{"data":{"id":"thinkingmachines/inkling-small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | thinkingmachines/inkling-small-20260730","model_id":"thinkingmachines/inkling-small","model_name":"Thinking Machines: Inkling Small","context_length":524288,"pricing":{"prompt":"0.00000045","completion":"0.0000012","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","service_tier":null,"quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":-5,"uptime_last_30m":80,"uptime_last_5m":100,"uptime_last_1d":99.05511811023622,"supports_implicit_caching":true,"native_tools":{},"supports_voice_cloning":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}