{"data":{"id":"thinkingmachines/inkling-2-small","name":"Inkling 2 Small","created":1755815280,"released":1794441600,"description":"Inkling 2 Small is Thinking Machines Lab’s second-generation multimodal Mixture-of-Experts model, with 594 billion total parameters and 17 billion active per token. It combines text and image understanding with controllable reasoning for coding, tool use, and professional knowledge work.","architecture":{"tokenizer":null,"instruct_type":null,"modality":"text+image→text","input_modalities":["text","image"],"output_modalities":["text"]},"reasoning":{"mandatory":false,"supported_efforts":["none","low","medium","high"]},"endpoints":[{"name":"modal | thinkingmachines/inkling-2-small","model_name":"Inkling 2 Small","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.000001","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","discount":0},"provider_name":"modal","has_zdr":true,"has_no_training":true,"headquarters_country":"US","tags":["implicit-caching","reasoning","tool-use","vision","open-weights"],"quantization":null,"max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":94.8805,"latency_last_1h":{"p50":493,"p95":575.0999999999999},"throughput_last_1h":{"p50":64,"p95":105.84999999999998},"supports_implicit_caching":true},{"name":"nebius | thinkingmachines/inkling-2-small","model_name":"Inkling 2 Small","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.000001","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000006","discount":0},"provider_name":"nebius","has_zdr":true,"has_no_training":true,"headquarters_country":"NL","tags":["implicit-caching","reasoning","structured-output","tool-use","vision","open-weights"],"quantization":null,"max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":97.6311,"latency_last_1h":{"p50":407,"p95":8882.599999999997},"throughput_last_1h":{"p50":93,"p95":160.5},"supports_implicit_caching":true},{"name":"togetherai | thinkingmachines/inkling-2-small","model_name":"Inkling 2 Small","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.000001","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","discount":0},"provider_name":"togetherai","has_zdr":true,"has_no_training":true,"headquarters_country":"US","tags":["implicit-caching","reasoning","structured-output","tool-use","vision","open-weights"],"quantization":null,"max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":99.9034,"latency_last_1h":{"p50":24681,"p95":48476.5},"throughput_last_1h":{"p50":20,"p95":23.599999999999998},"supports_implicit_caching":true}]}}