GPT-4 pricing & benchmarks
Released May 28, 2023 · served by 2 providers
What GPT-4 is
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...
- Model ID:
openai/gpt-4 - Modality: text->text
- Knowledge cutoff: 2021-09-30
- Tool calling: supported · Structured output: supported
Providers and prices for GPT-4
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| OpenAIcheapest | $30.00 | $60.00 | 8K | — | 99.8% | — |
| Azure | $30.00 | $60.00 | 8K | — | 99.9% | — |
FAQ
How much does the GPT-4 API cost?
$30.00 per 1M input tokens and $60.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $48.00.
Is GPT-4 free?
No. It is a paid model starting at $30.00 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GPT-4?
OpenAI at $30.00 input / $60.00 output per 1M tokens.
Can I self-host GPT-4?
No. GPT-4 is closed-weight and only available through hosted APIs.