# GPT-6.2 Astra (Reseller)

> GPT-6.2 Astra for Codex (Responses API).

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `codex/gpt-6.2-astra`
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/codex/gpt-6.2-astra
- Released: 2026-11-17
- Context: 272K tokens
- Max output: 128K tokens
- Input: text, image; output: text
- Knowledge cutoff: 2026-05-18

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.80–$1.60 | per 1M tokens |
| Output | $4.00–$6.00 | per 1M tokens |
| Cache read | $0.04–$0.08 | per 1M tokens |
| Cache write (5 min) | $1.00–$2.00 | per 1M tokens |
| Cache write (1 hour) | $2.00–$4.00 | per 1M tokens |
| Web search | $0.001 | per request |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:codex/gpt-6.2-astra`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| OhMyGPT (coding agents) | `omg:codex/gpt-6.2-astra` | — | $0.80–$1.60 | $4.00–$6.00 | — |

## Endpoints

| API | Request | model |
| --- | --- | --- |
| OpenAI Chat | POST https://api.ohmygpt.com/v1/chat/completions | `codex/gpt-6.2-astra` |
| OpenAI Responses | POST https://api.ohmygpt.com/v1/responses | `codex/gpt-6.2-astra` |
| Anthropic Messages | POST https://api.ohmygpt.com/v1/messages | `codex/gpt-6.2-astra` |
| Google Gemini | POST https://api.ohmygpt.com/v1/models/codex/gpt-6.2-astra:generateContent | `codex/gpt-6.2-astra` |

## Example

```bash
curl https://api.ohmygpt.com/v1/responses \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "codex/gpt-6.2-astra",
    "input": "Hello"
  }'
```

Web page: https://www.ohmygpt.com/models/codex/gpt-6.2-astra
