GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger visual reasoning for websites, slideshows and 3D designs. OpenAI reports new highs on its evals at less than a third of the cost per task of GPT-6 Astra.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $8.00 | $40.00 | $0.40 | 3.44s | 65 tok/s | ||
| $8.00 | $40.00 | $0.40 | 2.18s | 56 tok/s | ||
| $8.00 | $40.00 | $0.40 | 3.34s | 38 tok/s | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $8.80 | $44.00 | $0.44 | 1.43s | 64 tok/s | ||
| $8.80 | $44.00 | $0.44 | -- | -- | ||
| $9.60 | $48.00 | $0.48 | 2.03s | 68 tok/s | ||
Fast | $16.00 | $80.00 | $0.80 | 3.36s | 48 tok/s | |
Ultrafast | $24.00 | $120.00 | $1.20 | 0.75s | 59 tok/s | |
- Input $8.00 / Output $40.0065 tok/s100.00% uptime
- Input $8.00 / Output $40.0056 tok/s100.00% uptime
- Input $8.00 / Output $40.0038 tok/s100.00% uptime
- Not used in Standard routing:Why these endpoints are not used
- Input $8.80 / Output $44.0064 tok/s100.00% uptime
- Input $8.80 / Output $44.00-- tok/s-- uptime
- Input $9.60 / Output $48.0068 tok/s100.00% uptime
- Input $16.00 / Output $80.0048 tok/s100.00% uptimeFast
- Input $24.00 / Output $120.0059 tok/s100.00% uptimeUltrafast
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
GPT-6.2 Astra — Price history
| $1.19 | $40.12 | 92.7% | 27.8% | ||
| $1.56 | $40.22 | 89.2% | 59.3% | ||
| $2.10 | $40.03 | 83.2% | 9.1% | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $1.03 | $44.00 | 94.3% | 0.3% | ||
| $1.90 | $48.00 | 87.6% | 0.3% | ||
Fast | $2.99 | $86.55 | 93.3% | 3.1% | |
| $10.99 | $44.00 | 0.0% | 0.0% | ||
Ultrafast | $12.47 | $120.00 | 59.8% | 0.0% | |
- Effective in $1.19 / Effective out $40.12Token share27.8%
- Effective in $1.56 / Effective out $40.22Token share59.3%
- Effective in $2.10 / Effective out $40.03Token share9.1%
- Not used in Standard routing:Why these endpoints are not used
- Effective in $1.03 / Effective out $44.00Token share0.3%
- Effective in $1.90 / Effective out $48.00Token share0.3%
- Effective in $2.99 / Effective out $86.55FastToken share3.1%
- Effective in $10.99 / Effective out $44.00Token share0.0%
- Effective in $12.47 / Effective out $120.00UltrafastToken share0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
P50, best across providers
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Available through EU in-region routing
OpenAI: GPT-6.2 Astra is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
- Providers in Europe
- Azure
- Prices in Europe
- Azure: $9.60/M tokens input, $48/M tokens output
- Base URL
https://eu.openrouter.ai/api/v1- Plan
- Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Frequently asked questions
GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger visual reasoning for websites, slideshows and 3D designs. OpenAI reports new highs on its evals at less than a third of the cost per task of GPT-6 Astra.
GPT-6.2 Astra costs $8.00/M input tokens and $40.00/M output tokens, with separate rates for Cache Read at $0.40/M tokens, Cache Write at $10.00/M tokens, and Web Search at $10.00/1K calls.
GPT-6.2 Astra has a 1,050,000 token context window. It supports up to 128,000 completion tokens.
Yes. GPT-6.2 Astra accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6.2 Astra bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.
GPT-6.2 Astra accepts files such as PDFs, images, and text as input and returns text.
GPT-6.2 Astra is served by 3 providers on OpenRouter: OpenAI, Azure, and Amazon Bedrock. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
GPT-6.2 Astra was released on November 17, 2026.