The Orchestrator › Models › OpenAI
OpenAI: o3 Mini (batch)
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to...
Specifications
| Provider | OpenAI |
| Model ID | openai/o3-mini |
| Context window | 200K tokens (200,000) |
| Modalities | text + file → text |
| Tokenizer | GPT |
| Router sources | OpenRouter, Vercel AI Gateway, Cloudflare |
| Released | 2025-01-31 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| batch | OpenRouter | openai/o3-mini:batch | $0.55 | $2.20 | 200K |
| standard | Vercel AI Gateway | openai/o3-mini | $1.10 | $4.40 | 200K |
| standard | Cloudflare | openai/o3-mini | $1.10 | $4.40 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.10 | $4.40 | — |
| 2026-11-14 | $1.10 | $4.40 | 200K |
Capabilities
File inputAgentic tool useStructured outputsReasoning (always on)Controllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_tokens, reasoning, response_format, seed, structured_outputs, tool_choice, tools