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 |
|---|---|---|---|---|---|---|---|
|
wandb/deepseek-ai/DeepSeek-V3.1
wandb/deepseek-ai/DeepSeek-V3.1
|
Wandb | $0.5500 | $1.65 | — | — | 161,000 | text |
|
wandb/deepseek-ai/DeepSeek-V4-Flash
wandb/deepseek-ai/DeepSeek-V4-Flash
|
Wandb | $0.1400 | $0.2800 | $0.0700 | — | 1,048,576 | text |
|
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
|
Wandb | $0.1300 | $0.2800 | $0.0700 | — | 262,144 | text |
|
wandb/deepseek-ai/DeepSeek-V4-Pro
wandb/deepseek-ai/DeepSeek-V4-Pro
|
Wandb | $1.15 | $2.55 | $0.2000 | — | 1,048,576 | text |
|
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
|
Wandb | $1.31 | $3.96 | $0.0440 | — | — | text |
|
wandb/google/gemma-4-31B-it
wandb/google/gemma-4-31B-it
|
Wandb | $0.1000 | $0.3400 | — | — | 262,144 | text |
|
wandb/ibm-granite/granite-4.1-8b
wandb/ibm-granite/granite-4.1-8b
|
Wandb | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
wandb/ibm-granite/granite-4.2-8b
wandb/ibm-granite/granite-4.2-8b
|
Wandb | $0.1000 | $0.1500 | $0.0500 | — | — | text |
|
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
|
Wandb | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
wandb/meta-llama/Llama-3.1-70B-Instruct
wandb/meta-llama/Llama-3.1-70B-Instruct
|
Wandb | $0.8000 | $0.8000 | — | — | 128,000 | text |
|
wandb/meta-llama/Llama-3.1-8B-Instruct
wandb/meta-llama/Llama-3.1-8B-Instruct
|
Wandb | $0.2200 | $0.2200 | — | — | 128,000 | text |
|
wandb/meta-llama/Llama-3.3-70B-Instruct
wandb/meta-llama/Llama-3.3-70B-Instruct
|
Wandb | $0.7100 | $0.7100 | — | — | 128,000 | text |
|
wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
|
Wandb | $0.1700 | $0.6600 | — | — | 64,000 | text |
|
wandb/microsoft/Phi-4-mini-instruct
wandb/microsoft/Phi-4-mini-instruct
|
Wandb | $8,000.00 | $35,000.00 | — | — | 128,000 | text |
|
wandb/MiniMaxAI/MiniMax-M2.5
wandb/MiniMaxAI/MiniMax-M2.5
|
Wandb | $0.3000 | $1.20 | — | — | 197,000 | text |
|
wandb/MiniMaxAI/MiniMax-M3
wandb/MiniMaxAI/MiniMax-M3
|
Wandb | $0.2300 | $0.9600 | $0.0500 | — | 262,144 | text |
|
wandb/moonshotai/Kimi-K2-Instruct
wandb/moonshotai/Kimi-K2-Instruct
|
Wandb | $0.6000 | $2.50 | — | — | 128,000 | text |
|
wandb/moonshotai/Kimi-K2.5
wandb/moonshotai/Kimi-K2.5
|
Wandb | $0.6000 | $3.00 | $0.1000 | — | 262,144 | text |
|
wandb/moonshotai/Kimi-K2.6
wandb/moonshotai/Kimi-K2.6
|
Wandb | $0.6500 | $3.41 | $0.1500 | — | 262,144 | text |
|
wandb/moonshotai/Kimi-K2.7-Code
wandb/moonshotai/Kimi-K2.7-Code
|
Wandb | $0.7100 | $3.50 | $0.1500 | — | 262,144 | text |
|
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
|
Wandb | $0.7500 | $2.75 | $0.1500 | — | 262,144 | text |
|
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
|
Wandb | $0.1000 | $0.2500 | $0.0500 | — | 262,144 | text |
|
wandb/openai/gpt-oss-120b
wandb/openai/gpt-oss-120b
|
Wandb | $0.0300 | $0.1700 | — | — | 131,072 | text |
|
wandb/openai/gpt-oss-20b
wandb/openai/gpt-oss-20b
|
Wandb | $0.0300 | $0.1300 | — | — | 131,072 | text |
|
wandb/OpenPipe/Qwen3-14B-Instruct
wandb/OpenPipe/Qwen3-14B-Instruct
|
Wandb | $0.0500 | $0.2200 | — | — | 32,768 | text |
|
wandb/Qwen/Qwen3-235B-A22B-Instruct-2507
wandb/Qwen/Qwen3-235B-A22B-Instruct-2507
|
Wandb | $0.1000 | $0.1000 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507
|
Wandb | $0.1000 | $0.1000 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507
|
Wandb | $0.1000 | $0.3000 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct
wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct
|
Wandb | $1.00 | $1.50 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3.5-35B-A3B
wandb/Qwen/Qwen3.5-35B-A3B
|
Wandb | $0.2500 | $1.25 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3.6-27B
wandb/Qwen/Qwen3.6-27B
|
Wandb | $0.6000 | $3.60 | $0.1200 | — | 262,144 | text |
|
wandb/Qwen/Qwen3.6-35B-A3B
wandb/Qwen/Qwen3.6-35B-A3B
|
Wandb | $0.2500 | $1.25 | — | — | 262,144 | text |
|
wandb/Qwen/Qwen3.8-27B
wandb/Qwen/Qwen3.8-27B
|
Wandb | $0.4000 | $3.00 | $0.1500 | — | 262,144 | text |
|
