GPT-4-Turbo
by Poe · family gpt · listed Sep 2023TV
Compact GPT model for low-latency assistance and high-volume workloads
Current rates USD per 1M tokens
Input$9.00
Output$27.00
Cache read—
Cache write—
Against the market
On the record
- Model id
openai/gpt-4-turbo- Context window
- 128K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2023-09-13
- Last updated
- 2023-09-13
Back of the envelope
≈
Also listed at
- Vercel AI Gateway$10.00 in · $30.00 out
- OpenAI$10.00 in · $30.00 out
- OrcaRouter$10.00 in · $30.00 out
- LLM Gateway$10.00 in · $30.00 out
- Cloudflare AI Gateway$10.00 in · $30.00 out
- Azure$10.00 in · $30.00 out
- Kilo Gateway$10.00 in · $30.00 out
- OpenRouter$10.00 in · $30.00 out
- Azure Cognitive Services$10.00 in · $30.00 out
- NanoGPT$10.00 in · $30.00 out