Model Ranking
OpenAI | gpt-4o-mini | 128,000 | $0.15 | $0.60 |
OpenAI | gpt-4o | 128,000 | $5.00 | $15.00 |
OpenAI | gpt-4-turbo | 128,000 | $10.00 | $30.00 |
OpenAI | gpt-4 | 8,192 | $30.00 | $60.00 |
OpenAI | gpt-3.5-turbo | 4,096 | $1.50 | $2.00 |
Google | gemini-1.5-flash | 1,000,000 | $0.08 | $0.30 |
Google | gemini-1.5-pro | 1,000,000 | $3.50 | $10.50 |
Google | gemini-1.0-pro | 1,000,000 | $0.50 | $1.50 |
Anthropic | claude-3.5-sonnet-20240620 | 200,000 | $3.00 | $15.00 |
Anthropic | claude-3-opus-20240229 | 200,000 | $15.00 | $75.00 |
Anthropic | claude-3-sonnet-20240229 | 200,000 | $3.00 | $15.00 |
Anthropic | claude-3-haiku-20240307 | 200,000 | $0.25 | $1.25 |
Mistral | open-mistral-nemo-2407 | 128,000 | $0.30 | $0.30 |
Mistral | mistral-large-2407 | 128,000 | $3.00 | $9.00 |
Context length (or context window) refers to the maximum number of tokens the model can remember.Input and output prices are per million tokens.