YeeHooDevelopers
Developer Docs
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

FieldTypeRequiredDescription
modelstringYesTarget text model ID
inputstringYesUser input content
messagesarrayYes (Chat)Multi-turn system, user, and assistant messages
instructionsstringNo (Responses)System-level instructions for Responses
streambooleanNoWhether to stream the response
reasoningobjectNoReasoning configuration, for example {\"effort\":\"high\"}

Current Text Models

ModelRegionBest ForDetails
gpt_5_4Live configGeneral text generationPublic
gpt_5_5Live configGeneral text generationPublic
gpt_5_6_lunaLive configText generationPublic
gpt_5_6_solLive configText generationPublic
gpt_5_6_terraLive configText generationPublic

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 = system for Chat Completions and top-level instructions for Responses. Do not send a custom systemPrompt field.
  • Use /v1/chat/completions or /v1/responses for text models, not the media /v1/generations endpoint.

Read Next