{"name":"hyperfusion","display_name":"Hyperfusion","description":"DeepSeek, Qwen and MiniMax open-weight inference on GPUs domiciled in the UAE — inference and data stay in-country, without an API key or credit card. Pay per request in USDC or EURC on any of 7 chains. OpenAI-compatible chat completions; the model is required.","type":"simple-inference","persona":"","tools":"/tools","operations":["chat_completions"],"services":[{"endpoint":"/v1/chat/completions","method":"POST","description":"OpenAI-compatible chat completions over DeepSeek V4 Flash, Qwen3.8-27B or MiniMax M2.7. The model is required. Price is a flat amount in one of two bands (prompt under or over ~4,000 estimated tokens), set by the model; there is no peak-hour surcharge. Additional OpenAI parameters (temperature, max_tokens, top_p, frequency_penalty, presence_penalty, stop, etc.) are forwarded. The optional metered (`upto`) accept authorizes the prompt plus your `max_tokens` as a ceiling and settles the measured input and output tokens. Streaming is not supported on the paid route.","price":"0.00875","asset":"USDC","network":"base"},{"endpoint":"/v1/models","method":"GET","description":"List the three served models","price":"0","asset":"USDC","network":"base"},{"endpoint":"/hyperfusion/feedback","method":"GET","description":"Return the 50 most recent feedback entries","price":"0","asset":"USDC","network":"base"},{"endpoint":"/hyperfusion/feedback","method":"POST","description":"Submit feedback (response_id, rating 1-5, optional comment)","price":"0","asset":"USDC","network":"base"}],"pricing":{"/v1/chat/completions":{"Base USDC/EURC":"$0.00875","Arbitrum USDC":"$0.0075","Polygon USDC":"$0.00625","Avalanche USDC":"$0.0025","Ethereum USDC":"$3.75","Robinhood USDG":"$0.00875","Arc USDC":"$0.00875"}}}