davinci-002 pricing
davinci-002 from OpenAI costs $2.00 per 1M input tokens and $2.00 per 1M output tokens.
API id davinci-002 · OpenAI · source · updated 2026-09-26 · general-purpose
$2.00
Input / 1M tokens
$2.00
Output / 1M tokens
—
Cached input / 1M
—
Context window
davinci-002 specifications
- Provider
- OpenAI
- API id
davinci-002- Model type
- general-purpose
- Context window
- — tokens
- Max output
- not published
- Currency
- USD
- Price source
- First-party
- Last checked
- 2026-09-26
What davinci-002 costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0030 |
| Document summary | 50,000 | 2,000 | $0.10 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $2.40 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does davinci-002 cost per 1M tokens?
- davinci-002 costs $2.00 per 1M input tokens and $2.00 per 1M output tokens on the standard tier.
- What is davinci-002's context window?
- OpenAI does not publish a context window for davinci-002 on its pricing page.
- Is there a cheaper OpenAI model than davinci-002?
- Yes. omni-moderation-latest is free per 1M input tokens versus $2.00 for davinci-002.
- Where does this davinci-002 price come from?
- Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.