o1 Mini
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the launch announcement. Note: This model is currently experimental and not suitable for production use-cases, and may be heavily rate-limited.
- Input / output price
- $1.10 / $4.40 per 1M
- Context
- 128K tokens
- Released
- Sep 12, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/o1-mini | $1.10/M | $4.40/M |
Pricing
USD per 1M tokens on Azure Foundry, after gateway discounts.
- Input
- $1.10 per 1M
- Output
- $4.40 per 1M
- Cache read
- $0.55 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Benchmarks
The Respan Index plus 7 published scores from 5 sources, each linked to where it was published.
13.9/ 100
Respan Index#163 of 175
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| WeirdMLHåvard Tveit Ihle | 36.3% | Håvard Tveit Ihle | Nov 10, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 62.4% | Epoch AI | Nov 10, 2026 |
| SimpleBenchSimpleBench | 18.1% | SimpleBench | Nov 10, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 89.2% | Epoch AI | Nov 10, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 46.9% | Epoch AI | Nov 10, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1337 Elo · #155 of 187 | LMArena | Nov 18, 2026 |
Compare o1 Mini: o1-mini vs o3-mini, o1-mini vs GPT-6.2 Astra, o1-mini vs GPT-6 Astra, o1-mini vs GPT-6.1 Sol, o1-mini vs GPT-6.1 Terra, o1-mini vs GPT-6.2 Sol
Apps
Use o1 Mini in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
o1 Mini FAQ
Short answers, built from the data on this page.
o1 Mini is a model from OpenAI, released on Sep 12, 2024. The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the launch announcement. Note: This model is currently experimental and not suitable for production use-cases, and may be heavily rate-limited.
On the Respan gateway, o1 Mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens on Azure Foundry, after gateway discounts.
o1 Mini is served by Azure Foundry.
o1 Mini accepts up to 128K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "o1-mini". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
o1 Mini scores 13.9 out of 100 on the Respan Index v1.1, ranking #163 of 175 models. By category: Coding 3.8, Agents 8.2 (estimated), Reasoning 18.5, Knowledge & language 7.3 (estimated), and Human preference 36.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
o1 Mini has 7 published benchmark scores, including WeirdML 36.3%, GPQA Diamond 62.4%, and MATH Level 5 89.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.