Skip to main content

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
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "o1-mini".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Azure Foundryazure_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.

$1.10/MAzure Foundry

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

175 ranked models. The shaded band is this model's 95% interval, 10.3 to 22.3. Llama 4 Maverick and Qwen3 30B-A3B Instruct 2507 fall inside it, so the gap is within the margin of error.
o1 Mini by category: Coding 3.8, Agents 8.2 (estimated), Reasoning 18.5, Knowledge & language 7.3 (estimated), Human preference 36.9
  1. 163o1-mini13.9
  2. 162Llama 4 Maverick14.8
  3. 164Qwen3 30B-A3B Instruct 250713.8

Published scores

BenchmarkScore
WeirdMLHåvard Tveit Ihle36.3%

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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.