Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

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

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0030
Document summary50,0002,000$0.10
1M tokens in, 200K out1,000,000200,000$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.

Head-to-head comparisons

Other OpenAI models

See all OpenAI pricing →