Overview
Model specifications
- Context
- 2,000,000 tokens
- Maximum output
- Not provided
- Architecture
- text+image+file+audio+video->text+image
- Tokenizer
- Router
- Knowledge cutoff
- Not provided
- Moderated
- No
OPENROUTER
Variable pricing
The routed model determines the charge. A missing fixed rate does not mean the request is free.
API
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openrouter/auto-beta","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
textimageaudiofilevideo
Output
textimage
API
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppredictionpresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_pweb_search_optionsAvailable providers
0 providers
Checked: September 19, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
No endpoint details were provided at the last synchronization.