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 |
|---|---|---|---|---|---|---|---|
|
sambanova/Meta-Llama-3.2-1B-Instruct
sambanova/Meta-Llama-3.2-1B-Instruct
|
Sambanova | $0.0400 | $0.0800 | — | — | 16,384 | text |
|
sambanova/Meta-Llama-3.2-3B-Instruct
sambanova/Meta-Llama-3.2-3B-Instruct
|
Sambanova | $0.0800 | $0.1600 | — | — | 4,096 | text |
|
sambanova/Meta-Llama-3.3-70B-Instruct
sambanova/Meta-Llama-3.3-70B-Instruct
|
Sambanova | $0.6000 | $1.20 | — | — | 131,072 | text |
|
sambanova/Meta-Llama-Guard-3-8B
sambanova/Meta-Llama-Guard-3-8B
|
Sambanova | $0.3000 | $0.3000 | — | — | 16,384 | text |
|
sambanova/MiniMax-M2.7
sambanova/MiniMax-M2.7
|
Sambanova | $0.6000 | $2.40 | — | — | 196,608 | text |
|
sambanova/Qwen2-Audio-7B-Instruct
sambanova/Qwen2-Audio-7B-Instruct
|
Sambanova | $0.5000 | $100.00 | — | — | 4,096 | text |
|
sambanova/Qwen3-32B
sambanova/Qwen3-32B
|
Sambanova | $0.4000 | $0.8000 | — | — | 8,192 | text |
|
sambanova/QwQ-32B
sambanova/QwQ-32B
|
Sambanova | $0.5000 | $1.00 | — | — | 16,384 | text |
|
sarvam/sarvam-m
sarvam/sarvam-m
|
Sarvam | $0.0000 | $0.0000 | $0.0000 | $0.0000 | 8,192 | text |
|
scaledown/classify
scaledown/classify
|
Scaledown | $0.0500 | $0.0000 | — | — | — | text |
|
scaledown/compress
scaledown/compress
|
Scaledown | $0.0500 | $0.0000 | — | — | — | text |
|
scaledown/decisions
scaledown/decisions
|
Scaledown | $0.0500 | $0.0000 | — | — | — | text |
|
scaledown/extract
scaledown/extract
|
Scaledown | $0.0500 | $0.0000 | — | — | — | text |
|
scaledown/summarize
scaledown/summarize
|
Scaledown | $0.0500 | $0.0000 | — | — | — | text |
|
scaleway/BAAI/bge-multilingual-gemma2
scaleway/BAAI/bge-multilingual-gemma2
|
Scaleway | $0.1000 | $0.0000 | — | — | — | embedding |
|
scaleway/deepseek-v4-flash-0731
scaleway/deepseek-v4-flash-0731
|
Scaleway | $0.4000 | $0.8000 | $0.0800 | — | 256,000 | text |
|
scaleway/glm-5.2
scaleway/glm-5.2
|
Scaleway | $1.80 | $5.50 | — | — | 256,000 | text |
|
scaleway/google/gemma-3-27b-it
scaleway/google/gemma-3-27b-it
|
Scaleway | $0.2500 | $0.5000 | — | — | 40,000 | text |
|
scaleway/google/gemma-4-26b-a4b-it
scaleway/google/gemma-4-26b-a4b-it
|
Scaleway | $0.2500 | $0.5000 | — | — | 256,000 | text |
|
scaleway/hcompany/holo2-30b-a3b
scaleway/hcompany/holo2-30b-a3b
|
Scaleway | $0.3000 | $0.7000 | — | — | 22,000 | text |
|
scaleway/meta/llama-3.3-70b-instruct
scaleway/meta/llama-3.3-70b-instruct
|
Scaleway | $0.9000 | $0.9000 | — | — | 128,000 | text |
|
scaleway/mistralai/devstral-2-123b-instruct-2512
scaleway/mistralai/devstral-2-123b-instruct-2512
|
Scaleway | $0.4000 | $2.00 | — | — | 200,000 | text |
|
scaleway/mistralai/mistral-medium-3.5-128b
scaleway/mistralai/mistral-medium-3.5-128b
|
Scaleway | $1.50 | $7.50 | — | — | 256,000 | text |
|
scaleway/mistralai/mistral-small-3.2-24b-instruct-2506
scaleway/mistralai/mistral-small-3.2-24b-instruct-2506
|
Scaleway | $0.1500 | $0.3500 | — | — | 128,000 | text |
|
scaleway/mistralai/pixtral-12b-2409
