Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 3,719 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/MiniMaxAI/MiniMax-M3
wandb/MiniMaxAI/MiniMax-M3
|
Wandb | $0.2300 | $0.9600 | $0.0500 | — | 262,000 | 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 | — | 262,000 | text |
|
wandb/moonshotai/Kimi-K2.7-Code
wandb/moonshotai/Kimi-K2.7-Code
|
Wandb | $0.7100 | $3.50 | $0.1500 | — | 262,000 | text |
|
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
|
Wandb | $0.5000 | $2.15 | $0.1000 | — | 262,000 | text |
|
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
|
Wandb | $0.0700 | $0.2000 | $0.0400 | — | 262,000 | text |
|
wandb/openai/gpt-oss-120b
wandb/openai/gpt-oss-120b
|
Wandb | $0.0300 | $0.1700 | — | — | 131,000 | text |
|
wandb/openai/gpt-oss-20b
wandb/openai/gpt-oss-20b
|
Wandb | $0.0300 | $0.1300 | — | — | 131,000 | text |
|
wandb/OpenPipe/Qwen3-14B-Instruct
wandb/OpenPipe/Qwen3-14B-Instruct
|
Wandb | $0.0500 | $0.2200 | — | — | 32,800 | 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 | — | — | 262,000 | 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 | — | — | 262,000 | text |
|
wandb/Qwen/Qwen3.6-27B
wandb/Qwen/Qwen3.6-27B
|
Wandb | $0.6000 | $3.60 | $0.1200 | — | 262,000 | text |
|
wandb/Qwen/Qwen3.6-35B-A3B
wandb/Qwen/Qwen3.6-35B-A3B
|
Wandb | $0.2500 | $1.25 | — | — | 262,000 | text |
|
wandb/Qwen/Qwen3.8-27B
wandb/Qwen/Qwen3.8-27B
|
Wandb | $0.4000 | $3.00 | $0.1500 | — | 262,000 | 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 | — | 1,049,000 | text |
|
wandb/zai-org/GLM-5.3-Flash
wandb/zai-org/GLM-5.3-Flash
|
Wandb | $0.1500 | $0.5000 | $0.0500 | — | 1,049,000 | text |
|
watsonx/bigscience/mt0-xxl
watsonx/bigscience/mt0-xxl
|
Watsonx | $1.91 | $1.91 | — | — | 4,096 | text |
|
watsonx/bigscience/mt0-xxl-13b
watsonx/bigscience/mt0-xxl-13b
|
Watsonx | $1.91 | $1.91 | — | — | 4,096 | text |
|
watsonx/core42/jais-13b-chat
watsonx/core42/jais-13b-chat
|
Watsonx | $500.00 | $2,000.00 | — | — | 8,192 | text |
|
watsonx/google/flan-t5-xl-3b
watsonx/google/flan-t5-xl-3b
|
Watsonx | $0.6000 | $0.6000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-13b-chat-v2
watsonx/ibm/granite-13b-chat-v2
|
Watsonx | $0.6000 | $0.6000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-13b-instruct-v2
watsonx/ibm/granite-13b-instruct-v2
|
Watsonx | $0.6000 | $0.6000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-3-3-8b-instruct
watsonx/ibm/granite-3-3-8b-instruct
|
Watsonx | $0.2000 | $0.2000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-3-8b-instruct
watsonx/ibm/granite-3-8b-instruct
|
Watsonx | $0.2000 | $0.2000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-4-h-small
watsonx/ibm/granite-4-h-small
|
Watsonx | $0.0636 | $0.2650 | — | — | 131,072 | text |
|
watsonx/ibm/granite-guardian-3-2-2b
watsonx/ibm/granite-guardian-3-2-2b
|
Watsonx | $0.1000 | $0.1000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-guardian-3-3-8b
watsonx/ibm/granite-guardian-3-3-8b
|
Watsonx | $0.2000 | $0.2000 | — | — | 8,192 | text |
|
watsonx/ibm/granite-ttm-1024-96-r2
watsonx/ibm/granite-ttm-1024-96-r2
|
Watsonx | $0.3800 | $0.3800 | — | — | 512 | text |
|
watsonx/ibm/granite-ttm-1536-96-r2
watsonx/ibm/granite-ttm-1536-96-r2
|
Watsonx | $0.3800 | $0.3800 | — | — | 512 | text |
|
watsonx/ibm/granite-ttm-512-96-r2
watsonx/ibm/granite-ttm-512-96-r2
