Deprecated by its maker
The maker has already deprecated this model (23 Oct 2026).
OpenAI · Chat
Newer version: o4 Mini. We compared release dates and version names in our catalogue.
o3-mini is OpenAI's compact text-only reasoning model optimized for cost-efficient coding, math, science, and structured-output tasks.
Evidence and sources
The maker has already deprecated this model (23 Oct 2026).
The weights aren't public, so you can't run it yourself.
Supported operations and provider-stated features
| —Not published by the provider | $0.55 | $2.20 | — | |
| —Not published by the provider | $0.55 | $2.20 | — | |
| 200K | $0.55cache read $0.275 | $2.20 | — | |
| 200K | $0.99 | $4.00 | — | |
| 200K | $1.045cache read $0.5225 | $4.18 | — | |
| 128K | $1.10 | $4.40 | — | |
| 200K | $1.10cache read $0.55 | $4.40 | — | |
| 200K | $1.10cache read $0.55batch $0.55 | $4.40batch $2.20 | — | |
| 200K | $1.10 | $4.40 | — | |
| 200K | $1.10cache read $0.55 | $4.40 | $0.00 |
Showing 10 of 35: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Abacus, Cloudflare AI Gateway, Core42, Digitalocean, Eurouter, Gradient AI, Impossibl, Merge Gateway, Vercel, Vercel AI Gateway.
7 listings without a price are hidden.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Safety: BBQ - BBQ accuracy | |
| AIR-Bench: AIRBench 2024 - #1: Confidentiality | |
| AIR-Bench: AIRBench 2024 - #2: Integrity | |
| AIR-Bench: AIRBench 2024 - #3: Availability |
| Benchmark | low | medium | high |
|---|---|---|---|
| IF | |||
| Data Analysis | |||
| Language | |||
| Overall |
| Benchmark | medium |
|---|---|
| FictionLiveBench 0 | |
| 1k | |
| 2k | |
| 4k |
| Benchmark | Score |
|---|---|
| CLEAR - EM | |
| ACI-Bench - Jury Score | |
| ADHD-Behavior - EM | |
| ADHD-MedEffects - EM |
| Benchmark | openai/o3-mini-2025-01-31 |
|---|---|
| ALT_バイアス | |
| ALT_倫理・道徳 | |
| ALT_制御性 | |
| ALT_堅牢性 |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Arena-Hard-Auto, LMArena, Apache-2.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BrowserGym Leaderboard (ServiceNow), MIT (licence) · CyBench — cite Zhang et al. 2025 · DABstep (Adyen), CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · JudgeBench, Sijun Tan et al., ScalerLab · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Orak leaderboard, KRAFTON AI (Park et al., NeurIPS 2025). Public numeric scores; leaderboard licence not stated (code MIT not applied; CC BY-NC trajectories not used). · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Swallow LLM Leaderboard v2, Swallow LLM team (Institute of Science Tokyo). Contents CC BY 4.0; Japanese post-trained task scores on the source's 0..1 scale. (licence) · Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence)
news.ycombinator.com
Also known as: azure/eu/o3-mini, azure/eu/o3-mini-2025-01-31, azure/o3-mini, azure/o3-mini-2025-01-31, azure/us-gov/o3-mini, azure/us-gov/o3-mini-2025-01-31, azure/us/o3-mini, azure/us/o3-mini-2025-01-31, gradient_ai/openai-o3-mini, o3-mini-0131, o3-mini-2025-01-31, o3-mini-2025-01-31-high, o3-mini-2025-01-31-low, o3-mini-high, o3-mini-low, openai-o3-mini, openai/o3-mini, openai/o3-mini-high, openai/o3-mini:batch, vercel_ai_gateway/openai/o3-mini
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works