scaleway/mistralai/pixtral-12b-2409
|
Scaleway | $0.2000 | $0.2000 | — | — | 128,000 | text |
|
scaleway/mistralai/voxtral-small-24b-2507
scaleway/mistralai/voxtral-small-24b-2507
|
Scaleway | $0.1500 | $0.3500 | — | — | 32,000 | text |
|
scaleway/openai/gpt-oss-120b
scaleway/openai/gpt-oss-120b
|
Scaleway | $0.1500 | $0.6000 | — | — | 128,000 | text |
|
scaleway/openai/whisper-large-v3
scaleway/openai/whisper-large-v3
|
Scaleway | — | $0.0000 | — | — | — | audio |
|
scaleway/qwen/qwen3-235b-a22b-instruct-2507
scaleway/qwen/qwen3-235b-a22b-instruct-2507
|
Scaleway | $0.7500 | $2.25 | — | — | 256,000 | text |
|
scaleway/qwen/qwen3-coder-30b-a3b-instruct
scaleway/qwen/qwen3-coder-30b-a3b-instruct
|
Scaleway | $0.2000 | $0.8000 | — | — | 128,000 | text |
|
scaleway/qwen/qwen3-embedding-8b
scaleway/qwen/qwen3-embedding-8b
|
Scaleway | $0.1000 | $0.0000 | — | — | — | embedding |
|
scaleway/qwen/qwen3.5-397b-a17b
scaleway/qwen/qwen3.5-397b-a17b
|
Scaleway | $0.6000 | $3.60 | — | — | 256,000 | text |
|
scaleway/qwen/qwen3.6-35b-a3b
scaleway/qwen/qwen3.6-35b-a3b
|
Scaleway | $0.2500 | $1.50 | — | — | 256,000 | text |
|
scx-ai/DeepSeek-V4.1-flash
scx-ai/DeepSeek-V4.1-flash
|
Scx-Ai | $0.1500 | $0.6000 | $0.0100 | — | 1,000,000 | text |
|
scx-ai/GLM-5.2
scx-ai/GLM-5.2
|
Scx-Ai | $0.6100 | $1.98 | $0.2200 | — | 1,048,576 | text |
|
scx-ai/GLM-5.3
scx-ai/GLM-5.3
|
Scx-Ai | $0.9800 | $3.08 | $0.1800 | — | 1,000,000 | text |
|
scx-ai/Kimi-K3
scx-ai/Kimi-K3
|
Scx-Ai | $2.83 | $14.13 | $0.2800 | — | 1,000,000 | text |
|
scx-ai/Qwen3.8-Max
scx-ai/Qwen3.8-Max
|
Scx-Ai | $1.65 | $4.99 | $0.2100 | — | 1,000,000 | text |
|
snowflake/claude-3-5-sonnet
snowflake/claude-3-5-sonnet
|
Snowflake | $3.00 | $15.00 | $0.3000 | — | 200,000 | text |
|
snowflake/claude-3-7-sonnet
snowflake/claude-3-7-sonnet
|
Snowflake | $3.00 | $15.00 | $0.3000 | — | 200,000 | text |
|
snowflake/claude-4-opus
snowflake/claude-4-opus
|
Snowflake | $5.00 | $25.00 | $0.5000 | — | 200,000 | text |
|
snowflake/claude-4-sonnet
snowflake/claude-4-sonnet
|
Snowflake | $3.00 | $15.00 | $0.3000 | — | 200,000 | text |
|
snowflake/claude-haiku-4-5
snowflake/claude-haiku-4-5
|
Snowflake | $1.00 | $5.00 | $0.1000 | — | 200,000 | text |
|
snowflake/claude-sonnet-4-5
snowflake/claude-sonnet-4-5
|
Snowflake | $3.00 | $15.00 | $0.3000 | — | 200,000 | text |
|
snowflake/claude-sonnet-4-6
snowflake/claude-sonnet-4-6
|
Snowflake | $3.00 | $15.00 | $0.3000 | — | 200,000 | text |
|
snowflake/deepseek-r1
snowflake/deepseek-r1
|
Snowflake | $1.35 | $5.40 | — | — | 128,000 | text |
|
snowflake/llama3.1-405b
snowflake/llama3.1-405b
|
Snowflake | $1.20 | $1.20 | — | — | 128,000 | text |
|
snowflake/llama3.1-70b
snowflake/llama3.1-70b
|
Snowflake | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
snowflake/llama3.1-8b
snowflake/llama3.1-8b
|
Snowflake | $0.2400 | $0.2400 | — | — | 128,000 | text |
|
snowflake/llama3.3-70b
snowflake/llama3.3-70b
|
Snowflake | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
