GPT-6.2 Astra Pro is a large language model made by OpenAI, added to the catalog on 17 Nov 2026. It has a context window of 1,050,000 tokens and costs $8.00 per 1M input tokens and $40.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: reviewing supplied documents, responding to image-containing prompts and working with long text-based tasks.
Price checked ยท source: OpenRouter
What GPT-6.2 Astra Pro is
OpenAI GPT-6.2 Astra Pro is a text-output model served with its reasoning mode set to pro. It accepts text, image, and file inputs, and produces text. The provider describes it as the same underlying model as GPT-6.2 Astra, with the pro reasoning setting for complex tasks. The catalog does not specify particular file formats or image-processing features.
The model has a context length of 1,050,000 tokens and a maximum output of 128,000 tokens. The context length indicates how much material can be included in a request, while the output limit sets the maximum size of a response. These limits make it relevant to tasks that involve substantial source material or require long text responses.
Supported capabilities include tools, structured outputs, response-format controls, and reasoning. These options suit workflows that use available tools, request text in a specified structure, or involve complex prompts. The catalog does not name specific tools or schemas, so the details of those workflows may depend on the surrounding application.
With text, files, and images among its accepted inputs, the model can be considered for reviewing supplied documents, responding to image-containing prompts, and working with long text-based tasks. Its large context can help keep substantial source material together in a prompt. It is described as a text-producing model with multimodal input options and reasoning-oriented settings.
Key features
- Accepts text, image, and file inputs and produces text
- Has a context length of 1,050,000 tokens
- Supports a maximum output of 128,000 tokens
- Supports tools, structured outputs, response formats, and reasoning
Typical uses
- Reviewing supplied documents
- Responding to image-containing prompts
- Working with long text-based tasks
- Generating structured text responses
GPT-6.2 Astra Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $8.00 | $4.00 |
| Output, per 1M tokens | $40.00 | $20.00 |
| Cached input read, per 1M tokens | $0.40 | $0.20 |
| Cache write, per 1M tokens | $10.00 | $5.00 |
| Web search, per search | $0.01 | $0.01 |
| Input above 272,000 prompt tokens, per 1M | $16.00 | $8.00 |
| Output above 272,000 prompt tokens, per 1M | $60.00 | $30.00 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-6.2-astra-pro:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 17 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.016 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.232 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.320 |
| Read a 300-page contract set150,000 in / 1,500 out | $1.26 |
GPT-6.2 Astra Pro specifications
| Model id | openai/gpt-6.2-astra-pro |
|---|---|
| Version | gpt-6.2-astra-pro-20261117 |
| Context window | 1,050,000 tokensAbout 787,500 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 17 Nov 2026 |
| Input types | file, image, text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GPT-6.2 Astra Pro yet.
Compare GPT-6.2 Astra Pro
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.