Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 4,499 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 |
|---|---|---|---|---|---|---|---|
|
gemini/gemma-4-26b-a4b-it
gemini/gemma-4-26b-a4b-it
|
$0.0000 | $0.0000 | — | — | 262,144 | text | |
|
gemini/gemma-4-31b-it
gemini/gemma-4-31b-it
|
$0.0000 | $0.0000 | — | — | 262,144 | text | |
|
gemini/learnlm-1.5-pro-experimental
gemini/learnlm-1.5-pro-experimental
|
$0.0000 | $0.0000 | — | — | 32,767 | text | |
|
gemini/lyria-3-clip-preview
gemini/lyria-3-clip-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | text | |
|
gemini/lyria-3-pro-preview
gemini/lyria-3-pro-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | text | |
|
gemini/lyria-3.5
gemini/lyria-3.5
|
$0.0000 | $0.0000 | — | — | 131,072 | text | |
|
gemini/lyria-3.5-clip-preview
gemini/lyria-3.5-clip-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | text | |
|
gemini/lyria-3.5-pro-preview
gemini/lyria-3.5-pro-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | text | |
|
gemini/lyria-realtime-exp
gemini/lyria-realtime-exp
|
$0.0000 | $0.0000 | — | — | 1,048,576 | text | |
|
gemini/nano-banana-pro-preview
gemini/nano-banana-pro-preview
|
$2.00 | $12.00 | — | — | 131,072 | image | |
|
vertex_ai/deep-research-pro-preview-12-2025
vertex_ai/deep-research-pro-preview-12-2025
|
$2.00 | $12.00 | $0.2000 | — | 65,536 | image | |
|
vertex_ai/deepseek-ai/deepseek-ocr-maas
vertex_ai/deepseek-ai/deepseek-ocr-maas
|
$0.3000 | $1.20 | — | — | — | text | |
|
vertex_ai/gemini-2.0-flash
vertex_ai/gemini-2.0-flash
|
$0.1500 | $0.6000 | — | — | — | text | |
|
vertex_ai/gemini-2.0-flash-lite
vertex_ai/gemini-2.0-flash-lite
|
$0.0750 | $0.3000 | — | — | — | text | |
|
vertex_ai/gemini-2.5-flash-image
vertex_ai/gemini-2.5-flash-image
|
$0.3000 | $2.50 | — | — | 32,768 | image | |
|
vertex_ai/gemini-2.5-flash-native-audio
vertex_ai/gemini-2.5-flash-native-audio
|
$0.5000 | $2.00 | — | — | — | text | |
|
vertex_ai/gemini-2.5-flash-preview-tts
vertex_ai/gemini-2.5-flash-preview-tts
|
$0.5000 | $10.00 | — | — | — | audio | |
|
vertex_ai/gemini-2.5-flash-tts
vertex_ai/gemini-2.5-flash-tts
|
$0.5000 | $10.00 | — | — | — | audio | |
|
vertex_ai/gemini-2.5-pro-tts
vertex_ai/gemini-2.5-pro-tts
|
$1.00 | $20.00 | — | — | — | audio | |
|
vertex_ai/gemini-3-flash-preview
vertex_ai/gemini-3-flash-preview
|
$0.5000 | $3.00 | $0.0500 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3-pro-image
vertex_ai/gemini-3-pro-image
|
$2.00 | $12.00 | $0.2000 | — | 65,536 | image | |
|
vertex_ai/gemini-3-pro-image-preview
vertex_ai/gemini-3-pro-image-preview
|
$2.00 | $12.00 | $0.2000 | — | 65,536 | image | |
|
vertex_ai/gemini-3-pro-preview
vertex_ai/gemini-3-pro-preview
|
$2.00 | $12.00 | $0.2000 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.1-flash-image
vertex_ai/gemini-3.1-flash-image
|
$0.5000 | $3.00 | $0.0500 | — | 65,536 | image | |
|
vertex_ai/gemini-3.1-flash-image-preview
vertex_ai/gemini-3.1-flash-image-preview
|
