Migrating from davinci-002 to gpt-5.6-terra
What changes when you move from davinci-002 to gpt-5.6-terra: input price 0%, output price +500%.
- From
- davinci-002
- Status
- Retired
- Shutdown
- Sep 28, 2026
- Time left
- —
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | davinci-002 | gpt-5.6-terra | Change |
|---|---|---|---|
| Input | $2.00first seen October 1, 2026 · source | $2.00first seen October 1, 2026 · source | 0% |
| Cached input | Not published | $0.20first seen October 1, 2026 · source | — |
| Output | $2.00first seen October 1, 2026 · source | $12.00first seen October 1, 2026 · source | +500% |
At 1M input and 250K output tokens a month: $2.50 on davinci-002, $5.00 on gpt-5.6-terra (+100%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | davinci-002 | gpt-5.6-terra | Change |
|---|---|---|---|
| Context window | Not published | 1,050,000 tokensin place when tracking began (October 7, 2026) · source | — |
| Max output tokens | 16,384 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 7, 2026) · source | +681.3% |
Features and parameters
Compare models- Batch API: not supported on davinci-002, supported on gpt-5.6-terra.davinci-002: in place when tracking began (October 6, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
Same on both
- Fine-tuning: not supported on both.davinci-002: in place when tracking began (October 6, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
Not published for davinci-002: Structured outputs, Function calling, Prompt caching, Image input, PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window.
Not published for gpt-5.6-terra: PDF input, temperature parameter, top_p parameter, logprobs.
Free tier
davinci-002: no free tier listed
gpt-5.6-terra: Free for shared data, 10M tokens a day for Launch and Grow (2.5M for Build), in place when tracking began (October 12, 2026) (source) · All free models
gpt-5.6-terra adds a free tier.
Aliases
All aliasesNo aliases point at either model.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| gpt-5.6-terra | Amazon Bedrock | openai.gpt-5.6-terra | not before Jul 13, 2027Active | |
| gpt-5.6-terra | Microsoft Foundryversion 2026-07-09 | gpt-5.6-terra | Jan 11, 2028Active | 453 days |
Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.
Checklist
- Change the model string from
davinci-002togpt-5.6-terra. - Re-check costs: gpt-5.6-terra costs more than davinci-002 (output +500%).
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: davinci-002, gpt-5.6-terra.