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 |
|---|---|---|---|---|---|---|---|
|
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct
|
Deepinfra | $0.4000 | $0.4000 | — | — | 131,072 | text |
|
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
|
Deepinfra | $0.4000 | $0.4000 | — | — | 131,072 | text |
|
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct
|
Deepinfra | $0.0300 | $0.0500 | — | — | 131,072 | text |
|
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
|
Deepinfra | $0.0200 | $0.0400 | — | — | 131,072 | text |
|
deepinfra/meta-models/Muse-Glimmer-30B
deepinfra/meta-models/Muse-Glimmer-30B
|
Deepinfra | $0.3000 | $1.20 | $0.0400 | — | 131,072 | text |
|
deepinfra/microsoft/phi-4
deepinfra/microsoft/phi-4
|
Deepinfra | $0.0700 | $0.1400 | — | — | 16,384 | text |
|
deepinfra/microsoft/WizardLM-2-8x22B
deepinfra/microsoft/WizardLM-2-8x22B
|
Deepinfra | $0.4800 | $0.4800 | — | — | 65,536 | text |
|
deepinfra/MiniMaxAI/MiniMax-M2.7
deepinfra/MiniMaxAI/MiniMax-M2.7
|
Deepinfra | $0.2500 | $1.00 | $0.0500 | — | 196,608 | text |
|
deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo
deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo
|
Deepinfra | $0.3800 | $1.70 | $0.0700 | — | 196,608 | text |
|
deepinfra/MiniMaxAI/MiniMax-M3
deepinfra/MiniMaxAI/MiniMax-M3
|
Deepinfra | $0.2800 | $1.10 | $0.0560 | — | 524,288 | text |
|
deepinfra/mistralai/Mistral-Nemo-Instruct-2407
deepinfra/mistralai/Mistral-Nemo-Instruct-2407
|
Deepinfra | $0.0290 | $0.0300 | — | — | 131,072 | text |
|
deepinfra/mistralai/Mistral-Small-24B-Instruct-2501
deepinfra/mistralai/Mistral-Small-24B-Instruct-2501
|
Deepinfra | $0.0500 | $0.0800 | — | — | 32,768 | text |
|
deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506
deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
Deepinfra | $0.0750 | $0.2000 | — | — | 128,000 | text |
|
deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1
deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1
|
Deepinfra | $0.4000 | $0.4000 | — | — | 32,768 | text |
|
deepinfra/moonshotai/Kimi-K2-Instruct
deepinfra/moonshotai/Kimi-K2-Instruct
|
Deepinfra | $0.5000 | $2.00 | — | — | 131,072 | text |
|
deepinfra/moonshotai/Kimi-K2-Instruct-0905
deepinfra/moonshotai/Kimi-K2-Instruct-0905
|
Deepinfra | $0.5000 | $2.00 | $0.4000 | — | 262,144 | text |
|
deepinfra/moonshotai/Kimi-K2.5
deepinfra/moonshotai/Kimi-K2.5
|
Deepinfra | $0.4500 | $2.25 | $0.0700 | — | 262,144 | text |
|
deepinfra/moonshotai/Kimi-K2.6
deepinfra/moonshotai/Kimi-K2.6
|
Deepinfra | $0.7500 | $3.50 | $0.1500 | — | 262,144 | text |
|
deepinfra/moonshotai/Kimi-K2.7-Code
deepinfra/moonshotai/Kimi-K2.7-Code
|
Deepinfra | $0.6800 | $3.40 | $0.1360 | — | 262,144 | text |
|
deepinfra/moonshotai/Kimi-K3
deepinfra/moonshotai/Kimi-K3
|
Deepinfra | $2.85 | $14.25 | $0.2850 | — | 1,048,576 | text |
|
deepinfra/NousResearch/Hermes-3-Llama-3.1-405B
deepinfra/NousResearch/Hermes-3-Llama-3.1-405B
|
Deepinfra | $1.00 | $1.00 | — | — | 131,072 | text |
|
deepinfra/NousResearch/Hermes-3-Llama-3.1-70B
deepinfra/NousResearch/Hermes-3-Llama-3.1-70B
|
Deepinfra | $0.7000 | $0.7000 | — | — | 131,072 | text |
|
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
|
Deepinfra | $0.6000 | $0.6000 | — | — | 131,072 | text |
|
deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
|
Deepinfra | $0.1000 | $0.4000 | — | — | 131,072 | text |
|
deepinfra/nvidia/Nemotron-3-Nano-30B-A3B
