GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
Context
1.1Mtokens
About 1,500 pages of text at once
Max output
128Ktokens
About 183 pages in one answer
Intelligence
56.9/ 100
Above 89% of the catalogue
Output speed
44tokens/s
A 500-word answer in about 15.9 s
From public market statistics for this model
First token
4.2s
Reasoning models start later
From public market statistics for this model
Health, 30 days
85.82%
14 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 27,399,875 | IRR / 1M tokens |
|---|---|---|
| Output | 136,999,375 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 136,999,375 | IRR / 1M tokens |
| Cache read | 2,739,988 | IRR / 1M tokens |
| Cache write, 5 minutes | 34,249,844 | IRR / 1M tokens |
| Image input tokensThe input rate | 27,399,875 | IRR / 1M tokens |
| Per web search | 27,400 | IRR |
Under these conditions, these rates replace the ones above:
Prompts over 272K tokens
| Input | 54,799,750 | IRR / 1M tokens |
|---|---|---|
| Output | 205,499,063 | IRR / 1M tokens |
| Cache read | 5,479,975 | IRR / 1M tokens |
| Cache write, 5 minutes | 68,499,688 | IRR / 1M tokens |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
4.93BIRR
164.4M IRR a day, 82K IRR each request
The same work on peer models
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health85.82%
Time to first token4.43 s
Output speed44 tokens/s
Place in the market
By usage across the global model market.
Daily rank#42
Share of the day’s tokens0.3%
Among its peers
Cost of one message against intelligence; this model is highlighted.
Cost of one message, IRR (log scale)
Capabilities
- Input
- FileImageText
- Output
- Text
Parameters it accepts
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosityOther benchmarks
Standard tests
- GPQA DiamondScore: 94%Tasks: 198
- τ-bench Verified AirlineScore: 68%Tasks: 50
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="openai/gpt-6-astra", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
| Model | Against this model | ||||
|---|---|---|---|---|---|
| Anthropic: Claude Opus 5.5Anthropic | 49,338 | 58.4 | 79 | 1M | 60% cheaper |
| Qwen: Qwen3.8 MaxQwen | 19,187 | 53.4 | — | 1M | 84% cheaper |
Technical specs
- ID
openai/gpt-6-astra- Maker
- OpenAI
- Tokenizer
- GPT
- Released
- Sep 4, 2026
- Added to IranRouter
- Sep 5, 2026
- Context
- 1,050,000 tokens
- Max output
- 128,000 tokens
Scores by Artificial Analysis, as of Oct 31, 2026