{"object":"list","data":[{"canonical_slug":"qwen/qwen3.5-35b-a3b","supported_parameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","logit_bias","logprobs","top_logprobs","seed","response_format","structured_outputs","stop","tools","tool_choice","parallel_tool_calls","include_reasoning","reasoning_effort","max_completion_tokens","n"],"default_parameters":{},"name":"Qwen3.5 35B A3B","description":"Mixture-of-experts text and vision-language model for coding, agentic tasks, and multimodal reasoning.","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"context_length":262144,"is_moderated":false},"id":"qwen/qwen3.5-35b-a3b","object":"model","created":1789948800,"owned_by":"sprag"},{"canonical_slug":"rhythm","supported_parameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","response_format"],"default_parameters":{},"name":"Rhythm","description":"Sprag's speech recognition model for multilingual speech-to-text transcription.","context_length":32768,"architecture":{"modality":"audio->text","input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"context_length":32768,"is_moderated":false},"id":"rhythm","object":"model","created":1785456000,"owned_by":"sprag"},{"canonical_slug":"spev","supported_parameters":["input_audio","input_image","input_video"],"default_parameters":{},"name":"SPEV Decisions","description":"Evaluate predicate, choice and score questions over shared text, native audio, one inline image or visual video frames. Returns ordered typed answers, probabilities and token usage.","context_length":8192,"architecture":{"modality":"text+audio+image+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"context_length":8192,"is_moderated":false},"id":"spev","object":"model","created":1791331200,"owned_by":"sprag"},{"canonical_slug":"symphony","supported_parameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","logit_bias","seed","response_format","structured_outputs","stop","tools","tool_choice","parallel_tool_calls","include_reasoning","reasoning_effort","source_languages","target_language","max_completion_tokens","n"],"default_parameters":{"temperature":0.7,"top_p":1.0,"top_k":0,"frequency_penalty":0.0,"presence_penalty":0.0,"repetition_penalty":1.0,"modalities":["text"]},"name":"Symphony","description":"Sprag's flagship multimodal model: text, image, audio, and video in; text and speech out, with tool calling.","context_length":65536,"architecture":{"modality":"text+image+audio+video->text+audio","input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"],"tokenizer":"Qwen3"},"top_provider":{"context_length":65536,"is_moderated":false},"id":"symphony","object":"model","created":1785456000,"owned_by":"sprag"},{"canonical_slug":"chorus","supported_parameters":["response_format","language","voice","speed","stream_format","ref_audio","ref_text"],"default_parameters":{},"name":"Chorus","description":"Text-to-speech model that speaks in a built-in voice, a voice cloned from reference audio, or a voice designed from a description.","context_length":4096,"architecture":{"modality":"text->audio","input_modalities":["text","audio"],"output_modalities":["audio"],"tokenizer":"Qwen3"},"top_provider":{"context_length":4096,"is_moderated":false},"id":"chorus","object":"model","created":1785456000,"owned_by":"sprag"}]}