deepinfra/nvidia/Nemotron-3-Nano-30B-A3B
|
Deepinfra | $0.0500 | $0.2000 | $0.0250 | — | 262,144 | text |
|
deepinfra/nvidia/Nemotron-Content-Safety-3.5
deepinfra/nvidia/Nemotron-Content-Safety-3.5
|
Deepinfra | $0.2000 | $0.2000 | — | — | 131,072 | text |
|
deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
|
Deepinfra | $0.0750 | $0.4000 | — | — | 262,144 | text |
|
deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
|
Deepinfra | $0.5000 | $2.20 | $0.1000 | — | 262,144 | text |
|
deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning
deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning
|
Deepinfra | $0.0600 | $0.1600 | $0.0400 | — | 262,144 | text |
|
deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2
deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2
|
Deepinfra | $0.0400 | $0.1600 | — | — | 131,072 | text |
|
deepinfra/openai/gpt-oss-120b
deepinfra/openai/gpt-oss-120b
|
Deepinfra | $0.0370 | $0.1700 | — | — | 131,072 | text |
|
deepinfra/openai/gpt-oss-120b-Turbo
deepinfra/openai/gpt-oss-120b-Turbo
|
Deepinfra | $0.1500 | $0.6000 | — | — | 131,072 | text |
|
deepinfra/openai/gpt-oss-120b-Ultra
deepinfra/openai/gpt-oss-120b-Ultra
|
Deepinfra | $0.2000 | $0.9500 | — | — | 131,072 | text |
|
deepinfra/openai/gpt-oss-20b
deepinfra/openai/gpt-oss-20b
|
Deepinfra | $0.0300 | $0.1400 | — | — | 131,072 | text |
|
deepinfra/Qwen/Qwen2.5-72B-Instruct
deepinfra/Qwen/Qwen2.5-72B-Instruct
|
Deepinfra | $0.3600 | $0.4000 | — | — | 32,768 | text |
|
deepinfra/Qwen/Qwen2.5-7B-Instruct
deepinfra/Qwen/Qwen2.5-7B-Instruct
|
Deepinfra | $0.0400 | $0.1000 | — | — | 32,768 | text |
|
deepinfra/Qwen/Qwen2.5-VL-32B-Instruct
deepinfra/Qwen/Qwen2.5-VL-32B-Instruct
|
Deepinfra | $0.2000 | $0.6000 | — | — | 128,000 | text |
|
deepinfra/Qwen/Qwen3-14B
deepinfra/Qwen/Qwen3-14B
|
Deepinfra | $0.1200 | $0.2400 | — | — | 40,960 | text |
|
deepinfra/Qwen/Qwen3-235B-A22B
deepinfra/Qwen/Qwen3-235B-A22B
|
Deepinfra | $0.1800 | $0.5400 | — | — | 40,960 | text |
|
deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507
deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507
|
Deepinfra | $0.0900 | $0.5500 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507
deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507
|
Deepinfra | $0.3000 | $2.90 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-30B-A3B
deepinfra/Qwen/Qwen3-30B-A3B
|
Deepinfra | $0.1200 | $0.5000 | — | — | 40,960 | text |
|
deepinfra/Qwen/Qwen3-32B
deepinfra/Qwen/Qwen3-32B
|
Deepinfra | $0.0800 | $0.2800 | — | — | 40,960 | text |
|
deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct
deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct
|
Deepinfra | $0.4000 | $1.60 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
|
Deepinfra | $0.3000 | $1.00 | $0.1000 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-Max
deepinfra/Qwen/Qwen3-Max
|
Deepinfra | $1.20 | $6.00 | $0.2400 | — | 256,000 | text |
|
deepinfra/Qwen/Qwen3-Max-Thinking
deepinfra/Qwen/Qwen3-Max-Thinking
|
Deepinfra | $1.20 | $6.00 | $0.2400 | — | 256,000 | text |
|
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
|
Deepinfra | $0.0900 | $1.10 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking
deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking
|
Deepinfra | $0.1400 | $1.40 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct
deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct
