Model Pricing & Performance
Compare 50+ LLMs by speed, cost, and capabilities. Find the perfect model for your use case.
Get StartedShowing 8 of 8 models
| Model | Context | I/O | Features | Latency | Price (per 1M tokens) |
|---|---|---|---|---|---|
GPT-4 TurboOpenAI | 128K | textvision text | tool-callingjson-mode+1 | 8ms1250 tok/s | In: $10.00Out: $30.00 |
Claude 3.5 SonnetAnthropic | 200K | textvision text | tool-callingjson-mode+1 | 12ms1100 tok/s | In: $3.00Out: $15.00 |
Gemini 1.5 ProGoogle | 1000K | textvisionaudio text | tool-callingjson-mode+2 | 15ms980 tok/s | In: $3.50Out: $10.50 |
Llama 3.1 405BMeta | 128K | text text | tool-callingjson-mode+1 | 18ms850 tok/s | In: $5.00Out: $15.00 |
Mistral Large 2Mistral AI | 128K | text text | tool-callingjson-mode+1 | 10ms1150 tok/s | In: $4.00Out: $12.00 |
Command R+Cohere | 128K | text text | tool-callingstreaming+1 | 14ms920 tok/s | In: $3.00Out: $15.00 |
GPT-4oOpenAI | 128K | textvisionaudio textaudio | tool-callingjson-mode+2 | 9ms1200 tok/s | In: $5.00Out: $15.00 |
Claude 3 OpusAnthropic | 200K | textvision text | tool-callingjson-mode+1 | 20ms750 tok/s | In: $15.00Out: $75.00 |