Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

GPT-6.2 Astra

gpt-6.2-astraby OpenAI
Try in Chat

OpenAI's most capable GPT-6.2 reasoning model for the hardest work, with a 1.05M-token context window, image input and native Responses tool calling.

Context

1.05M

Max output

128K

Price per million tokens

$8in$0.40cached$40out

Speed

60.2 tok/s

Released

Nov 2026

Waterfall

  1. 1
    OpenAI via Experiential Cloud$8/$40100% up60.2 tok/s1.66s

Quickstart

I want you to route my LLM calls for "gpt-6.2-astra" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
3. Use the model id "gpt-6.2-astra" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text, image, pdf

Tools & structure

ToolsStrict toolsParallel tool callsStructured output

Streaming

Streaming

Limits

Max output128,000

Sending an unsupported field? See error referenceOpenAI docs

Providers serving this model3
Status
OpenAI via Experiential Cloudexperiential60.2 tok/s1.66s100%#1 / 11.05M128K$8$16 past 272K$40$60 past 272Kcache$0.40$0.80 past 272KWrite 5m: $10$20 past 272K-no dataactivemeasured
Azure Foundrygpt-6.2-astrano datano data99.9%-1.05M128Kno datano datano data-no dataactive-
Azure Foundrygpt-6.2-astra-2026-11-17deployed 2026-11-17no datano data99.9%-1.05M128Kno datano datano data-no dataactive-
Release notes