# GPT-5.2 Chat

> GPT-5.2 Chat, also called Instant, is the fast, low-latency member of the GPT-5.2 family. It reads text, images and files, supports tools and structured output, and thinks only when a task needs it.

**ID**: `openai/gpt-5.2-chat`  
**Creator**: OpenAI  
**Category**: text  
**Context**: 128K tokens  
**Pricing**: $1.75 / $14.00 per 1M · billed by your provider (BYOK)  
**Released**: 2025-12-10  
**Web page**: https://anyrouter.dev/model/openai/gpt-5.2-chat

**Input modalities**: image, text  
**Output modalities**: text  

**Capabilities**: chat, streaming, vision, function-calling, structured-output

**Supported parameters**: max_completion_tokens, response_format, seed, structured_outputs, tool_choice, tools, verbosity

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-5.2-chat",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openrouter-byok | $1.75/M (list) | $14.00/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.
