Smaller o-series reasoner for economical coding, math, and planning tasks
o3-mini by openai is offered by 21 providers on this page. Public prices are shown for 20 of them. Its official list price is $1.10 per 1M input tokens and $4.40 per 1M output tokens.
The context window is 200,000 tokens at the reference host, but hosts report different limits, from 131,072 to 200,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-05.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe | Gateway | $0.99 | $4.00 | — | — | 200,000 | 100,000 | |
| Impossibl | Gateway | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | |
| Azure Cognitive Services | First-party | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | deprecated |
| Jiekou.AI | Gateway | $1.10 | $4.40 | — | — | 131,072 ⚠ | 131,072 | |
| Vercel AI Gateway | Cloud | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | deprecated |
| DevPass (LLM Gateway) | Gateway | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | |
| Cloudflare AI Gateway | Cloud | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | |
| Kilo Gateway | Gateway | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | |
| Azure | First-party | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | deprecated |
| Merge Gateway | Gateway | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | |
| OpenAIOfficial | First-party | $1.10 | $4.40 | $0.55 | — | 200,000 | 100,000 | deprecated |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 60.4 | percent correct | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
2 / 21 providers expose no reasoning control (reasoning_options: []).