OpenAI: GPT-6 Astra (batch)
openai/gpt-6-astra-batchGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
Modalities
In / out per 1M$5.00 / $25
Context1M
ReleasedSep 4, 2026
Providers
8 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Azureeastus2 | $11 | $55 | $1.10 | 2.70s | 37 tps | 100% |
 OpenAI | $20 | $100 | $2.00 | 2.05s | 60 tps | 100% |
| Azure | $10 | $50 | $1.00 | 7.23s | 36 tps | 99.97% |
| OpenAI | $5.00 | $25 | $0.50 | 2.77s | 39 tps | 99.83% |
| OpenAI | $60 | $300 | $6.00 | 3.10s | 116 tps | 99.64% |
| OpenAI | $10 | $50 | $1.00 | 7.05s | 65 tps | 98.76% |
 Amazon Bedrockus-east-2 | $10 | $50 | $1.00 | 16.03s | 57 tps | 95.73% |
| Amazon Bedrockus-west-2 | $11 | $55 | $1.10 | — | — | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GPT-6 Astra (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GPT-6 Astra (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$5.00
per 1M tokens
Output
$25
per 1M tokens
Cache read
$0.50
per 1M cached tokens
Included in every pass
GPT-6 Astra (batch) is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
OpenAI OpenAI Azure (eastus2) Azure OpenAI OpenAI Amazon Bedrock (us-west-2) Amazon Bedrock (us-east-2)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
OpenAI OpenAI Azure OpenAI OpenAI Azure (eastus2) Amazon Bedrock (us-west-2) Amazon Bedrock (us-east-2)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 98.63%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.32%
100% 97% 93% 90%
Oct 31, 6:10 PMNow
Apps
Tools that most often run GPT-6 Astra (batch), by tokens this week.
Activity
2476.1B tokens processed market-wide in the last month.
0200.0B400.0B600.0B800.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for GPT-6 Astra (batch)?
openai/gpt-6-astra:batch. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does GPT-6 Astra (batch) hold?
1,050,000 tokens per request, of which up to 128,000 can be the response.
What can it accept and return?
Input: file, image, text. Output: text.
What does GPT-6 Astra (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $5.00 per 1M input tokens and $25 per 1M output tokens.
Who built GPT-6 Astra (batch)?
OpenAI, in the GPT family.
Explore
Other models your pass can call.