wandb/zai-org/GLM-4.5
wandb/zai-org/GLM-4.5
|
Wandb | $55,000.00 | $200,000.00 | — | — | 131,072 | text |
|
wandb/zai-org/GLM-5.2
wandb/zai-org/GLM-5.2
|
Wandb | $0.7600 | $2.42 | $0.1400 | — | 262,144 | text |
|
voyage/rerank-2
voyage/rerank-2
|
Voyage | $0.0500 | $0.0000 | — | — | 16,000 | rerank |
|
voyage/rerank-2-lite
voyage/rerank-2-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 8,000 | rerank |
|
voyage/rerank-2.5
voyage/rerank-2.5
|
Voyage | $0.0500 | $0.0000 | — | — | 32,000 | rerank |
|
voyage/rerank-2.5-lite
voyage/rerank-2.5-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 32,000 | rerank |
|
voyage/rerank-3
voyage/rerank-3
|
Voyage | $0.0500 | $0.0000 | — | — | 32,000 | rerank |
|
voyage/rerank-3-lite
voyage/rerank-3-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 32,000 | rerank |
|
voyage/voyage-2
voyage/voyage-2
|
Voyage | $0.1000 | $0.0000 | — | — | 4,000 | embedding |
|
voyage/voyage-3
voyage/voyage-3
|
Voyage | $0.0600 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-3-large
voyage/voyage-3-large
|
Voyage | $0.1800 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-3-lite
voyage/voyage-3-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-3.5
voyage/voyage-3.5
|
Voyage | $0.0600 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-3.5-lite
voyage/voyage-3.5-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-4
voyage/voyage-4
|
Voyage | $0.0600 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-4-large
voyage/voyage-4-large
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-4-lite
voyage/voyage-4-lite
|
Voyage | $0.0200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-code-2
voyage/voyage-code-2
|
Voyage | $0.1200 | $0.0000 | — | — | 16,000 | embedding |
|
voyage/voyage-code-3
voyage/voyage-code-3
|
Voyage | $0.1800 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-code-4
voyage/voyage-code-4
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-context-3
voyage/voyage-context-3
|
Voyage | $0.1800 | $0.0000 | — | — | 120,000 | embedding |
|
voyage/voyage-context-4
voyage/voyage-context-4
|
Voyage | $0.1200 | $0.0000 | — | — | 120,000 | embedding |
|
voyage/voyage-finance-2
voyage/voyage-finance-2
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-large-2
voyage/voyage-large-2
|
Voyage | $0.1200 | $0.0000 | — | — | 16,000 | embedding |
|
voyage/voyage-law-2
voyage/voyage-law-2
|
Voyage | $0.1200 | $0.0000 | — | — | 16,000 | embedding |
|
voyage/voyage-lite-01
voyage/voyage-lite-01
|
Voyage | $0.1000 | $0.0000 | — | — | 4,096 | embedding |
|
voyage/voyage-lite-02-instruct
voyage/voyage-lite-02-instruct
|
Voyage | $0.1000 | $0.0000 | — | — | 4,000 | embedding |
|
voyage/voyage-multilingual-2
voyage/voyage-multilingual-2
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-multimodal-3
voyage/voyage-multimodal-3
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
voyage/voyage-multimodal-3.5
voyage/voyage-multimodal-3.5
|
Voyage | $0.1200 | $0.0000 | — | — | 32,000 | embedding |
|
deepseek-v3-2-251201
deepseek-v3-2-251201
|
Volcengine | $0.0000 | $0.0000 | — | — | 98,304 | text |
|
doubao-embedding
doubao-embedding
|
Volcengine | $0.0000 | $0.0000 | — | — | 4,096 | embedding |
|
doubao-embedding-large
doubao-embedding-large
|
Volcengine | $0.0000 | $0.0000 | — | — | 4,096 | embedding |
|
doubao-embedding-large-text-240915
doubao-embedding-large-text-240915
|
Volcengine | $0.0000 | $0.0000 | — | — | 4,096 | embedding |
|
doubao-embedding-large-text-250515
doubao-embedding-large-text-250515
|
Volcengine | $0.0000 | $0.0000 | — | — | 4,096 | embedding |
|
doubao-embedding-text-240715
doubao-embedding-text-240715
|
Volcengine | $0.0000 | $0.0000 | — | — | 4,096 | embedding |
|
glm-4-7-251222
glm-4-7-251222
|
Volcengine | $0.0000 | $0.0000 | — | — | 204,800 | text |
|
kimi-k2-thinking-251104
kimi-k2-thinking-251104
|
Volcengine | $0.0000 | $0.0000 | — | — | 229,376 | text |
|
vertex_ai/zai-org/glm-4.7-maas
vertex_ai/zai-org/glm-4.7-maas
|
Vertex Ai-Zai Models | $0.6000 | $2.20 | — | — | 200,000 | text |
