{"input_schema":{"type":"object","properties":{"model":{"type":"string","description":"Preferred free model. The supplier may substitute another free model; output.model identifies the model that answered.","enum":["nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","nvidia/nemotron-3.5-lightning","nvidia/llama-3.2-11b-vision","nvidia/nemotron-3-ultra-550b","cohere/north-mini-code","poolside/laguna-xs-2.1","nvidia/muse-glimmer-30b"],"default":"nvidia/nemotron-3.5-lightning","examples":["nvidia/nemotron-3.5-lightning"]},"messages":{"type":"array","description":"Nonempty text chat messages with system, user or assistant roles.","examples":[[{"role":"user","content":"Return only OK."}]]},"max_tokens":{"type":"integer","description":"Maximum generated tokens.","default":256,"examples":[256],"minimum":1,"maximum":16384}},"required":["messages"],"additionalProperties":true,"examples":[{"messages":[{"role":"user","content":"Return only OK."}]}]},"output_schema":{"type":"object","description":"Public supplier JSON; top-level arrays are returned under data.","additionalProperties":true},"addons_schema":{"type":"object","additionalProperties":false},"capability_id":null,"session_compatible":false,"pricing_available":true,"id":"blockrun/free-chat","object":"endpoint","provider":"blockrun","endpoint":"free-chat","name":"Free model inference","summary":"Generate text using a shared pool of free models. Availability and the actual answering model vary; this does not guarantee the preferred model.","description":"Generate text using a shared pool of free models. Availability and the actual answering model vary; this does not guarantee the preferred model. Source: https://blockrun.ai/free. Upstream is public and requires no API key; Gateway access requires your gateway key. Standard list price: $0.01 per successful call. Supplier rate limits apply.","unit":"call","price_per_unit":"0.01","list_price_per_unit":"0.01","reports_cost":false,"input_fields":[{"name":"model","type":"string","required":false,"description":"Preferred free model. The supplier may substitute another free model; output.model identifies the model that answered.","example":"nvidia/nemotron-3.5-lightning","default":"nvidia/nemotron-3.5-lightning","enum_values":["nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","nvidia/nemotron-3.5-lightning","nvidia/llama-3.2-11b-vision","nvidia/nemotron-3-ultra-550b","cohere/north-mini-code","poolside/laguna-xs-2.1","nvidia/muse-glimmer-30b"]},{"name":"messages","type":"array","required":true,"description":"Nonempty text chat messages with system, user or assistant roles.","example":[{"role":"user","content":"Return only OK."}]},{"name":"max_tokens","type":"integer","required":false,"description":"Maximum generated tokens.","example":256,"default":256,"min":1,"max":16384}],"example_request":{"provider":"blockrun","endpoint":"free-chat","input":{"messages":[{"role":"user","content":"Return only OK."}]}},"output":"Public supplier JSON; top-level arrays are returned under data.","limits":{"request_bytes":1000000,"timeout_ms":120000,"input_characters":null,"audio_bytes":null}}