|
Deepinfra | $0.2000 | $0.8800 | $0.1100 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
|
Deepinfra | $0.1500 | $0.6000 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.5-122B-A10B
deepinfra/Qwen/Qwen3.5-122B-A10B
|
Deepinfra | $0.2900 | $2.40 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.5-27B
deepinfra/Qwen/Qwen3.5-27B
|
Deepinfra | $0.2600 | $2.60 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.5-35B-A3B
deepinfra/Qwen/Qwen3.5-35B-A3B
|
Deepinfra | $0.1400 | $1.00 | $0.0500 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.5-397B-A17B
deepinfra/Qwen/Qwen3.5-397B-A17B
|
Deepinfra | $0.4500 | $3.00 | $0.2200 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.5-9B
deepinfra/Qwen/Qwen3.5-9B
|
Deepinfra | $0.1000 | $0.1500 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.6-27B
deepinfra/Qwen/Qwen3.6-27B
|
Deepinfra | $0.3200 | $3.20 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.6-35B-A3B
deepinfra/Qwen/Qwen3.6-35B-A3B
|
Deepinfra | $0.1000 | $0.9500 | — | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.7-Max
deepinfra/Qwen/Qwen3.7-Max
|
Deepinfra | $2.50 | $7.50 | $0.5000 | — | 256,000 | text |
|
deepinfra/Qwen/Qwen3.8-2.4T-A95B
deepinfra/Qwen/Qwen3.8-2.4T-A95B
|
Deepinfra | $2.00 | $6.00 | $0.2000 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.8-27B
deepinfra/Qwen/Qwen3.8-27B
|
Deepinfra | $0.4000 | $3.00 | $0.0400 | — | 262,144 | text |
|
deepinfra/Qwen/Qwen3.8-Max
deepinfra/Qwen/Qwen3.8-Max
|
Deepinfra | $1.65 | $4.95 | $0.2060 | — | 256,000 | text |
|
deepinfra/Qwen/QwQ-32B
deepinfra/Qwen/QwQ-32B
|
Deepinfra | $0.1500 | $0.4000 | — | — | 131,072 | text |
|
deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo
deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo
|
Deepinfra | $0.0400 | $0.0500 | — | — | 8,192 | text |
|
deepinfra/Sao10K/L3.1-70B-Euryale-v2.2
deepinfra/Sao10K/L3.1-70B-Euryale-v2.2
|
Deepinfra | $0.8500 | $0.8500 | — | — | 131,072 | text |
|
deepinfra/Sao10K/L3.3-70B-Euryale-v2.3
deepinfra/Sao10K/L3.3-70B-Euryale-v2.3
|
Deepinfra | $0.6500 | $0.7500 | — | — | 131,072 | text |
|
deepinfra/stepfun-ai/Step-3.7-Flash
deepinfra/stepfun-ai/Step-3.7-Flash
|
Deepinfra | $0.2000 | $1.15 | $0.0400 | — | 262,144 | text |
|
deepinfra/tencent/Hy3
deepinfra/tencent/Hy3
|
Deepinfra | $0.1400 | $0.5800 | $0.0350 | — | 262,144 | text |
|
deepinfra/thinkingmachines/Inkling
deepinfra/thinkingmachines/Inkling
|
Deepinfra | $0.9500 | $4.05 | $0.1600 | — | 524,288 | text |
|
deepinfra/thinkingmachines/Inkling-Small
deepinfra/thinkingmachines/Inkling-Small
|
Deepinfra | $0.4500 | $1.20 | $0.1000 | — | 524,288 | text |
|
deepinfra/XiaomiMiMo/MiMo-V2.5
deepinfra/XiaomiMiMo/MiMo-V2.5
|
Deepinfra | $0.4000 | $2.00 | $0.0800 | — | 262,144 | text |
|
deepinfra/XiaomiMiMo/MiMo-V2.5-Pro
deepinfra/XiaomiMiMo/MiMo-V2.5-Pro
|
Deepinfra | $1.00 | $3.00 | $0.2000 | — | 1,048,576 | text |
|
deepinfra/zai-org/GLM-4.5
deepinfra/zai-org/GLM-4.5
|
Deepinfra | $0.4000 | $1.60 | — | — | 131,072 | text |
|
deepinfra/zai-org/GLM-4.6
deepinfra/zai-org/GLM-4.6
|
Deepinfra | $0.5000 | $2.00 | $0.1000 | — | 202,752 | text |
|
deepinfra/zai-org/GLM-4.7
deepinfra/zai-org/GLM-4.7
|
Deepinfra | $0.4000 | $1.75 | $0.0800 | — | 202,752 | text |
|
deepinfra/zai-org/GLM-4.7-Flash
deepinfra/zai-org/GLM-4.7-Flash
|
Deepinfra | $0.0600 | $0.4000 | $0.0100 | — | 202,752 | text |
|
deepinfra/zai-org/GLM-5
deepinfra/zai-org/GLM-5