snowflake/llama4-maverick
snowflake/llama4-maverick
|
Snowflake | $0.2400 | $0.9700 | — | — | 128,000 | text |
|
snowflake/mistral-large2
snowflake/mistral-large2
|
Snowflake | $2.00 | $6.00 | — | — | 128,000 | text |
|
snowflake/openai-gpt-4.1
snowflake/openai-gpt-4.1
|
Snowflake | $2.00 | $8.00 | $0.5000 | — | 300,000 | text |
|
snowflake/openai-gpt-5
snowflake/openai-gpt-5
|
Snowflake | $1.25 | $10.00 | $0.1250 | — | 300,000 | text |
|
snowflake/openai-gpt-5-mini
snowflake/openai-gpt-5-mini
|
Snowflake | $0.3000 | $1.20 | — | — | 1,000,000 | text |
|
snowflake/openai-gpt-5-nano
snowflake/openai-gpt-5-nano
|
Snowflake | $0.1500 | $0.6000 | — | — | 5,000,000 | text |
|
snowflake/snowflake-arctic-embed-l-v2.0
snowflake/snowflake-arctic-embed-l-v2.0
|
Snowflake | $0.0700 | $0.0000 | — | — | 8,192 | embedding |
|
snowflake/snowflake-arctic-embed-m-v2.0
snowflake/snowflake-arctic-embed-m-v2.0
|
Snowflake | $0.0700 | $0.0000 | — | — | 8,192 | embedding |
|
snowflake/snowflake-llama-3.3-70b
snowflake/snowflake-llama-3.3-70b
|
Snowflake | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
strands_decider/strands-decider-2B-hobson-v19
strands_decider/strands-decider-2B-hobson-v19
|
Strands Decider | $0.0000 | $0.0000 | — | — | — | text |
|
streamlake/deepseek-r1
streamlake/deepseek-r1
|
Streamlake | $0.5710 | $2.29 | $0.2290 | — | 98,304 | text |
|
streamlake/DeepSeek-V3
streamlake/DeepSeek-V3
|
Streamlake | $0.2860 | $1.14 | $0.1140 | — | 56,000 | text |
|
streamlake/deepseek-v3.1
streamlake/deepseek-v3.1
|
Streamlake | $0.5710 | $1.71 | $0.2290 | — | 98,304 | text |
|
streamlake/deepseek-v4-flash
streamlake/deepseek-v4-flash
|
Streamlake | $0.1400 | $0.2800 | $0.0280 | — | 1,048,576 | text |
|
streamlake/deepseek-v4-flash-0731
streamlake/deepseek-v4-flash-0731
|
Streamlake | $0.4400 | $1.32 | $0.0140 | — | 1,048,576 | text |
|
streamlake/deepseek-v4-pro
streamlake/deepseek-v4-pro
|
Streamlake | $1.74 | $3.48 | $0.1450 | — | 1,048,576 | text |
|
streamlake/DeepSeek-V4-Pro-0813
streamlake/DeepSeek-V4-Pro-0813
|
Streamlake | $1.32 | $3.96 | $0.0440 | — | 1,048,566 | text |
|
streamlake/deepseek-v4.1-flash-1017
streamlake/deepseek-v4.1-flash-1017
|
Streamlake | $0.3000 | $1.20 | $0.0060 | — | 1,048,576 | text |
|
streamlake/deepseek-v4.1-flash-260910
streamlake/deepseek-v4.1-flash-260910
|
Streamlake | $0.3000 | $1.20 | $0.0060 | — | 1,048,568 | text |
|
streamlake/glm-5
streamlake/glm-5
|
Streamlake | $1.00 | $3.20 | $0.2000 | — | 202,752 | text |
|
streamlake/glm-5.1
streamlake/glm-5.1
|
Streamlake | $1.40 | $4.40 | $0.2600 | — | 202,752 | text |
|
streamlake/glm-5.2
streamlake/glm-5.2
|
Streamlake | $1.40 | $4.40 | $0.2600 | — | 1,048,566 | text |
|
streamlake/GLM-5.3
streamlake/GLM-5.3
|
Streamlake | $1.40 | $4.40 | $0.2600 | — | 1,048,576 | text |
|
streamlake/GLM-5.3-Flash
streamlake/GLM-5.3-Flash
|
Streamlake | $0.1500 | $0.5000 | $0.0300 | — | 1,048,576 | text |
|
streamlake/Kimi-K2-Instruct-0905
streamlake/Kimi-K2-Instruct-0905
