Fast o-series model for compact reasoning, coding, and tool use
o4-mini by openai is offered by 21 providers on this page. Public prices are shown for 19 of them. Its official list price is $1.10 per 1M input tokens and $4.40 per 1M output tokens.
Artificial Analysis rates it 16.7 on the Intelligence Index. Against its lowest blended price of $1.74 per 1M, that is roughly 10 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 152 tokens per second, with 25.87s to the first token.
The context window is 200,000 tokens, with an output limit of 100,000 tokens. 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.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe | Gateway | $0.99 | $4.00 | $0.25 | — | 200,000 | 100,000 | |
| NEAR AI Cloud | Gateway | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | |
| Kilo Gateway | Gateway | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | |
| Abacus | Gateway | $1.10 | $4.40 | — | — | 200,000 | 100,000 | |
| OpenRouter | Gateway | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | |
| Azure | Cloud | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | deprecated |
| Azure Cognitive Services | Cloud | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | deprecated |
| Impossibl | Gateway | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | |
| Cloudflare AI Gateway | Cloud | $1.10 | $4.40 | $0.28 | — | 200,000 | 100,000 | |
| Jiekou.AI | Gateway | $1.10 | $4.40 | — | — | 200,000 | 100,000 | |
| OpenAIOfficial | First-party | $1.10 | $4.40 | $0.28 | — | 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.
1 / 21 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | Vercel AI Gateway | $2.00 | $8.00 | $0.50 | — |
| flex | Vercel AI Gateway | $0.55 | $2.20 | $0.14 | — |
| fast | OpenAI | $2.00 | $8.00 | $0.50 | — |
| flex | OpenAI | $0.55 | $2.20 | $0.14 | — |
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 72 | percent correct | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.