Skip to main content

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
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 "openai/gpt-6.2-astra".

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Azure Foundryazure_foundry/gpt-6.2-astra
$8.00/M$40.00/M
OpenAIopenai/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.

$8.00/MAzure Foundry and OpenAI

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 better

70tokens/sacross providers

Faster than 71% of the other 590 models on the gateway

Time to first token

Lower is better

3.1sacross providers

Faster than 30% of the other 151 models on the gateway

Response latency

Lower is better

13sacross providers

Faster than 14% of the other 739 models on the gateway

Benchmarks

The Respan Index plus 15 published scores from 5 sources, each linked to where it was published.

175 ranked models. The shaded band is this model's 95% interval, 71.4 to 78.8. Claude Opus 5.5 and Claude Sonnet 5.5 fall inside it, so the gap is within the margin of error.
GPT-6.2 Astra by category: Coding 58.2, Agents 84.8, Reasoning 89.8, Knowledge & language 78.6, Human preference 61.4
  1. 5GPT-6.2 Astra75.3
  2. 4Claude Opus 5.576.0
  3. 6Claude Sonnet 5.573.4

Published scores

BenchmarkScore
MirrorCodeEpoch AI67.8%
Terminal-Bench 4.0Vals AI63.1%

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.

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.