# GPT-6.2 Astra API Pricing

> Markdown mirror of https://router.one/models/gpt-6-2-astra for AI assistants and crawlers. Router One is a unified, OpenAI-compatible LLM API gateway.
> Rates on this page were read from the live catalog on 2026-11-19 (UTC) and refresh within the hour.

## GPT-6.2 Astra at a glance

GPT-6.2 Astra (model ID openai/gpt-6.2-astra) is a GPT-series text model on Router One. GPT-6.2 Astra is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $1.60 / 1M tokens, Output $8.00 / 1M tokens, Cache write $2.00 / 1M tokens, Cached input $0.08 / 1M tokens; request input > 272,000 tokens: Input $3.20 / 1M tokens, Output $12.00 / 1M tokens, Cache write $4.00 / 1M tokens, Cached input $0.16 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Router One subscriptions include GPT-6.2 Astra in the Flagship models allowance: Max 150, Ultra 450 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 272,000 input tokens counts as 2 requests. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path).

## Call summary

- **Model ID**: `openai/gpt-6.2-astra`
- **Pricing**: request input ≤ 272,000 tokens: Input $1.60 / 1M tokens, Output $8.00 / 1M tokens, Cache write $2.00 / 1M tokens, Cached input $0.08 / 1M tokens; request input > 272,000 tokens: Input $3.20 / 1M tokens, Output $12.00 / 1M tokens, Cache write $4.00 / 1M tokens, Cached input $0.16 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
- **Context Window**: 1.05M
- **Capabilities**: `chat` `streaming` `tool_calling` `vision`

## GPT-6.2 Astra API endpoints

One API key — call this model through any of the 2 endpoints below.

| Endpoint | Protocol | Docs |
| --- | --- | --- |
| `POST https://api.router.one/v1/chat/completions` | OpenAI-compatible · Works for every model | [Docs](https://router.one/docs/chat/createChatCompletion) |
| `POST https://api.router.one/v1/responses` | Responses API · Native for Codex CLI | [Docs](https://router.one/docs/chat/createResponse) |

### Request example: POST /v1/chat/completions

```bash
curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-6.2-astra",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
```

### Request example: POST /v1/responses

```bash
curl -X POST \
  https://api.router.one/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-6.2-astra",
    "input": "Hello!"
  }'
```

## Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

| Window | Success 2xx | Rate limit 429 | Server 5xx | Avg. time to first token | Avg. latency | TPS (tokens/s) |
| --- | --- | --- | --- | --- | --- | --- |
| Last 7 days | 99.92% | 0.00% | 0.08% | 10.86 s | 10.96 s | 70.94 |
| Last 30 days | 99.88% | 0.00% | 0.12% | 12.52 s | 8.35 s | 65.7 |

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

[All models' reliability data](https://router.one/benchmarks/model-reliability)

Updated Nov 19, 2026, 4:59 PM UTC

## GPT-6.2 Astra FAQ

### How much does GPT-6.2 Astra cost on Router One?

GPT-6.2 Astra is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $1.60 / 1M tokens, Output $8.00 / 1M tokens, Cache write $2.00 / 1M tokens, Cached input $0.08 / 1M tokens; request input > 272,000 tokens: Input $3.20 / 1M tokens, Output $12.00 / 1M tokens, Cache write $4.00 / 1M tokens, Cached input $0.16 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.

### Is GPT-6.2 Astra included in Router One subscriptions?

Router One subscriptions include GPT-6.2 Astra in the Flagship models allowance: Max 150, Ultra 450 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 272,000 input tokens counts as 2 requests.

### Which endpoints serve GPT-6.2 Astra?

GPT-6.2 Astra is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.

### What is GPT-6.2 Astra's context window?

GPT-6.2 Astra accepts up to 1.05M tokens of context per request on Router One.

## Start using GPT-6.2 Astra

Create an API key and call GPT-6.2 Astra on Router One — pay as you go, with per-request cost and latency visibility.

- [Plans & pay-as-you-go pricing](https://router.one/pricing)
- [Compare models side by side](https://router.one/models/compare)
- [Quickstart guide](https://router.one/docs/guides/quickstart)

Live HTML version: https://router.one/models/gpt-6-2-astra.
