OpenAI GPT-6 Astra
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...
OpenAI GPT-6 Astra costs $10.00 per 1M input tokens and $50.00 per 1M output tokens at the standard tier, the lowest default-region price among the 3 providers SF·SIX tracks, from OpenAI. Cached input reads cost $1.00 per 1M tokens. Updated ; prices checked .
- Developer
- OpenAI
- Input modalities
- file, image, text
- Output modalities
- text
- Context tokens
- 1,050,000
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $10.00 input / $50.00 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| AzureOpenRouter | $10.00 | $50.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter | $10.00 | $50.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Amazon BedrockOpenRouter · us-west-2 region | $11.00 | $55.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AzureOpenRouter · US region | $11.00 | $55.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter · Fast tier | $20.00 | $100.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter · Ultrafast tier | $60.00 | $300.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter · Flex tier | $5.00 | $25.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
Batch and free variants
- GPT-6 Astra (batch) · from $5.00 input / $25.00 output per 1M tokens
Prices by service tier
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cheapest provider | vs standard (blended) |
|---|---|---|---|---|---|
| Standard | $10.00 | $50.00 | $1.00 | OpenAI | 100% |
| BatchBatch endpoint | $5.00 | $25.00 | $0.50 | OpenRouter (auto-routed) | 50% |
| Flex | $5.00 | $25.00 | $0.50 | OpenAI | 50% |
| Fast | $20.00 | $100.00 | $2.00 | OpenAI | 200% |
| Ultrafast | $60.00 | $300.00 | $6.00 | OpenAI | 600% |
Each tier’s cheapest endpoint. Standard is the default-region headline; flex and batch trade speed or latency for a lower price, priority and fast cost more for faster service.
Regional endpoints
| Provider and region | Input / 1M | Output / 1M |
|---|---|---|
| Amazon Bedrockus-west-2 region | $11.00 | $55.00 |
| AzureUS region | $11.00 | $55.00 |
Data-residency endpoints in a named region; they are never used as the headline while a default-region price exists.
Conditional pricing
- Prompts over 272,000 tokens: $20.00 input / $75.00 output per 1M tokens (OpenAI).
Speed by provider
| Provider and terms | Throughput | Latency | Uptime | Input / 1M |
|---|---|---|---|---|
| OpenAIUltrafast tier | 114 tok/s | 1.86 s | 100.0% | $60.00 |
| OpenAIFlex tier | 61 tok/s | 2.66 s | 100.0% | $5.00 |
| OpenAI | 39 tok/s | 3.30 s | 100.0% | $10.00 |
| Azure | 33 tok/s | 6.25 s | 100.0% | $10.00 |
| AzureUS region | 32 tok/s | 3.05 s | Not reported | $11.00 |
| OpenAIFast tier | 29 tok/s | 3.33 s | Not reported | $20.00 |
Previous 30 minutes; reported by OpenRouter. Fastest first.
Usage on OpenRouter
| UTC day | Tokens |
|---|---|
| 2026-10-10 | 82,018,558,538 |
| 2026-10-11 | 64,669,665,022 |
| 2026-10-12 | 74,150,982,234 |
| 2026-10-13 | 61,247,699,987 |
| 2026-10-14 | Not in named rows |
| 2026-10-15 | Not in named rows |
| 2026-10-16 | 61,764,770,432 |
OpenRouter rankings (CC BY 4.0), named daily rows. Most-used AI models
Benchmarks
Artificial Analysis Intelligence Index 52.7, coding index 76.9, agentic index 51.0 (Artificial Analysis via OpenRouter, CC BY 4.0; not an SF·SIX measurement).
Prediction markets
OpenAI GPT-6 Astra meets the rule for SF·SIX usage ladders. Open OpenAI GPT-6 Astra markets (Hedera testnet, test funds only) · How AI prediction markets work
Compare and estimate
Sources and method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Prices from OpenRouter; each row below links its source and observation date. Methodology and editorial policy.
Frequently asked questions
How much does OpenAI GPT-6 Astra cost per 1M tokens?
$10.00 per 1M input tokens and $50.00 per 1M output tokens at the standard tier, the lowest default-region price SF·SIX tracks, from OpenAI. The cheapest batch price is $5.00 input and $25.00 output per 1M tokens.
Which providers offer OpenAI GPT-6 Astra?
3 providers with 7 priced endpoints: Amazon Bedrock, Azure, OpenAI.
What is the context window of OpenAI GPT-6 Astra?
1,050,000 tokens; prompts over 272,000 tokens: $20.00 input / $75.00 output per 1M tokens (OpenAI).
How fast is OpenAI GPT-6 Astra?
The fastest measured endpoint is OpenAI (Ultrafast tier) at 114 tok/s, as reported by OpenRouter for the previous 30 minutes.
How much is OpenAI GPT-6 Astra used?
61,764,770,432 tokens on 2026-10-16 (UTC) through OpenRouter, per OpenRouter’s public rankings. This is OpenRouter traffic only, not all usage.
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.