openai/gpt-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| OpenAI | $30.00 | $60.00 | 8K | — |
| Azure | $30.00 | $60.00 | 8K | — |
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens via OpenRouter, making it 297th cheapest of 298 paid models.
GPT-4 generates around 20 tokens per second with 371ms time-to-first-token (p50), the 264th fastest tracked model.
GPT-4 supports a 8K-token context window and can output up to 4K tokens. It accepts text input.