o3
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.
- Input / output price
- $2.00 / $8.00 per 1M
- Context
- 200K tokens
- Released
- Apr 16, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure OpenAI azure_openai/o3 | $2.00/M | $8.00/M |
OpenAIRetiring openai/o3 | $2.00/M | $8.00/M |
Azure FoundryRetired azure_foundry/o3 | $2.00/M | $8.00/M |
OpenRouterRetired openrouter/o3 | $2.00/M | $8.00/M |
Is a provider down? Azure OpenAI status, ChatGPT status, OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $2.00 per 1M
- Average output
- $8.00 per 1M
- Average cache read
- $0.50 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better325tokens/sacross providers
Time to first token
Lower is better4.6sacross providers
Response latency
Lower is better7.0sacross providers
Benchmarks
The Respan Index plus 17 published scores from 9 sources, each linked to where it was published.
25.8/ 100
Respan Index#108 of 176
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedOpenAI | 69.1% | OpenAI | Aug 7, 2025 |
| SWE-bench VerifiedEpoch AI | 62.3% | Epoch AI | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 52.4% | Håvard Tveit Ihle | Oct 5, 2026 |
| GSO Opt@1GSO | 3.9% | GSO | Jun 9, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OSWorld-VerifiedXLANG | 23% | XLANG | Jul 28, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 81.8% | Epoch AI | Oct 5, 2026 |
| SimpleBenchSimpleBench | 53.1% | SimpleBench | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 37% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 29% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 97.8% | Epoch AI | Oct 5, 2026 |
| AIME 2025MathArena | 89.2% | MathArena | Sep 17, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 84.4% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 33.3% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SimpleQA VerifiedEpoch AI | 49.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1432 Elo · #90 of 191 | LMArena | Oct 8, 2026 |
| LMArena VisionLMArena | 1216 Elo · #62 of 91 | LMArena | Oct 9, 2026 |
Compare o3: o3 vs o1, o3 vs GPT-6.2 Astra, o3 vs GPT-6 Astra, o3 vs GPT-6.1 Sol, o3 vs GPT-6.1 Terra, o3 vs GPT-6.2 Sol
Apps
Use o3 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.
o3 FAQ
Short answers, built from the data on this page.
o3 is a model from OpenAI, released on Apr 16, 2025. o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.
On the Respan gateway, o3 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens on every provider, after gateway discounts.
o3 is available through 4 providers: Azure OpenAI, OpenAI, Azure Foundry, and OpenRouter.
o3 accepts up to 200K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "openai/o3". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
o3 scores 25.8 out of 100 on the Respan Index v1.1, ranking #108 of 176 models. By category: Coding 7.8, Agents 8.3, Reasoning 38.2, Knowledge & language 49.2, and Human preference 49.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
o3 has 17 published benchmark scores, including SWE-bench Verified 69.1%, OSWorld-Verified 23%, and GPQA Diamond 81.8%. 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.