Migrating from o4-mini-2025-04-16 to gpt-5.6-terra
What changes when you move from o4-mini-2025-04-16 to gpt-5.6-terra: input price +81.8%, output price +172.7%, context window 200,000 → 1,050,000 tokens.
- Status
- Deprecated
- Shutdown
- Oct 23, 2026
- Time left
- 8 days
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | o4-mini-2025-04-16 | gpt-5.6-terra | Change |
|---|---|---|---|
| Input | $1.10first seen October 1, 2026 · source | $2.00first seen October 1, 2026 · source | +81.8% |
| Cached input | $0.275first seen October 1, 2026 · source | $0.20first seen October 1, 2026 · source | −27.3% |
| Output | $4.40first seen October 1, 2026 · source | $12.00first seen October 1, 2026 · source | +172.7% |
At 1M input and 250K output tokens a month: $2.20 on o4-mini-2025-04-16, $5.00 on gpt-5.6-terra (+127.3%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | o4-mini-2025-04-16 | gpt-5.6-terra | Change |
|---|---|---|---|
| Context window | 200,000 tokensin place when tracking began (October 7, 2026) · source | 1,050,000 tokensin place when tracking began (October 7, 2026) · source | +425% |
| Max output tokens | 100,000 tokensin place when tracking began (October 7, 2026) · source | 128,000 tokensin place when tracking began (October 7, 2026) · source | +28% |
Benchmarks
Same benchmark and source on both sides; settings named where they differ| Benchmark | o4-mini-2025-04-16 | gpt-5.6-terra | Change |
|---|---|---|---|
| Arena TextArena, xhigh effort (vs no setting). Ranges don't overlap. | 1391 ±4 | 1466 ±4 | +75 |
| Arena Text: CodingArena, xhigh effort (vs no setting). Ranges don't overlap. | 1433 ±7 | 1517 ±7 | +84 |
| Arena VisionArena, xhigh effort (vs no setting). Ranges don't overlap. | 1201 ±7 | 1268 ±7 | +67 |
| FrontierMath Tier 4Epoch AI, max effort (vs high effort). | 4.9% | 70.7% | +65.8 pts |
| FrontierMath Tiers 1-3Epoch AI, max effort (vs high effort). | 36.1% | 86.0% | +49.9 pts |
GPQA DiamondEpoch AI, max effort (vs high effort).Other settings
| 79.6% | 93.3% | +13.7 pts |
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs high effort).Other settings
| 81.7% | 99.7% | +18.0 pts |
| SimpleQA VerifiedEpoch AI, max effort (vs low effort). | 19.6% | 43.2% | +23.6 pts |
A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
Features and parameters
Compare models- Fine-tuning: supported on o4-mini-2025-04-16, not supported on gpt-5.6-terra.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
Same on both
- Structured outputs: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
- Function calling: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
- Prompt caching: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
- Batch API: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
- Image input: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
- Reasoning / thinking: supported on both.o4-mini-2025-04-16: in place when tracking began (October 7, 2026) · source · gpt-5.6-terra: in place when tracking began (October 7, 2026) · source
Not published for o4-mini-2025-04-16: PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.
Not published for gpt-5.6-terra: PDF input, temperature parameter, top_p parameter, logprobs.
Free tier
o4-mini-2025-04-16: 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)
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
Aliases
All aliasesAliases pointing at o4-mini-2025-04-16: o4-mini (in place when tracking began (October 7, 2026) · source)
No aliases point at gpt-5.6-terra.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| o4-mini-2025-04-16 | Microsoft Foundryversion 2025-04-16 | o4-mini | Nov 19, 2026Deprecated | 35 days |
| 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
o4-mini-2025-04-16togpt-5.6-terra. - Re-check costs: gpt-5.6-terra costs more than o4-mini-2025-04-16 (input +81.8%, output +172.7%).
Counting to 8:00 pm ET on October 22, 2026, which is 00:00 UTC on October 23, 2026.
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: o4-mini-2025-04-16, gpt-5.6-terra.