✨ GPT Image 2.6 is now available. Come and experience it!

gpt-6-astra

Hotopenai/gpt-6-astra
Capabilities
6
VisionToolsSearchThink
Context length
1.05M
Tokens
Max output tokens
128K
Tokens
Type
Chat
OpenAI
Release date
2026-08-27
Model brand

Playground

Up to 50 messages are kept on this page; only the last 10 are sent as context, and refreshing clears them

Pricing

Pricing breakdown
Usage-based pricing, broken down by billing item at your current rates.
20% off

Input tokens

2 price tiers

Total prompt tokens (including cache) ≤ 272,000
10 credits / 1M8 credits / 1M
All other cases
20 credits / 1M16 credits / 1M

Output tokens

2 price tiers

Total prompt tokens (including cache) ≤ 272,000
50 credits / 1M40 credits / 1M
All other cases
75 credits / 1M60 credits / 1M

Cache read tokens

2 price tiers

Total prompt tokens (including cache) ≤ 272,000
1 credits / 1M0.8 credits / 1M
All other cases
2 credits / 1M1.6 credits / 1M

Cache write tokens

2 price tiers

Total prompt tokens (including cache) ≤ 272,000
12.5 credits / 1M10 credits / 1M
All other cases
25 credits / 1M20 credits / 1M

Cache write tokens (12 hours)

2 price tiers

Total prompt tokens (including cache) ≤ 272,000
25 credits / 1M20 credits / 1M
All other cases
50 credits / 1M40 credits / 1M

Billing items are additive. Only one matching price tier applies to each item. Each request is calculated exactly from actual usage, and the total is rounded up once to the nearest 0.000001 credits.

Rate limits

Rate limits
Per-account quota for this model. Account-level limits in the console apply on top and the stricter one wins.
LimitPer accountNotes
Requests per minuteUnlimitedRefill is continuous; an idle account can send a full minute's quota at once.
Concurrent requestsUnlimitedCounts requests in flight at the same moment, per account.
Requests per dayUnlimitedNot enforced on this model.

These are the platform defaults per customer. Limits you configure for an API key or wallet also apply, and the strictest one takes effect. Exceeding a limit returns 429 with a Retry-After header; when every channel for the model is at capacity the request returns 503 instead.

API

cURL example
POST/v1/chat/completions
SynchronousOpenAI-compatible
curl "https://api.modelrover.ai/v1/chat/completions" \  -X POST \  -H "Authorization: Bearer $API_KEY" \  -H "Content-Type: application/json" \  -d '{  "model": "openai/gpt-6-astra",  "messages": [    {      "role": "user",      "content": "Explain model gateways in one sentence."    }  ]}'

Set your API_KEY environment variable before running. Keep your key server-side.

API documentation

Uptime