# GPT-6.2 Astra and Sol on AnyRouter

> OpenAI's GPT-6.2 Astra and Sol, plus their Pro variants, are listed on AnyRouter with your own provider key: 1,050,000-token context, text and image input.

- Date: November 18, 2026
- Category: product
- HTML: https://anyrouter.dev/blog/gpt-6-2-astra-sol

## The GPT-6.2 series

OpenAI released [GPT-6.2 Astra and GPT-6.2 Sol](https://openai.com/index/introducing-gpt-6-2-astra-sol/) on November 17, 2026. Both are one family released on the same day, so they share this post. Each keeps its own model page.

OpenAI describes Astra as a model for demanding, end-to-end projects: it can build and revise software, operate a computer and work with documents. Sol is its model for everyday work, including coding and agents at scale. Both take text and image input and return text, with a 1,050,000-token context window (at most 922,000 input tokens) and up to 128,000 output tokens.

| Model | Input per 1M | Cached input per 1M | Output per 1M |
| --- | --- | --- | --- |
| [GPT-6.2 Astra](https://anyrouter.dev/model/openai/gpt-6.2-astra) | $8 | $0.40 | $40 |
| [GPT-6.2 Sol](https://anyrouter.dev/model/openai/gpt-6.2-sol) | $2 | $0.10 | $10 |
| [GPT-6.2 Astra Pro](https://anyrouter.dev/model/openai/gpt-6.2-astra-pro) | $8 | $0.40 | $40 |
| [GPT-6.2 Sol Pro](https://anyrouter.dev/model/openai/gpt-6.2-sol-pro) | $2 | $0.10 | $10 |

These are OpenAI's list rates. Above 272K input tokens, OpenAI doubles the input and cache rates and charges 1.5 times the output rate. The Pro rows are OpenRouter's reasoning configurations of Astra and Sol, not separate OpenAI model ids, and they use the same list rates.

## What OpenAI reports

These are OpenAI's published claims from the launch post, not AnyRouter measurements.

- Astra gains 5.2 points over GPT-6 Astra on Agents' Last Exam at under a third of the cost.
- Sol comes within 0.5 points of Astra on FrontierCode 2.0 at about one fifth of the cost, with both at max reasoning.
- Sol improves 5.3 points over GPT-6.1 Sol on GDPval v2.

## Call it on AnyRouter

All four models are listed and use your own provider key (BYOK). Astra and Sol have routes through OpenAI, Vercel AI Gateway, OpenRouter and Respan keys. The Pro rows go through an OpenRouter key. Add a key under [Dashboard, BYOK](https://anyrouter.dev/dashboard/byok); your provider bills you and AnyRouter adds no charge.

### curl

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6.2-sol",
    "messages": [{"role": "user", "content": "Summarize this diff in three bullets."}]
  }'
```

### Coding agent

```bash
anyr claude --model "openai/gpt-6.2-astra"
```
