Model Details
Where is Davinci-002 a perfect fit?
- High-quality text generation with structured prompts
- Legacy applications requiring stronger reasoning than babbage models
- Content rewriting, summarisation, and structured outputs
- Prompt-engineered workflows built before chat-based models
- Data extraction and transformation pipelines
- Systems prioritising consistency with historical outputs
Quick Model Estimate
Your Davinci-002 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
Cost Breakdown
Prices are watched for changes and checked against the provider's own page.
Pricing
Other Models in the Davinci-002 Family
FAQs about Davinci-002
How much does Davinci-002 cost per 1M tokens?
Davinci-002 costs between $1.00 and $2.00 per million input tokens, and between $1.00 and $2.00 per million output tokens. The range covers Standard and Batch pricing.
What does a typical workload cost with Davinci-002?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $2.50 with Davinci-002 at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use Davinci-002?
Davinci-002 is available through OpenAI, from $1.00 per million input tokens.
Is there cheaper Davinci-002 pricing than the standard rate?
Yes. Batch pricing for Davinci-002 starts at $1.00 per million input tokens against $2.00 on the standard tier, about 50% lower.
What is Davinci-002's context window?
Davinci-002 has a context window of 16,384 tokens.
Is Davinci-002 still available?
Davinci-002 is deprecated and was retired on 28 September 2026. The replacement is GPT-5.6 Terra.