Migrating from o3-mini-2025-01-31 to gpt-5.6-sol
What changes when you move from o3-mini-2025-01-31 to gpt-5.6-sol: input price +263.6%, output price +354.5%, 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 | o3-mini-2025-01-31 | gpt-5.6-sol | Change |
|---|---|---|---|
| Input | $1.10first seen October 1, 2026 · source | $4.00first seen October 1, 2026 · source | +263.6% |
| Cached input | $0.55first seen October 1, 2026 · source | $0.40first seen October 1, 2026 · source | −27.3% |
| Output | $4.40first seen October 1, 2026 · source | $20.00first seen October 1, 2026 · source | +354.5% |
At 1M input and 250K output tokens a month: $2.20 on o3-mini-2025-01-31, $9.00 on gpt-5.6-sol (+309.1%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | o3-mini-2025-01-31 | gpt-5.6-sol | 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 | o3-mini-2025-01-31 | gpt-5.6-sol | Change |
|---|---|---|---|
| Arena TextArena, xhigh effort (vs high effort). Ranges don't overlap. | 1364 ±5 | 1485 ±4 | +121 |
| Arena Text: CodingArena, xhigh effort (vs high effort). Ranges don't overlap. | 1434 ±12 | 1534 ±7 | +100 |
| FrontierMath Tier 4Epoch AI, max effort (vs high effort). | 0.0% | 82.9% | +82.9 pts |
| FrontierMath Tiers 1-3Epoch AI, max effort (vs high effort). | 18.6% | 89.1% | +70.5 pts |
GPQA DiamondEpoch AI, max effort (vs high effort).Other settings
| 77.0% | 93.5% | +16.5 pts |
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs high effort).Other settings
| 76.9% | 100.0% | +23.1 pts |
| SimpleQA VerifiedEpoch AI, max effort (vs high effort). | 15.3% | 69.7% | +54.4 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 modelsSame on both
- Structured outputs: supported on both.o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source · gpt-5.6-sol: in place when tracking began (October 7, 2026) · source
- Function calling: supported on both.o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source · gpt-5.6-sol: in place when tracking began (October 7, 2026) · source
- Batch API: supported on both.o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source · gpt-5.6-sol: in place when tracking began (October 7, 2026) · source
- Reasoning / thinking: supported on both.o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source · gpt-5.6-sol: in place when tracking began (October 7, 2026) · source
- Fine-tuning: not supported on both.o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source · gpt-5.6-sol: in place when tracking began (October 7, 2026) · source
Not published for o3-mini-2025-01-31: Prompt caching, Image input, PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.
Not published for gpt-5.6-sol: PDF input, temperature parameter, top_p parameter, logprobs.
Free tier
o3-mini-2025-01-31: no free tier listed
gpt-5.6-sol: Free for shared data, 1M tokens a day for Launch and Grow (250K for Build), in place when tracking began (October 12, 2026) (source) · All free models
gpt-5.6-sol adds a free tier.
Aliases
All aliasesAliases pointing at o3-mini-2025-01-31: o3-mini (in place when tracking began (October 7, 2026) · source)
Aliases pointing at gpt-5.6-sol: gpt-daybreak-blue-latest (in place when tracking began (October 7, 2026) · source)
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| o3-mini-2025-01-31 | Microsoft Foundryversion 2025-01-31 | o3-mini | Nov 19, 2026Deprecated | 35 days |
| gpt-5.6-sol | Amazon Bedrock | openai.gpt-5.6-sol | not before Jul 13, 2027Active | |
| gpt-5.6-sol | Microsoft Foundryversion 2026-07-09 | gpt-5.6-sol | 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
o3-mini-2025-01-31togpt-5.6-sol. - Re-check costs: gpt-5.6-sol costs more than o3-mini-2025-01-31 (input +263.6%, output +354.5%).
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: o3-mini-2025-01-31, gpt-5.6-sol.