|
Watsonx | $0.3800 | $0.3800 | — | — | 512 | text |
|
watsonx/ibm/granite-vision-3-2-2b
watsonx/ibm/granite-vision-3-2-2b
|
Watsonx | $0.1000 | $0.1000 | — | — | 8,192 | text |
|
watsonx/meta-llama/llama-3-2-11b-vision-instruct
watsonx/meta-llama/llama-3-2-11b-vision-instruct
|
Watsonx | $0.3500 | $0.3500 | — | — | 128,000 | text |
|
watsonx/meta-llama/llama-3-2-1b-instruct
watsonx/meta-llama/llama-3-2-1b-instruct
|
Watsonx | $0.1000 | $0.1000 | — | — | 128,000 | text |
|
watsonx/meta-llama/llama-3-2-3b-instruct
watsonx/meta-llama/llama-3-2-3b-instruct
|
Watsonx | $0.1500 | $0.1500 | — | — | 128,000 | text |
|
watsonx/meta-llama/llama-3-2-90b-vision-instruct
watsonx/meta-llama/llama-3-2-90b-vision-instruct
|
Watsonx | $2.00 | $2.00 | — | — | 128,000 | text |
|
watsonx/meta-llama/llama-3-3-70b-instruct
watsonx/meta-llama/llama-3-3-70b-instruct
|
Watsonx | $0.7526 | $0.7526 | — | — | 131,072 | text |
|
watsonx/meta-llama/llama-4-maverick-17b
watsonx/meta-llama/llama-4-maverick-17b
|
Watsonx | $0.3710 | $1.48 | — | — | 131,072 | text |
|
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
|
Watsonx | $0.3710 | $1.48 | — | — | 131,072 | text |
|
watsonx/meta-llama/llama-guard-3-11b-vision
watsonx/meta-llama/llama-guard-3-11b-vision
|
Watsonx | $0.3500 | $0.3500 | — | — | 128,000 | text |
|
watsonx/mistralai/mistral-large
watsonx/mistralai/mistral-large
|
Watsonx | $3.00 | $10.00 | — | — | 131,072 | text |
|
watsonx/mistralai/mistral-medium-2505
watsonx/mistralai/mistral-medium-2505
|
Watsonx | $3.00 | $10.00 | — | — | 128,000 | text |
|
watsonx/mistralai/mistral-small-2503
watsonx/mistralai/mistral-small-2503
|
Watsonx | $0.1000 | $0.3000 | — | — | 32,000 | text |
|
watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
|
Watsonx | $0.1060 | $0.3180 | — | — | 131,072 | text |
|
watsonx/mistralai/pixtral-12b-2409
watsonx/mistralai/pixtral-12b-2409
|
Watsonx | $0.3500 | $0.3500 | — | — | 128,000 | text |
|
watsonx/openai/gpt-oss-120b
watsonx/openai/gpt-oss-120b
|
Watsonx | $0.1590 | $0.6360 | — | — | 131,072 | text |
|
watsonx/sdaia/allam-1-13b-instruct
watsonx/sdaia/allam-1-13b-instruct
|
Watsonx | $1.80 | $1.80 | — | — | 8,192 | text |
|
xai/grok-2
xai/grok-2
|
xAI | $2.00 | $10.00 | — | — | 131,072 | text |
|
xai/grok-2-1212
xai/grok-2-1212
|
xAI | $2.00 | $10.00 | — | — | 131,072 | text |
|
xai/grok-2-latest
xai/grok-2-latest
|
xAI | $2.00 | $10.00 | — | — | 131,072 | text |
|
xai/grok-2-vision
xai/grok-2-vision
|
xAI | $2.00 | $10.00 | — | — | 32,768 | text |
|
xai/grok-2-vision-1212
xai/grok-2-vision-1212
|
xAI | $2.00 | $10.00 | — | — | 32,768 | text |
|
xai/grok-2-vision-latest
xai/grok-2-vision-latest
|
xAI | $2.00 | $10.00 | — | — | 32,768 | text |
|
xai/grok-3
xai/grok-3
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-beta
xai/grok-3-beta
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-fast-beta
xai/grok-3-fast-beta
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-fast-latest
xai/grok-3-fast-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-latest
xai/grok-3-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini
xai/grok-3-mini
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini-beta
xai/grok-3-mini-beta
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini-fast
xai/grok-3-mini-fast
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini-fast-beta
