Davinci 002
davinci-002Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $2.00 | |
| Batch 50% off | $1.00 | $1.00 | 50% off |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$750
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,032
- Coding agent1,000 requests a day, 40K in / 2K out$2,520
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$2,640
Where to run it
1 host serve Davinci 002. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API davinci-002 | $2.00 / $2.00 | davinci-002 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| fine-tuning ft:davinci-002 | $12.00 / $12.00 | ft:davinci-002 | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 16% less
- 77% less
- 90% less
Other frontier labs
- 22% less
- 25% less
- 90% less
- 38% less
Open-weight picks
- 14% less
- 57% less
- 59% less
- 60% less
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="davinci-002", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "davinci-002", "input": "Hello"}'from litellm import completion
response = completion(
model="text-completion-openai/davinci-002",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Davinci 002 cost?
On OpenAI, Davinci 002 costs $2.00 per million input tokens and $2.00 per million output tokens.
Which APIs offer Davinci 002?
Davinci 002 runs on 1 API: OpenAI.
What is Davinci 002's context window?
16K tokens, with up to 4K tokens in one reply.
Is Davinci 002 being retired?
It has been retired: OpenAI retired it on 28 Sep 2026.
What are cheaper alternatives to Davinci 002?
Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (16% less), Grok 4.20 Multi Agent on xAI (22% less), Gemini 3.8 Flash on Google AI Studio (25% less) and Inkling on DeepInfra (14% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Davinci 002's API model id?
Use davinci-002 with OpenAI.
Sources
Raw catalog entry for davinci-002 on OpenAI
{
"deprecation_date": "2026-09-28",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-5.6-terra",
"input_cost_per_token": 0.000002,
"input_cost_per_token_batches": 0.000001,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 16384,
"max_output_tokens": 4096,
"mode": "completion",
"output_cost_per_token": 0.000002,
"output_cost_per_token_batches": 0.000001,
"source": "https://developers.openai.com/api/docs/pricing"
}