GPT-6.2 Astra
GPT-6.2 Astra can build and revise software, use a computer, and work with documents. It accepts text and images and responds with text. In the Responses API, use the Multi-agent beta to delegate work to subagents.
- Input / output price
- $8.00 / $40.00 per 1M
- Context
- 1.1M tokens
- Released
- Nov 17, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
2 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/gpt-6.2-astra | $8.00/M | $40.00/M |
OpenAI openai/gpt-6.2-astra | $8.00/M | $40.00/M |
Is a provider down? OpenAI status
Pricing
Averaged across 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $8.00 per 1M
- Average output
- $40.00 per 1M
- Average cache read
- $0.40 per 1M
- Average cache write
- $10.00 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 better70tokens/sacross providers
Time to first token
Lower is better3.1sacross providers
Response latency
Lower is better13sacross providers
Benchmarks
The Respan Index plus 15 published scores from 5 sources, each linked to where it was published.
75.3/ 100
Respan Index#5 of 175
- 5GPT-6.2 Astra75.3
- 4Claude Opus 5.576.0
- 6Claude Sonnet 5.573.4
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MirrorCodeEpoch AI | 67.8% | Epoch AI | Nov 18, 2026 |
| Terminal-Bench 4.0Vals AI | 63.1% | Vals AI | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondOpenAI | 97% | OpenAI | Nov 17, 2026 |
| GPQA DiamondEpoch AI | 96.8% | Epoch AI | Nov 18, 2026 |
| Mystery Game PuzzlesEpoch AI | 95% | Epoch AI | Nov 18, 2026 |
| EBR-benchEpoch AI | 92.4% | Epoch AI | Nov 18, 2026 |
| Chess PuzzlesEpoch AI | 78% | Epoch AI | Nov 18, 2026 |
| SimpleBenchSimpleBench | 77.3% | SimpleBench | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| FrontierMath Tier 4 v2Epoch AI | 100% | Epoch AI | Nov 18, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 100% | Epoch AI | Nov 18, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 92.6% | Epoch AI | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SimpleQA VerifiedEpoch AI | 78.5% | Epoch AI | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Furniture AssemblyEpoch AI | 89.2% | Epoch AI | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1781 Elo · #3 of 123 | LMArena | Nov 18, 2026 |
| LMArena AgentLMArena | 0.1522 · #6 of 68 | LMArena | Nov 18, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
Apps
Use GPT-6.2 Astra 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.
GPT-6.2 Astra FAQ
Short answers, built from the data on this page.
GPT-6.2 Astra is a model from OpenAI, released on Nov 17, 2026. GPT-6.2 Astra can build and revise software, use a computer, and work with documents. It accepts text and images and responds with text. In the Responses API, use the Multi-agent beta to delegate work to subagents.
On the Respan gateway, GPT-6.2 Astra costs $8.00 per 1M input tokens and $40.00 per 1M output tokens on every provider, after gateway discounts.
GPT-6.2 Astra is available through 2 providers: Azure Foundry and OpenAI.
GPT-6.2 Astra accepts up to 1.1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "openai/gpt-6.2-astra". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GPT-6.2 Astra scores 75.3 out of 100 on the Respan Index v1.1, ranking #5 of 175 models. By category: Coding 58.2, Agents 84.8, Reasoning 89.8, Knowledge & language 78.6, and Human preference 61.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
GPT-6.2 Astra has 15 published benchmark scores, including MirrorCode 67.8%, GPQA Diamond 97%, and FrontierMath Tier 4 v2 100%. 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.