GPT-4o (2024-11-20): API pricing, providers and specs
GPT-4o (2024-11-20) is a text model by OpenAI. 24 providers serve it, from $8 to $10.69 /1M; the lowest price is at APIMart.
How GPT-4o (2024-11-20) compares
Against the 737 text models on the site priced the same way.
- Pricey for its class: at $8 /1M, its lowest price is above 83% of comparable models (median $1.10).
- Its 128K-token context window is larger than 12% of them (median 262K), about 190 pages of text.
- 24 providers serve it; 90% of comparable models have fewer.
GPT-4o (2024-11-20) prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 CometAPI | — | $0.04/run | — | — |
| MMuAPI | — | $0.04/run | — | — |
| MMuAPI | — | $0.04/run | — | — |
| APIMart | $2/1M | From$8/1M | — | — |
| CometAPI | $2/1M | From$8/1M | $1/1M | — |
 Poe | $2.27/1M | $9.09/1M | $1.14/1M | 128K |
| OpenAIOfficial | $2.50/1M | From$10/1M | $1.25/1M | — |
 Venice AI | $2.50/1M | $10/1M | $1.25/1M | — |
 OrcaRouter | $2.50/1M | From$10/1M | $1.25/1M | 128K |
| Vercel AI Gateway | $2.50/1M | From$10/1M | $1.25/1M | 128K |
 Helicone | $2.50/1M | From$10/1M | $1.25/1M | — |
 Prime Inference | $2.50/1M | $10/1M | — | — |
 Impossibl | $2.50/1M | $10/1M | $1.25/1M | — |
| OpenRouter | $2.50/1M | From$10/1M | $1.25/1M | 128K |
| DevPass (LLM Gateway) | $2.50/1M | From$10/1M | $1.25/1M | — |
| Replicate | $2.50/1M | $10/1M | — | — |
 APIYI | $2.50/1M | From$10/1M | — | — |
 LaoZhang API | $2.50/1M | From$10/1M | — | — |
 CrazyRouter | $2.50/1M | $10/1M | — | — |
 AIHubMix | $2.50/1M | From$10/1M | $1.25/1M | 128K |
| ZenMux | $2.50/1M | $10/1M | $1.25/1M | 128K |
 Requesty | $2.50/1M | From$10/1M | $1.25/1M | 128K |
 FastRouter | $2.50/1M | From$10/1M | $1.25/1M | 128K |
| AI/ML API | $2.50/1M | $10/1M | $1.25/1M | — |
 DigitalOcean | $2.50/1M | $10/1M | $1.25/1M | — |
 Cortecs | $2.67/1M | $10.69/1M | $1.34/1M | — |
- APIMartFrom$8
- CometAPIFrom$8
- Poe$9.09
- Venice AI$10
- Prime Inference$10
- Impossibl$10
- Replicate$10
- CrazyRouter$10
- ZenMux$10
- AI/ML API$10
- DigitalOcean$10
- OpenAIOfficialFrom$10
Specs
- Type
- Text
- Maker
- OpenAI
- Inputs
- Image, Text
- Outputs
- Text
- Context
- 128K≈ 190 pages of text
- Max output
- 16K
- Capabilities
- Prompt caching, JSON, Tool calling, Vision
- Released
- May 13, 2024
- License
- proprietary
- Open weights
- No, API only
- Monthly searches
- 13K
Alternatives to GPT-4o (2024-11-20)
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| GPT-4o (2024-11-20)this model | $8/1M | 128K | — | 24 |
 Gemini 4 Argon | $8/1M | 1.05M | 1673 | 26 |
| Kimi K3 | $8.28/1M | 1.05M | 1655 | 47 |
 Muse Wonder | $16/1M | 1.05M | — | 14 |
| Claude Opus 5.5 | $16/1M | 1M | 1807 | 33 |
 Qwen3.8 2.4T A95B | $4.11/1M | 1M | — | 22 |
| Grok 4.7 | $4.80/1M | 500K | 1637 | 28 |
| Muse Spark 1.3 | $4.25/1M | 1.05M | 1657 | 11 |
| Claude Sonnet 5.5 | $8/1M | 1M | 1767 | 32 |
More from OpenAI
GPT-4o (2024-11-20) FAQ
APIMart, at $8 /1M. 24 providers serve GPT-4o (2024-11-20); the table above lists every one with its price.
GPT-4o (2024-11-20) reads up to 128K tokens per request and writes up to 16K.
No. GPT-4o (2024-11-20) is only available through an API; OpenAI does not publish its weights.
24 API providers serve GPT-4o (2024-11-20). Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us