$0.5000 | $3.00 | $0.0500 | — | 65,536 | image | |
|
vertex_ai/gemini-3.1-flash-lite
vertex_ai/gemini-3.1-flash-lite
|
$0.2500 | $1.50 | $0.0250 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.1-flash-lite-image
vertex_ai/gemini-3.1-flash-lite-image
|
$0.2500 | $1.50 | $0.0250 | — | 65,536 | image | |
|
vertex_ai/gemini-3.1-flash-lite-preview
vertex_ai/gemini-3.1-flash-lite-preview
|
$0.2500 | $1.50 | $0.0250 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.1-flash-live-preview
vertex_ai/gemini-3.1-flash-live-preview
|
$0.7500 | $4.50 | — | — | — | text | |
|
vertex_ai/gemini-3.1-flash-tts-preview
vertex_ai/gemini-3.1-flash-tts-preview
|
$1.00 | $20.00 | — | — | — | audio | |
|
vertex_ai/gemini-3.1-pro-preview
vertex_ai/gemini-3.1-pro-preview
|
$2.00 | $12.00 | $0.2000 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.1-pro-preview-customtools
vertex_ai/gemini-3.1-pro-preview-customtools
|
$2.00 | $12.00 | $0.2000 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.5-flash
vertex_ai/gemini-3.5-flash
|
$1.50 | $9.00 | $0.1500 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.5-flash-lite
vertex_ai/gemini-3.5-flash-lite
|
$0.3000 | $2.50 | $0.0300 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.5-live-translate-preview
vertex_ai/gemini-3.5-live-translate-preview
|
$3.50 | $21.00 | — | — | — | text | |
|
vertex_ai/gemini-3.5-transcribe
vertex_ai/gemini-3.5-transcribe
|
— | $12.00 | — | — | — | audio | |
|
vertex_ai/gemini-3.5-transcribe-live
vertex_ai/gemini-3.5-transcribe-live
|
— | $21.00 | — | — | — | audio | |
|
vertex_ai/gemini-3.5-transcribe-live-preview
vertex_ai/gemini-3.5-transcribe-live-preview
|
$3.50 | $21.00 | — | — | — | audio | |
|
vertex_ai/gemini-3.5-transcribe-preview
vertex_ai/gemini-3.5-transcribe-preview
|
$2.00 | $12.00 | — | — | — | audio | |
|
vertex_ai/gemini-3.6-flash
vertex_ai/gemini-3.6-flash
|
$0.7500 | $3.75 | $0.0750 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.7-flash
vertex_ai/gemini-3.7-flash
|
$0.7500 | $3.75 | $0.0750 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.8-flash
vertex_ai/gemini-3.8-flash
|
$0.7500 | $3.75 | $0.0750 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.8-flash-cyber
vertex_ai/gemini-3.8-flash-cyber
|
$1.50 | $7.50 | $0.1500 | — | 1,048,576 | text | |
|
vertex_ai/gemini-3.8-flash-lite-tts
vertex_ai/gemini-3.8-flash-lite-tts
|
$0.5000 | $6.00 | — | — | 8,192 | audio | |
|
vertex_ai/gemini-3.8-flash-tts
vertex_ai/gemini-3.8-flash-tts
|
$0.5000 | $9.00 | — | — | 8,192 | audio | |
|
vertex_ai/gemini-3.8-live
vertex_ai/gemini-3.8-live
|
$0.7500 | $4.50 | — | — | 131,072 | text | |
|
vertex_ai/gemini-4-argon
vertex_ai/gemini-4-argon
|
$2.00 | $10.00 | $0.1000 | — | 1,048,576 | text | |
|
vertex_ai/gemini-4-argon-cyber-permissive
vertex_ai/gemini-4-argon-cyber-permissive
|
$4.00 | $20.00 | $0.2000 | — | 1,048,576 | text | |
|
vertex_ai/gemini-embedding-2
vertex_ai/gemini-embedding-2
|
$0.2000 | $0.0000 | — | — | 8,192 | embedding | |
|
