Is gpt-5.6-terra cheaper than davinci-002?

No. The labeled example monthly cost is $24 for the old model and $44 for the replacement.

Does gpt-5.6-terra have a bigger context window than davinci-002?

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

davinci-002 to gpt-5.6-terra: price, context, and code

The official replacement is gpt-5.6-terra. davinci-002 shut down on 2026-09-28 per OpenAI's deprecation page (checked 2026-10-17). On the labeled example of 10 million input tokens and 2 million output tokens, gpt-5.6-terra costs $44 a month, higher than $24 for davinci-002.

davinci-002 to gpt-5.6-terra

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	$2	$2	0% (same)
Output	$2	$12	+500% (higher)
Cached input	Not published	$0.2	Not published
Example monthly cost	$24	$44	Example only

Context and max output

Token limits
Limit	Old	New	Change
Context window	Not published	1,050,000	Not published
Max output	16,384	128,000	+681.3% (higher)

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-002",
    messages=[{"role": "user", "content": "Hello"}],
)

python after

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5.6-terra",
    messages=[{"role": "user", "content": "Hello"}],
)

typescript before

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

typescript after

import OpenAI from "openai";
const client = new OpenAI();
const response = await client.chat.completions.create({
  model: "gpt-5.6-terra",
  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-002","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":"gpt-5.6-terra","messages":[{"role":"user","content":"Hello"}]}'

Checklist

Read the shutdown date for davinci-002 on the linked official page.
Point your requests at gpt-5.6-terra.
Re-check price, context, and parameters on the provider pages linked here.
Ship the change before the published shutdown date.

Replacement for davinci-002: what changes when you switch