-llama-2-13b-f
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sagemaker/meta-textgeneration-llama-2-70b
sagemaker/meta-textgeneration-llama-2-70b
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sagemaker/meta-textgeneration-llama-2-70b-b-f
sagemaker/meta-textgeneration-llama-2-70b-b-f
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sagemaker/meta-textgeneration-llama-2-7b
sagemaker/meta-textgeneration-llama-2-7b
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sagemaker/meta-textgeneration-llama-2-7b-f
sagemaker/meta-textgeneration-llama-2-7b-f
|
Sagemaker | $0.0000 | $0.0000 | — | — | 4,096 | text |
|
sail/deepseek-ai/DeepSeek-V4-Flash-0731
sail/deepseek-ai/DeepSeek-V4-Flash-0731
|
Sail | $0.0900 | $0.1800 | $0.0200 | — | 1,048,576 | text |
|
sail/deepseek-ai/DeepSeek-V4-Pro-0813
sail/deepseek-ai/DeepSeek-V4-Pro-0813
|
Sail | $0.9200 | $2.77 | $0.0400 | — | 1,048,576 | text |
|
sail/deepseek-ai/DeepSeek-V4.1-Flash
sail/deepseek-ai/DeepSeek-V4.1-Flash
|
Sail | $0.0900 | $0.3000 | $0.0060 | — | 1,048,576 | text |
|
sail/google/gemma-4-12B-it
sail/google/gemma-4-12B-it
|
Sail | $0.3000 | $2.00 | $0.1500 | — | 16,384 | text |
|
sail/google/gemma-4-31B-it
sail/google/gemma-4-31B-it
|
Sail | $0.4000 | $0.6000 | $0.2000 | — | 256,000 | text |
|
sail/moonshotai/Kimi-K2.6
sail/moonshotai/Kimi-K2.6
|
Sail | $1.00 | $4.00 | $0.2000 | — | 262,144 | text |
|
sail/moonshotai/Kimi-K3
sail/moonshotai/Kimi-K3
|
Sail | $2.50 | $12.50 | $0.2500 | — | 1,048,576 | text |
|
sail/nvidia/Gemma-4-31B-IT-NVFP4
sail/nvidia/Gemma-4-31B-IT-NVFP4
|
Sail | $0.1400 | $0.4000 | $0.0700 | — | 262,144 | text |
|
sail/openai/gpt-oss-120b
sail/openai/gpt-oss-120b
|
Sail | $0.0600 | $0.4000 | $0.0300 | — | 131,072 | text |
|
sail/Qwen/Qwen3.6-35B-A3B
sail/Qwen/Qwen3.6-35B-A3B
|
Sail | $0.0500 | $0.4000 | $0.0200 | — | 262,144 | text |
|
sail/zai-org/GLM-5.3
sail/zai-org/GLM-5.3
|
Sail | $0.9800 | $3.08 | $0.1800 | — | 1,048,576 | text |
|
sail/zai-org/GLM-5.3-Flash
sail/zai-org/GLM-5.3-Flash
|
Sail | $0.1100 | $0.3500 | $0.0200 | — | 1,048,576 | text |
|
sambanova/DeepSeek-R1
sambanova/DeepSeek-R1
|
Sambanova | $5.00 | $7.00 | — | — | 32,768 | text |
|
sambanova/DeepSeek-R1-Distill-Llama-70B
sambanova/DeepSeek-R1-Distill-Llama-70B
|
Sambanova | $0.7000 | $1.40 | — | — | 131,072 | text |
|
sambanova/DeepSeek-V3-0324
sambanova/DeepSeek-V3-0324
|
Sambanova | $3.00 | $4.50 | — | — | 32,768 | text |
|
sambanova/DeepSeek-V3.1
sambanova/DeepSeek-V3.1
|
Sambanova | $3.00 | $4.50 | — | — | 131,072 | text |
|
sambanova/DeepSeek-V3.2
sambanova/DeepSeek-V3.2
|
Sambanova | $3.00 | $4.50 | — | — | 32,768 | text |
|
sambanova/gemma-4-31B-it
sambanova/gemma-4-31B-it
|
Sambanova | $0.3800 | $1.15 | — | — | 131,072 | text |
|
sambanova/gpt-oss-120b
sambanova/gpt-oss-120b
|
Sambanova | $0.2200 | $0.5900 | — | — | 131,072 | text |
|
sambanova/Llama-4-Maverick-17B-128E-Instruct
sambanova/Llama-4-Maverick-17B-128E-Instruct
|
Sambanova | $0.6300 | $1.80 | — | — | 131,072 | text |
|
sambanova/Llama-4-Scout-17B-16E-Instruct
sambanova/Llama-4-Scout-17B-16E-Instruct
|
Sambanova | $0.4000 | $0.7000 | — | — | 8,192 | text |
|
sambanova/Meta-Llama-3.1-405B-Instruct
sambanova/Meta-Llama-3.1-405B-Instruct
|
Sambanova | $5.00 | $10.00 | — | — | 16,384 | text |
|
sambanova/Meta-Llama-3.1-8B-Instruct
sambanova/Meta-Llama-3.1-8B-Instruct
|
Sambanova | $0.1000 | $0.2000 | — | — | 16,384 | 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.