|
vertex_ai/zai-org/glm-5-maas
vertex_ai/zai-org/glm-5-maas
|
Vertex Ai-Zai Models | $1.00 | $3.20 | $0.1000 | — | 200,000 | text |
|
text-unicorn
text-unicorn
|
Vertex Ai-Text-Models | $10.00 | $28.00 | — | — | 8,192 | text |
|
text-unicorn@001
text-unicorn@001
|
Vertex Ai-Text-Models | $10.00 | $28.00 | — | — | 8,192 | text |
|
vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas
vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas
|
Vertex Ai-Qwen Models | $0.2200 | $0.8800 | — | — | 262,144 | text |
|
vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas
vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas
|
Vertex Ai-Qwen Models | $0.2200 | $1.80 | — | — | 262,144 | text |
|
vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas
vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas
|
Vertex Ai-Qwen Models | $0.1500 | $1.20 | — | — | 262,144 | text |
|
vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas
vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas
|
Vertex Ai-Qwen Models | $0.1500 | $1.20 | — | — | 262,144 | text |
|
vertex_ai/google/gemma-4-26b-a4b-it-maas
vertex_ai/google/gemma-4-26b-a4b-it-maas
|
Vertex Ai-Openai Models | $0.1500 | $0.6000 | — | — | 256,000 | text |
|
vertex_ai/openai/gpt-oss-120b-maas
vertex_ai/openai/gpt-oss-120b-maas
|
Vertex Ai-Openai Models | $0.0900 | $0.3600 | — | — | 131,072 | text |
|
vertex_ai/openai/gpt-oss-20b-maas
vertex_ai/openai/gpt-oss-20b-maas
|
Vertex Ai-Openai Models | $0.0700 | $0.2500 | $0.0070 | — | 131,072 | text |
|
vertex_ai/moonshotai/kimi-k2-thinking-maas
vertex_ai/moonshotai/kimi-k2-thinking-maas
|
Vertex Ai-Moonshot Models | $0.6000 | $2.50 | — | — | 256,000 | text |
|
vertex_ai/codestral-2
vertex_ai/codestral-2
|
Vertex Ai-Mistral Models | $0.3000 | $0.9000 | — | — | 128,000 | text |
|
vertex_ai/codestral-2@001
vertex_ai/codestral-2@001
|
Vertex Ai-Mistral Models | $0.3000 | $0.9000 | — | — | 128,000 | text |
|
vertex_ai/codestral-2501
vertex_ai/codestral-2501
|
Vertex Ai-Mistral Models | $0.2000 | $0.6000 | — | — | 128,000 | text |
|
vertex_ai/codestral@2405
vertex_ai/codestral@2405
|
Vertex Ai-Mistral Models | $0.2000 | $0.6000 | — | — | 128,000 | text |
|
vertex_ai/codestral@latest
vertex_ai/codestral@latest
|
Vertex Ai-Mistral Models | $0.2000 | $0.6000 | — | — | 128,000 | text |
|
vertex_ai/mistral-large-2411
vertex_ai/mistral-large-2411
|
Vertex Ai-Mistral Models | $2.00 | $6.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-large@2407
vertex_ai/mistral-large@2407
|
Vertex Ai-Mistral Models | $2.00 | $6.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-large@2411-001
vertex_ai/mistral-large@2411-001
|
Vertex Ai-Mistral Models | $2.00 | $6.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-large@latest
vertex_ai/mistral-large@latest
|
Vertex Ai-Mistral Models | $2.00 | $6.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-medium-3
vertex_ai/mistral-medium-3
|
Vertex Ai-Mistral Models | $0.4000 | $2.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-medium-3@001
vertex_ai/mistral-medium-3@001
|
Vertex Ai-Mistral Models | $0.4000 | $2.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-nemo@2407
vertex_ai/mistral-nemo@2407
|
Vertex Ai-Mistral Models | $3.00 | $3.00 | — | — | 128,000 | text |
|
vertex_ai/mistral-nemo@latest
vertex_ai/mistral-nemo@latest
|
Vertex Ai-Mistral Models | $0.1500 | $0.1500 | — | — | 128,000 | text |
|
vertex_ai/mistral-small-2503
vertex_ai/mistral-small-2503
|
Vertex Ai-Mistral Models | $0.1000 | $0.3000 | — | — | 128,000 | text |
|
vertex_ai/mistral-small-2503@001
vertex_ai/mistral-small-2503@001
|
Vertex Ai-Mistral Models | $0.1000 | $0.3000 | — | — | 32,000 | text |
|
vertex_ai/mistralai/codestral-2
vertex_ai/mistralai/codestral-2
|
Vertex Ai-Mistral Models | $0.3000 | $0.9000 | — | — | 128,000 | text |
|
vertex_ai/mistralai/codestral-2@001
vertex_ai/mistralai/codestral-2@001
|
Vertex Ai-Mistral Models | $0.3000 | $0.9000 | — | — | 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.