GPT-6 Astra

OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use, research, and document creation.

Input price
$9.00–$18.00list $10.00-10%
Output price
$45.00–$67.50list $50.00-10%
Context
1.1M
Max output
128K
Modalities
InputTextImageOutputText
169 (#1 of 89)
1441
—
Released
2026-09-03
Knowledge cutoff
2026-04-30
Try in ChatCompare

Providers

This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].

Included providers2
  • SuccessTTFT
  • Azure AI FoundryGlobal——
  • OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

ItemStandardFlexBatchPriorityPrice
Prompt ≤ 272K tokens
Inputper 1M tokens$9.00list $10.00-10%$4.50list $5.00-10%$4.50list $5.00-10%$18.00list $20.00-10%—
Outputper 1M tokens$45.00list $50.00-10%$22.50list $25.00-10%$22.50list $25.00-10%$90.00list $100.00-10%—
Cache readper 1M tokens$0.90list $1.00-10%$0.45list $0.50-10%$0.45list $0.50-10%$1.80list $2.00-10%—
Cache write (5 min)per 1M tokens$11.25list $12.50-10%$5.625list $6.25-10%$5.625list $6.25-10%$22.50list $25.00-10%—
Cache write (1 hour)per 1M tokens$22.50list $25.00-10%$11.25list $12.50-10%$11.25list $12.50-10%$45.00list $50.00-10%—
Prompt > 272K tokens
Inputper 1M tokens$18.00list $20.00-10%$9.00list $10.00-10%$9.00list $10.00-10%$36.00list $40.00-10%—
Outputper 1M tokens$67.50list $75.00-10%$33.75list $37.50-10%$33.75list $37.50-10%$135.00list $150.00-10%—
Cache readper 1M tokens$1.80list $2.00-10%$0.90list $1.00-10%$0.90list $1.00-10%$3.60list $4.00-10%—
Cache write (5 min)per 1M tokens$22.50list $25.00-10%$11.25list $12.50-10%$11.25list $12.50-10%$45.00list $50.00-10%—
Cache write (1 hour)per 1M tokens$45.00list $50.00-10%$22.50list $25.00-10%$22.50list $25.00-10%$90.00list $100.00-10%—
Web searchper request————$0.009list $0.01-10%

Make a request

Set your provider preferences, then copy the request. It reads your API key from OHMYGPT_API_KEY.

Provider preferences don’t apply to this model. Need a custom setup? Contact [email protected].

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Similar models

Other models with the same output types at a similar price.

  • Better value: more capable, lower price
  • Pareto frontier
  • This model
  • Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GPT-6 AstraThis model
169
Input
$9.00–$18.00
Output
$45.00–$67.50
Claude Fable 5.1
166
Input
$11.00
Output
$55.00
GPT-5 Pro
151
Input
$13.50
Output
$108.00
Kimi K3.1 Pro HighSpeed
—
Input
$4.1756–$4.40
Output
$21.8416–$22.00
Llama 3.1 405B Instruct
129
Input
$3.85
Output
$3.85

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text