{"data":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","created":1755815280,"released":1785369600,"description":"Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.","architecture":{"tokenizer":null,"instruct_type":null,"modality":"text+image+file→text","input_modalities":["text","image","file"],"output_modalities":["text"]},"reasoning":{"mandatory":false,"supported_efforts":["none","minimal","low","medium","high","xhigh","max"]},"endpoints":[{"name":"deepinfra | thinkingmachines/inkling-small","model_name":"Inkling Small","context_length":1000000,"pricing":{"prompt":"0.00000045","completion":"0.0000012","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000001","discount":0},"provider_name":"deepinfra","has_zdr":false,"has_no_training":true,"headquarters_country":"US","tags":["reasoning","tool-use","vision","file-input","implicit-caching","structured-output","open-weights"],"quantization":"fp8","max_completion_tokens":1000000,"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":99.934,"latency_last_1h":{"p50":396,"p95":490.09999999999997},"throughput_last_1h":{"p50":369,"p95":396},"supports_implicit_caching":true},{"name":"thinkingmachines | thinkingmachines/inkling-small","model_name":"Inkling Small","context_length":64000,"pricing":{"prompt":"0.0000003","completion":"0.0000012","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000006","discount":0},"provider_name":"thinkingmachines","has_zdr":false,"has_no_training":false,"headquarters_country":"US","tags":["reasoning","tool-use","vision","file-input","structured-output","open-weights"],"quantization":null,"max_completion_tokens":64000,"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":100,"latency_last_1h":{"p50":1870,"p95":1979.85},"throughput_last_1h":{"p50":272.5,"p95":311.75},"supports_implicit_caching":false}]}}