Is davinci-002 cheaper than davinci?

A full price comparison is not published. One or both prices are missing from the official pages we checked.

Does davinci-002 have a bigger context window than davinci?

Context window sizes are not both published on the official pages we checked.

davinci to davinci-002: price, context, and code

The official replacement is davinci-002. davinci shut down on 2024-01-04 per OpenAI's deprecation page (checked 2026-10-17). Published on the official docs: input price $20 per million tokens.

davinci to davinci-002

Some values not published Checked 2026-10-17.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
Field	Old	New	Change
Input	$20	$2	-90% (lower)
Output	Not published	$2	Not published
Cached input	Not published	Not published	Not published
Example monthly cost	Not published	$24	Example only

Context and max output

Token limits
Limit	Old	New	Change
Context window	Not published	Not published	Not published
Max output	Not published	16,384	Not published

Capabilities that differ

No differing capability values are published for both models.

API changes

No parameter change is listed on the official pages we checked. The sample below only swaps the model id.

Code

python typescript curl

python before

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="davinci",
    messages=[{"role": "user", "content": "Hello"}],
)

python after

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="davinci-002",
    messages=[{"role": "user", "content": "Hello"}],
)

typescript before

import OpenAI from "openai";
const client = new OpenAI();
const response = await client.chat.completions.create({
  model: "davinci",
  messages: [{ role: "user", content: "Hello" }],
});

typescript after

import OpenAI from "openai";
const client = new OpenAI();
const response = await client.chat.completions.create({
  model: "davinci-002",
  messages: [{ role: "user", content: "Hello" }],
});

curl before

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"davinci","messages":[{"role":"user","content":"Hello"}]}'

curl after

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"davinci-002","messages":[{"role":"user","content":"Hello"}]}'

Checklist

Read the shutdown date for davinci on the linked official page.
Point your requests at davinci-002.
Re-check price, context, and parameters on the provider pages linked here.
Ship the change before the published shutdown date.

Replacement for davinci: what changes when you switch