Supported Models and ParametersText Models
Text Models
Review shared text-model fields and open the single-model page for exact guidance.
Text models are different from image and video task models. They usually return text generation results directly instead of relying on async task polling.
The following CodexReverse text models are confirmed public in the live configuration. Actual availability, region, API-key access, and pricing always follow GET /v1/models.
Shared Text Fields
| Field | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Target text model ID |
input | string | Yes | User input content |
messages | array | Yes (Chat) | Multi-turn system, user, and assistant messages |
instructions | string | No (Responses) | System-level instructions for Responses |
stream | boolean | No | Whether to stream the response |
reasoning | object | No | Reasoning configuration, for example {\"effort\":\"high\"} |
Current Text Models
| Model | Region | Best For | Details |
|---|---|---|---|
gpt_5_4 | Live config | General text generation | Public |
gpt_5_5 | Live config | General text generation | Public |
gpt_5_6_luna | Live config | Text generation | Public |
gpt_5_6_sol | Live config | Text generation | Public |
gpt_5_6_terra | Live config | Text generation | Public |
Why This Section Exists Now
- Text models support system instructions, multi-turn history, streaming, and reasoning; image, video, and audio inputs are not supported.
- Use
messages[].role = systemfor Chat Completions and top-levelinstructionsfor Responses. Do not send a customsystemPromptfield. - Use
/v1/chat/completionsor/v1/responsesfor text models, not the media/v1/generationsendpoint.