|
Streamlake | $0.5710 | $2.29 | $0.1430 | — | 224,000 | text |
|
streamlake/kimi-k2.6
streamlake/kimi-k2.6
|
Streamlake | $0.9500 | $4.00 | $0.1600 | — | 262,144 | text |
|
streamlake/kimi-k2.7-code
streamlake/kimi-k2.7-code
|
Streamlake | $0.9500 | $4.00 | $0.1900 | — | 262,144 | text |
|
streamlake/mimo-v2.6-flash
streamlake/mimo-v2.6-flash
|
Streamlake | $0.1400 | $0.2800 | $0.0028 | — | — | text |
|
streamlake/mimo-v2.6-pro
streamlake/mimo-v2.6-pro
|
Streamlake | $0.4350 | $0.8700 | $0.0036 | — | — | text |
|
streamlake/minimax-m2.5
streamlake/minimax-m2.5
|
Streamlake | $0.3000 | $1.20 | $0.0300 | $0.3750 | 196,608 | text |
|
streamlake/minimax-m3
streamlake/minimax-m3
|
Streamlake | $0.6000 | $2.40 | $0.1200 | — | 1,000,000 | text |
|
streamlake/qwen3.5-397b-a17b
streamlake/qwen3.5-397b-a17b
|
Streamlake | $0.6000 | $3.60 | $0.1200 | — | 258,048 | text |
|
streamlake/qwen3.6-27b
streamlake/qwen3.6-27b
|
Streamlake | $0.6000 | $3.60 | — | — | 229,376 | text |
|
streamlake/qwen3.6-35b-a3b
streamlake/qwen3.6-35b-a3b
|
Streamlake | $0.3750 | $2.25 | — | — | 229,376 | text |
|
streamlake/qwen3.8-2.4t-a95b
streamlake/qwen3.8-2.4t-a95b
|
Streamlake | $2.00 | $6.00 | $0.2500 | $2.50 | 983,616 | text |
|
streamlake/qwen3.8-27b
streamlake/qwen3.8-27b
|
Streamlake | $0.5000 | $3.00 | $0.1000 | $0.6250 | 983,616 | text |
|
tencent/deepseek-v4-flash
tencent/deepseek-v4-flash
|
Tencent | $0.1400 | $0.2800 | $0.0028 | $0.0000 | 1,000,000 | text |
|
tencent/deepseek-v4-pro
tencent/deepseek-v4-pro
|
Tencent | $1.74 | $3.48 | $0.1450 | $0.0000 | 1,000,000 | text |
|
tencent/deepseek-v4-pro-0813
tencent/deepseek-v4-pro-0813
|
Tencent | $1.32 | $3.96 | $0.0440 | $0.0000 | 1,000,000 | text |
|
tencent/deepseek-v4.1-flash
tencent/deepseek-v4.1-flash
|
Tencent | $0.3000 | $1.20 | $0.0060 | $0.0000 | 1,000,000 | text |
|
tencent/glm-5.2
tencent/glm-5.2
|
Tencent | $1.40 | $4.40 | $0.2600 | $0.0000 | 1,000,000 | text |
|
tencent/glm-5.3
tencent/glm-5.3
|
Tencent | $1.40 | $4.40 | $0.2600 | $0.0000 | 1,000,000 | text |
|
tencent/glm-5.3-flash
tencent/glm-5.3-flash
|
Tencent | $0.1500 | $0.5000 | $0.0300 | $0.0000 | 1,000,000 | text |
|
tencent/glm-5.3-flashx
tencent/glm-5.3-flashx
|
Tencent | $0.3700 | $1.25 | $0.0750 | $0.0000 | 1,000,000 | text |
|
tencent/hy4
tencent/hy4
|
Tencent | $0.4170 | $1.25 | $0.0210 | — | 960,000 | text |
|
tencent/hy4-preview
tencent/hy4-preview
|
Tencent | $0.4170 | $1.25 | $0.0210 | — | 960,000 | text |
|
tencent/kimi-k2.7-code
tencent/kimi-k2.7-code
|
Tencent | $0.9500 | $4.00 | $0.1900 | $0.0000 | 256,000 | text |
|
tencent/kimi-k2.7-code-highspeed
tencent/kimi-k2.7-code-highspeed
|
Tencent | $1.90 | $8.00 | $0.3800 | $0.0000 | 256,000 | text |
|
tencent/kimi-k2.8-preview
tencent/kimi-k2.8-preview
|
Tencent | $1.00 | $4.00 | $0.2500 | $0.0000 | 1,000,000 | text |
|
tencent/kimi-k3
tencent/kimi-k3
|
Tencent | $3.00 | $15.00 | $0.3000 | $0.0000 | 1,000,000 | 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.