LLM / Multimodal

openrouter-vision

Analyze images with vision using OpenRouter (access to many models). Input: image, question or prompt. Output: text analysis. Use for: image understanding, visual Q&A.

post/api/v1/openrouter-vision

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/openrouter-vision
  • Auth: one of:
    • API key in header x-api-key
    • OAuth 2 (client credentials, token URL https://api.muapi.ai/oauth/token)

Query parameters

webhookstring
team_idinteger nullable

Headers

x-api-keystring
x-embed-codestring nullable
x-agent-embed-codestring nullable
x-whitelabel-studiostring nullable
authorizationstring nullable

Request body

promptstring required
webhook_urlstring uri nullable
images_liststring[] required
system_promptstring nullable required
model'google/gemini-2.5-flash' | 'anthropic/claude-sonnet-4.5' | 'openai/gpt-4o' | 'qwen/qwen3-vl-235b-a22b-instruct' | 'x-ai/grok-4-fast'
reasoningboolean
temperaturenumber
max_tokensinteger nullable required

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 2 revisions of this API.