|
Deepinfra | $0.6000 | $2.08 | $0.1200 | — | 202,752 | text |
|
deepinfra/zai-org/GLM-5.1
deepinfra/zai-org/GLM-5.1
|
Deepinfra | $1.05 | $3.50 | $0.2050 | — | 202,752 | text |
|
deepinfra/zai-org/GLM-5.2
deepinfra/zai-org/GLM-5.2
|
Deepinfra | $0.7500 | $2.40 | $0.1400 | — | 1,048,576 | text |
|
databricks/ai_decide
databricks/ai_decide
|
Databricks | $0.0000 | $0.0000 | $0.0000 | $0.0000 | — | text |
|
databricks/databricks-bge-large-en
databricks/databricks-bge-large-en
|
Databricks | $0.1000 | $0.0000 | $0.1000 | $0.1000 | 512 | embedding |
|
databricks/databricks-claude-3-7-sonnet
databricks/databricks-claude-3-7-sonnet
|
Databricks | $3.00 | $15.00 | $0.3000 | $3.75 | 200,000 | text |
|
databricks/databricks-claude-fable-5
databricks/databricks-claude-fable-5
|
Databricks | $10.00 | $50.00 | $1.00 | $12.50 | 1,000,000 | text |
|
databricks/databricks-claude-fable-5-1
databricks/databricks-claude-fable-5-1
|
Databricks | $10.00 | $50.00 | $0.2500 | $12.50 | 1,000,000 | text |
|
databricks/databricks-claude-fable-5-2
databricks/databricks-claude-fable-5-2
|
Databricks | $8.00 | $40.00 | $0.2000 | $10.00 | 1,000,000 | text |
|
databricks/databricks-claude-haiku-4-5
databricks/databricks-claude-haiku-4-5
|
Databricks | $1.00 | $5.00 | $0.1000 | $1.25 | 200,000 | text |
|
databricks/databricks-claude-haiku-5-5
databricks/databricks-claude-haiku-5-5
|
Databricks | $0.1000 | $0.5000 | $0.0100 | $0.1250 | 1,000,000 | text |
|
databricks/databricks-claude-opus-4
databricks/databricks-claude-opus-4
|
Databricks | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | text |
|
databricks/databricks-claude-opus-4-1
databricks/databricks-claude-opus-4-1
|
Databricks | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | text |
|
databricks/databricks-claude-opus-4-5
databricks/databricks-claude-opus-4-5
|
Databricks | $5.00 | $25.00 | $0.5000 | $6.25 | 200,000 | text |
|
databricks/databricks-claude-opus-4-6
databricks/databricks-claude-opus-4-6
|
Databricks | $5.00 | $25.00 | $0.5000 | $6.25 | 1,000,000 | text |
|
databricks/databricks-claude-opus-4-7
databricks/databricks-claude-opus-4-7
|
Databricks | $5.00 | $25.00 | $0.5000 | $6.25 | 1,000,000 | text |
|
databricks/databricks-claude-opus-4-8
databricks/databricks-claude-opus-4-8
|
Databricks | $5.00 | $25.00 | $0.5000 | $6.25 | 1,000,000 | text |
|
databricks/databricks-claude-opus-5
databricks/databricks-claude-opus-5
|
Databricks | $5.00 | $25.00 | $0.5000 | $6.25 | 1,000,000 | text |
|
databricks/databricks-claude-opus-5-5
databricks/databricks-claude-opus-5-5
|
Databricks | $4.00 | $20.00 | $0.2000 | $5.00 | 1,000,000 | text |
|
databricks/databricks-claude-sonnet-4
databricks/databricks-claude-sonnet-4
|
Databricks | $3.00 | $15.00 | $0.3000 | $3.75 | 200,000 | text |
|
databricks/databricks-claude-sonnet-4-1
databricks/databricks-claude-sonnet-4-1
|
Databricks | $3.00 | $15.00 | $0.3000 | $3.75 | 200,000 | text |
|
databricks/databricks-claude-sonnet-4-5
databricks/databricks-claude-sonnet-4-5
|
Databricks | $3.00 | $15.00 | $0.3000 | $3.75 | 200,000 | text |
|
databricks/databricks-claude-sonnet-4-6
databricks/databricks-claude-sonnet-4-6
|
Databricks | $3.00 | $15.00 | $0.3000 | $3.75 | 1,000,000 | text |
|
databricks/databricks-claude-sonnet-5
databricks/databricks-claude-sonnet-5
|
Databricks | $2.00 | $10.00 | $0.2000 | $2.50 | 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.