openai Vision
GPT-4 Turbo pricing & benchmarks
Released Apr 9, 2024 · served by 1 provider
Input / 1M tokens$10.00
Output / 1M tokens$30.00
Context window128K
Cached input—
Coding index21.5
1M in + 300K out$19.00
What GPT-4 Turbo is
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.
- Model ID:
openai/gpt-4-turbo - Modality: text+image->text
- Knowledge cutoff: 2023-12-31
- Tool calling: supported · Structured output: supported
Providers and prices for GPT-4 Turbo
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 | $10.00 | $30.00 | 128K | — | 100.0% | — |
FAQ
How much does the GPT-4 Turbo API cost?
$10.00 per 1M input tokens and $30.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $19.00.
Is GPT-4 Turbo free?
No. It is a paid model starting at $10.00 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GPT-4 Turbo?
OpenAI at $10.00 input / $30.00 output per 1M tokens.
Can I self-host GPT-4 Turbo?
No. GPT-4 Turbo is closed-weight and only available through hosted APIs.