- Home
- All models
- GPT-3.5 Turbo
GPT-3.5 Turbo: price, performance and context
Proprietary GPT-3.5 Turbo by OpenAI costs $0.50 per 1M input and $1.50 per 1M output tokens, handles up to 16.4K tokens in one request (≈ 49 pages of text) and scores 5.5 points on the AgentKernel performance index, rank 206 of 212.
Privacy: no zero-retention provider listed.
Updated Oct 09, 2026, 17:39 UTC · openai/gpt-3.5-turbo
Open in the interactive comparison
Key facts
- Licence
- Proprietary: no public weights, only through a provider API
- Input / 1M tokens
- $0.50
- Output / 1M tokens
- $1.50
- Context window
- 16.4K tokens
- Max. output
- 4.1K tokens
- Performance index
- 5.5 points · rank 206 of 212
- Coding index
- 10.7 points · rank 112 of 119
- Agentic index
- n/a
- Cost at your usage
- $0.875 / month
- Knowledge cutoff
- Sep 2021
- In the catalog since
- May 28, 2023
- Capabilities
- Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|
| Chat repliesA question with a short history, a detailed answer | $0.001 | 11,000 |
| Email draftsBullet points in, a finished email out | $0.001 | 14,000 |
| Document summariesRead 10 pages, write a one-page summary | $0.002 | 4,200 |
| Code reviewsReview and comment on 500 lines of code | $0.004 | 2,400 |
| Book analysesAnalyse a 300-page book in one go | – | does not fit the context |
Cheaper with similar performance
Stronger models
Open alternatives
AGENTKERNEL