GPT-3.5-Turbo: API pricing, providers and specs
GPT-3.5-Turbo is a text model by OpenAI. 9 providers serve it, from $1.20 to $2 /1M; the lowest price is at APIMart.
How GPT-3.5-Turbo compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $1.20 /1M against a median of $1.10; 52% of comparable models cost less.
- Its 16K-token context window is larger than 4% of them (median 262K), about 20 pages of text.
- On LMArena's Text board it ranks #113 of the 120 comparable models scored there.
- 9 providers serve it; 75% of comparable models have fewer.
GPT-3.5-Turbo 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 |
|---|---|---|---|---|
| APIMart | $0.40/1M | From$1.20/1M | — | — |
| OpenAIOfficial | $0.50/1M | $1.50/1M | — | — |
 OrcaRouter | $0.50/1M | From$1.50/1M | — | 16K |
| AI/ML API | $0.50/1M | $1.50/1M | — | — |
 Impossibl | $0.50/1M | $1.50/1M | — | — |
 APIYI | $0.50/1M | From$1.50/1M | — | — |
 LaoZhang API | $0.50/1M | From$1.50/1M | — | — |
 FastRouter | $0.50/1M | From$1.50/1M | — | 16K |
| OpenRouter | $1/1M | From$2/1M | — | 4K |
- APIMartFrom$1.20
- OpenAIOfficial$1.50
- AI/ML API$1.50
- Impossibl$1.50
- OrcaRouterFrom$1.50
- APIYIFrom$1.50
- LaoZhang APIFrom$1.50
- FastRouterFrom$1.50
- OpenRouterFrom$2
Specs
- Type
- Text
- Maker
- OpenAI
- Inputs
- Text
- Outputs
- Text
- Context
- 16K≈ 20 pages of text
- Max output
- 4K
- Capabilities
- JSON, Tool calling
- Released
- May 28, 2023
- License
- proprietary
- Open weights
- No, API only
- Arena score
- 1125Text
Alternatives to GPT-3.5-Turbo
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| GPT-3.5-Turbothis model | $1.20/1M | 16K | 1125 | 9 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
 Sonar | $1/1M | 127K | — | 9 |
| GLM-5.2 | $1.80/1M | 1M | 1604 | 44 |
| Grok Build 0.1 | $1.60/1M | 256K | — | 18 |
| Gemini 3.8 Flash | $3/1M | 1.05M | 1585 | 30 |
More from OpenAI
GPT-3.5-Turbo FAQ
APIMart, at $1.20 /1M. 9 providers serve GPT-3.5-Turbo; the table above lists every one with its price.
GPT-3.5-Turbo reads up to 16K tokens per request and writes up to 4K.
No. GPT-3.5-Turbo is only available through an API; OpenAI does not publish its weights.
9 API providers serve GPT-3.5-Turbo. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us