Overall · Snapshot captured:
- Artificial Analysis Intelligence Index
- 52.7
- Coding Index
- 76.9
- Agentic Index
- 51
Back to models
Artificial Analysis
GPT-6 Astra
FeaturedZDRAzure•
GPT-6 Astra is OpenAI's frontier flagship model for complex multistep engineering and agentic workflows, featuring state-of-the-art reasoning, vision, async tool calling, a 1.05M-token context window, and up to 128K output tokens. Available through the DOS.AI gateway with unified billing and OpenAI compatibility.
Capabilities:Next-gen reasoningVisionTool callingCode generationAgentic workflowsLong context (1.05M)
Modalities
Text input tokens
Image input
Text generation tokens
Input / Output Price
$9.50/$47.50/ 1M
Context Length
1M tokens
Released
Sep 19, 2026
Providers
Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick - Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
Reasoning effortⓘAll
| Provider | Input /1M | Output /1M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
AzureSale off 5% | 9.85 s | - | 100.0% | |||
OpenAI | $10.00 | $50.00 | $1.00 | - | - | - |
Pricing
Rates from the DOS.AI catalog for the billing units shown. Caching and provider discounts mean the price actually paid is often below the listed one.
Weighted Averagei
Weighted Avg Input Price
$9.04/ 1M tokens
-$0.71 /M compared to average list price
Weighted Avg Output Price
$50.109/ 1M tokens
Equal to list price
Cache read
$0.95/ 1M tokens
Rate for cached input tokens
Price History2 verified endpoints
Weighted Average($9.04)
Provider↕ | Effective in /M↕ | Effective out /M↕ | Cache read /M↕ | Latency↕ | Throughput↕ | Uptime↕ | Savings↕ |
|---|---|---|---|---|---|---|---|
Azure | $9.50$5.75 | $47.50 | $0.95 | 9.85 s | - | 100.0% | -39% |
OpenAI | $14.58 | $55.39 | $1.00 | - | - | - | - |
Based on settled billing for the last 30d.Effective pricing represents the average price paid for requests to this endpoint, factoring in caching, discounts, and tiered pricing. Listed pricing shows the posted provider list prices.
Observed performance
Provider results (Last 7 days).
Updated Oct 16, 07:25 AM UTC
ProviderUptimeP50 responseP95 responseLatency spreadSamples
Azure
894 samples
100.0%
9.85 s
125.23 s
894
Azure
894 samples
- Uptime
- 100.0%
- P50 response
- 9.85 s
- P95 response
- 125.23 s
- Latency spread
Uptime is based on observed valid provider attempts. Not a contractual guarantee.
Latency is measured to provider response headers, not end-to-end completion.
Observed reliability
Success rate across observed provider requests. This is historical sample data, not live health or an uptime guarantee.
Request observations
Last 7 days
- Observed success rate
- 100.00%
- Observed requests
- 894
Benchmarks
Dated third-party measurements with source links.
Observed gateway latency
Window: 7d
- Lowest provider median TTFT
- -
- Lowest provider median latency
- 9.85 s
- Lowest provider P95 latency
- 125.23 s
- Providers with latency samples
- 1
API Integration
Use the DOS API to integrate GPT-6 Astra into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.
</>Run inference
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-astra",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'