vertex_ai/gemini-embedding-2-preview
vertex_ai/gemini-embedding-2-preview
|
$0.2000 | $0.0000 | — | — | 8,192 | embedding | |
|
vertex_ai/gemini-nano-banana-2.1
vertex_ai/gemini-nano-banana-2.1
|
$1.50 | $7.50 | $0.1500 | — | 131,072 | image | |
|
vertex_ai/gemini-omni-1.1-flash
vertex_ai/gemini-omni-1.1-flash
|
$1.50 | $9.00 | — | — | — | text | |
|
vertex_ai/gemini-omni-1.1-flash-preview
vertex_ai/gemini-omni-1.1-flash-preview
|
$1.50 | $9.00 | — | — | 57,920 | text | |
|
vertex_ai/gemini-robotics-er-2
vertex_ai/gemini-robotics-er-2
|
$1.00 | $5.00 | $0.1000 | — | — | text | |
|
vertex_ai/gemini-robotics-er-2-preview
vertex_ai/gemini-robotics-er-2-preview
|
$1.00 | $5.00 | $0.1000 | — | 131,072 | text | |
|
vertex_ai/gemma-4-26b-a4b-it
vertex_ai/gemma-4-26b-a4b-it
|
$0.1500 | $0.6000 | $0.0150 | — | — | text | |
|
vertex_ai/lyria-3-clip-preview
vertex_ai/lyria-3-clip-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | audio | |
|
vertex_ai/lyria-3-pro-preview
vertex_ai/lyria-3-pro-preview
|
$0.0000 | $0.0000 | — | — | 131,072 | audio | |
|
vertex_ai/semantic-ranker-default
vertex_ai/semantic-ranker-default
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-default-002
vertex_ai/semantic-ranker-default-002
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-default-003
vertex_ai/semantic-ranker-default-003
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-default-004
vertex_ai/semantic-ranker-default-004
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-default@latest
vertex_ai/semantic-ranker-default@latest
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-fast
vertex_ai/semantic-ranker-fast
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-fast-004
vertex_ai/semantic-ranker-fast-004
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/semantic-ranker-fast@latest
vertex_ai/semantic-ranker-fast@latest
|
$0.0000 | $0.0000 | — | — | — | rerank | |
|
vertex_ai/xai/grok-4.1-fast-non-reasoning
vertex_ai/xai/grok-4.1-fast-non-reasoning
|
$0.2000 | $0.5000 | $0.0500 | — | 128,000 | text | |
|
vertex_ai/xai/grok-4.1-fast-reasoning
vertex_ai/xai/grok-4.1-fast-reasoning
|
$0.2000 | $0.5000 | $0.0500 | — | 128,000 | text | |
|
vertex_ai/xai/grok-4.20-non-reasoning
vertex_ai/xai/grok-4.20-non-reasoning
|
$1.25 | $2.50 | $0.2000 | — | 2,000,000 | text | |
|
vertex_ai/xai/grok-4.20-reasoning
vertex_ai/xai/grok-4.20-reasoning
|
$1.25 | $2.50 | $0.2000 | — | 2,000,000 | text | |
|
vertex_ai/xai/grok-4.3
vertex_ai/xai/grok-4.3
|
$1.25 | $2.50 | $0.2000 | — | 200,000 | text | |
|
vertex_ai/xai/grok-4.6
vertex_ai/xai/grok-4.6
|
$2.00 | $6.00 | $0.5000 | — | 524,288 | text | |
|
vertex_ai/xai/grok-4.7
vertex_ai/xai/grok-4.7
|
$2.00 | $6.00 | $0.5000 | — | 524,288 | text | |
|
gmi/anthropic/claude-opus-4
gmi/anthropic/claude-opus-4
|
Gmi | $15.00 | $75.00 | — | — | 409,600 | text |
|
gmi/anthropic/claude-opus-4.5
gmi/anthropic/claude-opus-4.5
|
Gmi | $5.00 | $25.00 | — | — | 409,600 | text |
|
gmi/anthropic/claude-sonnet-4
