Skip to the content

GPT-6.2 Astra

openai/gpt-6.2-astra

Maker
OpenAI, United States
Released
2026-11-17
Knowledge cutoff
2026-05-18
Family
gpt-astra
Weights
closed
Tasks
text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering
Experiential Labs, about $0.02 for a typical text.chat call

Offerings

ProviderModel id at the providerStatusPrice per 1M tokensPer-unit pricesLimitsCapabilities (level)
Experiential Labsgpt-6.2-astraga
  • Input: $8
  • Output: $40
  • Cache read: $0.4
  • Cache write (5 min): $10
  • Input, prompts over 272,001 tokens: $16
  • Output, prompts over 272,001 tokens: $60
  • Cache read, prompts over 272,001 tokens: $0.8
  • Reasoning, prompts over 272,001 tokens: $60
Since 2026-11-18
none
  • Context: 1,050,000 tokens
  • Max input: 922,000 tokens
  • Max output: 128,000 tokens
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • input.image claimed
OpenAIgpt-6.2-astraga
  • Input: $8
  • Output: $40
  • Cache read: $0.4
  • Cache write (5 min): $10
  • Input, prompts over 272,000 tokens: $16
  • Output, prompts over 272,000 tokens: $60
  • Cache read, prompts over 272,000 tokens: $0.8
  • Cache write (5 min), prompts over 272,000 tokens: $20
  • Input, priority tier: $16
  • Output, priority tier: $80
  • Cache read, priority tier: $0.8
  • Cache write (5 min), priority tier: $20
  • Input, batch tier: $4
  • Output, batch tier: $20
  • Cache read, batch tier: $0.2
  • Cache write (5 min), batch tier: $5
Since 2026-11-18 · models.dev, MIT
none
  • Context: 1,050,000 tokens
  • Max input: 922,000 tokens
  • Max output: 128,000 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • parallel_tools claimed
  • tool_choice claimed
  • prompt_caching claimed
  • web_search claimed
  • computer_use claimed
  • no_training claimed
OpenRouteropenai/gpt-6.2-astraga
  • Input: $8
  • Output: $40
  • Cache read: $0.4
  • Cache write (5 min): $10
  • Input, prompts over 272,000 tokens: $16
  • Output, prompts over 272,000 tokens: $60
  • Cache read, prompts over 272,000 tokens: $0.8
  • Cache write (5 min), prompts over 272,000 tokens: $20
Since 2026-11-18
none
  • Context: 1,050,000 tokens
  • Max input: 922,000 tokens
  • Max output: 128,000 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf native
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
OpenRouteropenai/gpt-6.2-astra:batchga
  • Input: unknown
  • Output: unknown
  • Input, prompts over 272,000 tokens: $8
  • Output, prompts over 272,000 tokens: $30
  • Cache read, prompts over 272,000 tokens: $0.4
  • Cache write (5 min), prompts over 272,000 tokens: $10
  • Input, batch tier: $4
  • Output, batch tier: $20
  • Cache read, batch tier: $0.2
  • Cache write (5 min), batch tier: $5
Since 2026-11-18
none
  • Context: 1,050,000 tokens
  • Max output: 128,000 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf native
  • output.text claimed
  • tools claimed
  • tool_choice claimed
  • structured_output claimed
  • reasoning claimed
  • prompt_caching claimed

Quality scores

BasisScore (0–1)RawMeasuredSource
epoch:gpqa_diamond1.0000.96842026-10-27Epoch AI, CC-BY-4.0, normalized by Nanner Tech
epoch:eci1.000174.17002026-11-17Epoch AI, CC-BY-4.0, normalized by Nanner Tech
epoch:frontiermath0.9740.92632026-10-27Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

  • gpt-6.2-astra
  • openai/gpt-6.2-astra:batch
  • ~openai/gpt-astra-latest

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model
curl 'https://rhumbdata.com/v1/models/openai/gpt-6.2-astra' \
  -H "Authorization: Bearer $RHUMB_KEY"
Resolve text.chat on its providers
curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=experiential,openai,openrouter' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-18.1 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).