xai/grok-3-mini-fast-beta
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini-fast-latest
xai/grok-3-mini-fast-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-3-mini-latest
xai/grok-3-mini-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 131,072 | text |
|
xai/grok-4
xai/grok-4
|
xAI | $1.25 | $2.50 | $0.2000 | — | 256,000 | text |
|
xai/grok-4-0709
xai/grok-4-0709
|
xAI | $1.25 | $2.50 | $0.2000 | — | 256,000 | text |
|
xai/grok-4-1-fast
xai/grok-4-1-fast
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-1-fast-non-reasoning
xai/grok-4-1-fast-non-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-1-fast-non-reasoning-latest
xai/grok-4-1-fast-non-reasoning-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-1-fast-reasoning
xai/grok-4-1-fast-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-1-fast-reasoning-latest
xai/grok-4-1-fast-reasoning-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-fast-non-reasoning
xai/grok-4-fast-non-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-fast-reasoning
xai/grok-4-fast-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 2,000,000 | text |
|
xai/grok-4-latest
xai/grok-4-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 256,000 | text |
|
xai/grok-4.20
xai/grok-4.20
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-0309-non-reasoning
xai/grok-4.20-0309-non-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-0309-reasoning
xai/grok-4.20-0309-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-beta-0309-non-reasoning
xai/grok-4.20-beta-0309-non-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-beta-0309-reasoning
xai/grok-4.20-beta-0309-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-multi-agent
xai/grok-4.20-multi-agent
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-multi-agent-0309
xai/grok-4.20-multi-agent-0309
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-multi-agent-beta-0309
xai/grok-4.20-multi-agent-beta-0309
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-multi-agent-latest
xai/grok-4.20-multi-agent-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-non-reasoning
xai/grok-4.20-non-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-non-reasoning-latest
xai/grok-4.20-non-reasoning-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-reasoning
xai/grok-4.20-reasoning
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.20-reasoning-latest
xai/grok-4.20-reasoning-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.3
xai/grok-4.3
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.3-latest
xai/grok-4.3-latest
|
xAI | $1.25 | $2.50 | $0.2000 | — | 1,000,000 | text |
|
xai/grok-4.5
xai/grok-4.5
|
xAI | $2.00 | $6.00 | $0.3000 | — | 500,000 | text |
|
xai/grok-4.5-latest
xai/grok-4.5-latest
|
xAI | $2.00 | $6.00 | $0.3000 | — | 500,000 | text |
|
xai/grok-4.6
xai/grok-4.6
|
xAI | $2.00 | $6.00 | $0.5000 | — | 500,000 | text |
|
xai/grok-beta
xai/grok-beta
|
xAI | $5.00 | $15.00 | — | — | 131,072 | text |
|
xai/grok-build-0.1
xai/grok-build-0.1
|
xAI | $1.00 | $2.00 | $0.2000 | — | 256,000 | text |
|
xai/grok-build-latest
xai/grok-build-latest
|
xAI | $2.00 | $6.00 | $0.3000 | — | 500,000 | text |
|
xai/grok-code-fast
xai/grok-code-fast
|
xAI | $1.00 | $2.00 | $0.2000 | — | 256,000 | 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.