OpenAI · gpt family
Compact GPT model for low-latency assistance and high-volume workloads
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| LLM Gateway | gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Azure Cognitive Services | gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Azure | gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| OpenAI | gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| NanoGPT | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Kilo Gateway | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| OpenRouter | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| OrcaRouter | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Vercel AI Gateway | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Cloudflare AI Gateway | openai/gpt-4-turbo | $10 / 1M | $30 / 1M | 128,000 | 4,096 |
| Poe | openai/gpt-4-turbo | $9 / 1M | $27 / 1M | 128,000 | 4,096 |
Attachments
Yes
Reasoning
No
Tool calling
Yes
Structured output
No
Temperature
Yes