gmi/anthropic/claude-sonnet-4
|
Gmi | $3.00 | $15.00 | — | — | 409,600 | text |
|
gmi/anthropic/claude-sonnet-4.5
gmi/anthropic/claude-sonnet-4.5
|
Gmi | $3.00 | $15.00 | — | — | 409,600 | text |
|
gmi/deepseek-ai/DeepSeek-V3-0324
gmi/deepseek-ai/DeepSeek-V3-0324
|
Gmi | $0.2800 | $0.8800 | — | — | 163,840 | text |
|
gmi/deepseek-ai/DeepSeek-V3.2
gmi/deepseek-ai/DeepSeek-V3.2
|
Gmi | $0.2800 | $0.4000 | — | — | 163,840 | text |
|
gmi/google/gemini-3-flash-preview
gmi/google/gemini-3-flash-preview
|
Gmi | $0.5000 | $3.00 | — | — | 1,048,576 | text |
|
gmi/google/gemini-3-pro-preview
gmi/google/gemini-3-pro-preview
|
Gmi | $2.00 | $12.00 | — | — | 1,048,576 | text |
|
gmi/MiniMaxAI/MiniMax-M2.1
gmi/MiniMaxAI/MiniMax-M2.1
|
Gmi | $0.3000 | $1.20 | — | — | 196,608 | text |
|
gmi/moonshotai/Kimi-K2-Thinking
gmi/moonshotai/Kimi-K2-Thinking
|
Gmi | $0.8000 | $1.20 | — | — | 262,144 | text |
|
gmi/openai/gpt-4o
gmi/openai/gpt-4o
|
Gmi | $2.50 | $10.00 | — | — | 131,072 | text |
|
gmi/openai/gpt-4o-mini
gmi/openai/gpt-4o-mini
|
Gmi | $0.1500 | $0.6000 | — | — | 131,072 | text |
|
gmi/openai/gpt-5
gmi/openai/gpt-5
|
Gmi | $1.25 | $10.00 | — | — | 409,600 | text |
|
gmi/openai/gpt-5.1
gmi/openai/gpt-5.1
|
Gmi | $1.25 | $10.00 | — | — | 409,600 | text |
|
gmi/openai/gpt-5.2
gmi/openai/gpt-5.2
|
Gmi | $1.75 | $14.00 | — | — | 409,600 | text |
|
gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
|
Gmi | $0.3000 | $1.40 | — | — | 262,144 | text |
|
gmi/zai-org/GLM-4.7-FP8
gmi/zai-org/GLM-4.7-FP8
|
Gmi | $0.4000 | $2.00 | — | — | 202,752 | text |
|
github_copilot/claude-fable-5
github_copilot/claude-fable-5
|
Github Copilot | $10.00 | $50.00 | $1.00 | $12.50 | 200,000 | text |
|
github_copilot/claude-fable-5.1
github_copilot/claude-fable-5.1
|
Github Copilot | $10.00 | $50.00 | $0.2500 | $12.50 | 200,000 | text |
|
github_copilot/claude-haiku-4.5
github_copilot/claude-haiku-4.5
|
Github Copilot | $1.00 | $5.00 | $0.1000 | $1.25 | 128,000 | text |
|
github_copilot/claude-haiku-5.5
github_copilot/claude-haiku-5.5
|
Github Copilot | $0.1000 | $0.5000 | $0.0100 | $0.1250 | 128,000 | text |
|
github_copilot/claude-opus-4.8
github_copilot/claude-opus-4.8
|
Github Copilot | $5.00 | $25.00 | $0.5000 | $6.25 | 200,000 | text |
|
github_copilot/claude-opus-4.8-fast
github_copilot/claude-opus-4.8-fast
|
Github Copilot | $10.00 | $50.00 | $1.00 | $12.50 | 200,000 | text |
|
github_copilot/claude-opus-5
github_copilot/claude-opus-5
|
Github Copilot | $5.00 | $25.00 | $0.5000 | $6.25 | 200,000 | text |
|
github_copilot/claude-opus-5.5
github_copilot/claude-opus-5.5
|
Github Copilot | $4.00 | $20.00 | $0.2000 | $5.00 | 200,000 | text |
|
github_copilot/claude-sonnet-4
github_copilot/claude-sonnet-4
|
Github Copilot | $3.00 | $15.00 | $0.3000 | $3.75 | 128,000 | text |
|
github_copilot/claude-sonnet-4.6
github_copilot/claude-sonnet-4.6
|
Github Copilot | $3.00 | $15.00 | $0.3000 | $3.75 | 200,000 | 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.