AI Model Pricing
| Model | Provider | Input | Cached | Output | Context |
|---|---|---|---|---|---|
claude-3-5-haiku-20241022 Claude 3.5 Haiku — fastest | anthropic | $0.800 | $0.080 | $4.00 | 200K |
claude-3-5-sonnet-20241022 Claude 3.5 Sonnet | anthropic | $3.00 | $0.300 | $15.00 | 200K |
claude-3-opus-20240229 Claude 3 Opus — most capable legacy | anthropic | $15.00 | $1.50 | $75.00 | 200K |
claude-sonnet-4-20250514 Latest Claude Sonnet | anthropic | $3.00 | $0.300 | $15.00 | 200K |
gemini-2.0-flash Fast multimodal model | $0.100 | $0.025 | $0.400 | 1.0M | |
gemini-2.0-flash-lite Cost-efficient lightweight model | $0.075 | — | $0.300 | 1.0M | |
gemini-2.5-flash Fast, efficient model | $0.300 | $0.020 | $2.50 | 1.0M | |
gemini-2.5-pro Advanced reasoning and coding | $1.25 | $0.310 | $10.00 | 1.0M | |
gemini-3-flash-preview Fast, intelligent model | $0.500 | $0.050 | $3.00 | — | |
gemini-3.1-flash-lite-preview Most cost-efficient Gemini | $0.250 | $0.025 | $1.50 | — | |
gemini-3.1-pro-preview Most intelligent Gemini model | $2.00 | $0.200 | $12.00 | — | |
text-embedding-3-large Large embedding model | openai | $0.130 | — | — | 8K |
text-embedding-3-small Small embedding model | openai | $0.020 | — | — | 8K |
gpt-4.1 GPT-4.1 | openai | $2.00 | $0.500 | $8.00 | — |
gpt-4.1-mini GPT-4.1 mini | openai | $0.400 | $0.100 | $1.60 | — |
gpt-4.1-nano GPT-4.1 nano | openai | $0.100 | $0.025 | $0.400 | — |
gpt-4o GPT-4o multimodal | openai | $2.50 | $1.25 | $10.00 | 128K |
gpt-4o-mini GPT-4o mini, budget-friendly | openai | $0.150 | $0.075 | $0.600 | 128K |
gpt-5 GPT-5 baseline | openai | $1.25 | $0.125 | $10.00 | — |
gpt-5-mini GPT-5 mini variant | openai | $0.250 | $0.025 | $2.00 | — |
gpt-5-nano GPT-5 nano variant | openai | $0.050 | $0.0050 | $0.400 | — |
gpt-5-pro GPT-5 pro variant | openai | $15.00 | — | $120.00 | — |
gpt-5.1 GPT-5.1 | openai | $1.25 | $0.125 | $10.00 | — |
gpt-5.2 Previous generation flagship | openai | $1.75 | $0.175 | $14.00 | — |
gpt-5.2-pro Previous generation pro | openai | $21.00 | — | $168.00 | — |
gpt-5.4 Latest flagship model | openai | $2.50 | $0.250 | $15.00 | 272K |
gpt-5.4-mini Fast, cost-efficient flagship | openai | $0.750 | $0.075 | $4.50 | — |
gpt-5.4-nano Ultra-low cost flagship | openai | $0.200 | $0.020 | $1.25 | — |
gpt-5.4-pro Pro-tier flagship for complex tasks | openai | $30.00 | — | $180.00 | 272K |
gpt-3.5-turboDeprecated GPT-3.5 Turbo | openai | $0.500 | — | $1.50 | 16K |
gpt-4-turboDeprecated GPT-4 Turbo | openai | $10.00 | — | $30.00 | 128K |
o1Reasoning Original reasoning model | openai | $15.00 | $7.50 | $60.00 | — |
o1-miniReasoning Mini reasoning model (legacy) | openai | $1.10 | $0.550 | $4.40 | — |
o1-proReasoning Pro reasoning model (legacy) | openai | $150.00 | — | $600.00 | — |
o3Reasoning Reasoning model | openai | $2.00 | $0.500 | $8.00 | — |
o3-miniReasoning Mini reasoning model | openai | $1.10 | $0.550 | $4.40 | — |
o3-proReasoning Pro reasoning model | openai | $20.00 | — | $80.00 | — |
o4-miniReasoning Compact reasoning model | openai | $1.10 | $0.275 | $4.40 | — |
Nano Banana — speed-optimized
Nano Banana Pro — professional assets
Nano Banana 2 — fast image generation
Imagen 3
Imagen 4
DALL-E 2 image model
DALL-E 3 image model
GPT Image generation model
Cost-efficient image generation
State-of-the-art image generation
npm run ai:pricing to refresh.