{"object":"list","data":[{"id":"GLM-5.2","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GLM-5.2","parent":null,"pricing":{"prompt":"0.0000014","completion":"0.0000044","cache_read":"0.00000026","off_peak":{"prompt":"0.00000126","completion":"0.00000396","cache_read":"0.000000234","discount_percent":10,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":262144,"max_output_tokens":128000,"quota_multiplier":2,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","low"]}},{"id":"GLM-5.3","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GLM-5.3","parent":null,"pricing":{"prompt":"0.0000014","completion":"0.0000044","cache_read":"0.00000026","off_peak":{"prompt":"0.00000126","completion":"0.00000396","cache_read":"0.000000234","discount_percent":10,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":128000,"quota_multiplier":10,"quota_multiplier_peak":20,"quota_peak_window_utc":{"start_hour":6,"end_hour":10},"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":2},"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"GLM-5.3-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GLM-5.3-Flash","parent":null,"pricing":{"prompt":"0.00000015","completion":"0.0000005","cache_read":"0.00000003","off_peak":{"prompt":"0.000000135","completion":"0.00000045","cache_read":"0.000000027","discount_percent":10,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":128000,"quota_multiplier":2,"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":1.5},"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"]},"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"description":"The first natively multimodal model in the GLM-5 series. 320B total parameters, 18B active. Outperforms GLM-5.2 at one-tenth the price on benchmarks and real-world workloads, with a 1M-token context window and native text, image, and video input.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"DeepSeek-V4-Flash-0731","object":"model","created":0,"owned_by":"openference","permission":[],"root":"DeepSeek-V4-Flash-0731","parent":null,"pricing":{"prompt":"0.00000044","completion":"0.00000132","cache_read":"0.000000044","off_peak":{"prompt":"0.00000022","completion":"0.00000066","cache_read":"0.000000022","discount_percent":50,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":384000,"quota_multiplier":1.7,"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":1.4705882352941178},"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"description":"DeepSeek V4 Flash — 1M context, vision input, tool calls, and thinking mode.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"MiniMax M3","object":"model","created":0,"owned_by":"openference","permission":[],"root":"MiniMax M3","parent":null,"pricing":{"prompt":"0.0000003","completion":"0.0000012","cache_read":"0.00000006","off_peak":{"prompt":"0.00000003","completion":"0.00000012","cache_read":"0.000000006","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":131072,"quota_multiplier":0.1,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"quantization":"FP8","reasoning":{"supported":true,"control":"adaptive"}},{"id":"SenseNova 6.8 Flash-Lite","object":"model","created":0,"owned_by":"openference","permission":[],"root":"SenseNova 6.8 Flash-Lite","parent":null,"pricing":{"prompt":"0.0000007","completion":"0.0000042"},"context_length":262144,"max_output_tokens":65536,"quota_multiplier":0.5,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"description":"Lightweight multimodal agent model for real-world workflows and image understanding.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","medium","low"]}},{"id":"DeepSeek-V4.1-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"DeepSeek-V4.1-Flash","parent":null,"pricing":{"prompt":"0.0000003","completion":"0.0000012","cache_read":"0.000000006","off_peak":{"prompt":"0.00000015","completion":"0.0000006","cache_read":"0.000000003","discount_percent":50,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":384000,"quota_multiplier":2,"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":1.5},"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"display_name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash — official on-demand model with scheduled peak and off-peak pricing.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"DeepSeek-V4.1-Flash-1017","object":"model","created":0,"owned_by":"openference","permission":[],"root":"DeepSeek-V4.1-Flash-1017","parent":null,"pricing":{"prompt":"0.0000003","completion":"0.0000012","cache_read":"0.000000006","off_peak":{"prompt":"0.00000015","completion":"0.0000006","cache_read":"0.000000003","discount_percent":50,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":384000,"quota_multiplier":2,"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":1.5},"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"display_name":"DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 snapshot with scheduled peak and off-peak pricing.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"DeepSeek-V4-Pro-0813","object":"model","created":0,"owned_by":"openference","permission":[],"root":"DeepSeek-V4-Pro-0813","parent":null,"pricing":{"prompt":"0.00000132","completion":"0.00000396","cache_read":"0.000000132","off_peak":{"prompt":"0.00000066","completion":"0.00000198","cache_read":"0.000000066","discount_percent":50,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":655360,"max_output_tokens":384000,"quota_multiplier":10,"quota_context_surcharge":{"threshold_input_tokens":262144,"factor":2},"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"display_name":"DeepSeek V4 Pro","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high"]}},{"id":"GLM-5.1","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GLM-5.1","parent":null,"pricing":{"prompt":"0.0000014","completion":"0.0000044","cache_read":"0.00000026","off_peak":{"prompt":"0.00000126","completion":"0.00000396","cache_read":"0.000000234","discount_percent":10,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":202752,"max_output_tokens":128000,"quota_multiplier":2,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"BF16","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","medium","low"]}},{"id":"Kimi K3","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Kimi K3","parent":null,"pricing":{"prompt":"0.000003","completion":"0.000015","cache_read":"0.0000003","off_peak":{"prompt":"0.0000027","completion":"0.0000135","cache_read":"0.00000027","discount_percent":10,"windows_utc":[{"start_hour":14,"end_hour":24}]}},"context_length":1048576,"max_output_tokens":131072,"quota_multiplier":7,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["max","high","low"]}},{"id":"GLM-4.7-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GLM-4.7-Flash","parent":null,"pricing":{"prompt":"0.00000006","completion":"0.0000004"},"context_length":131072,"max_output_tokens":128000,"quota_multiplier":0.1,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","medium","low"]}},{"id":"Qwen3.8 27b","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Qwen3.8 27b","parent":null,"pricing":{"prompt":"0.00000045","completion":"0.0000032","off_peak":{"prompt":"0.000000045","completion":"0.00000032","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":262144,"max_output_tokens":65536,"quota_multiplier":0.1,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["xhigh","medium","low"]}},{"id":"Agnes-3.0-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Agnes-3.0-Flash","parent":null,"pricing":{"prompt":"0.00000005","completion":"0.00000015"},"context_length":524288,"quota_multiplier":1.7,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"description":"512K-context text and vision-language model with coding, tool calling, reasoning, and agent workflows."},{"id":"Agnes-Image-2.5-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Agnes-Image-2.5-Flash","parent":null,"pricing":{"prompt":"0","completion":"0.000003"},"context_length":4096,"quota_multiplier":25,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"]},"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"description":"Latest-generation text-to-image and image editing. Set size to a tier (1K–4K) and ratio (e.g. 16:9) for predictable output dimensions. Costs 25 plan requests per image."},{"id":"Agnes-Video-2.5-Flash","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Agnes-Video-2.5-Flash","parent":null,"pricing":{"prompt":"0","completion":"0.000000025"},"context_length":4096,"quota_multiplier":0.1,"architecture":{"modality":"text->video","input_modalities":["text"],"output_modalities":["video"]},"input_modalities":["text"],"output_modalities":["video"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"description":"Text-to-video and image-reference video generation via OpenAI Videos-compatible API."},{"id":"Llama 3.2 3B","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Llama 3.2 3B","parent":null,"pricing":{"prompt":"0.000000051","completion":"0.000000335","off_peak":{"prompt":"0.0000000051","completion":"0.0000000335","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":131072,"quota_multiplier":0.1,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"FP8"},{"id":"Gemma 4 26B","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Gemma 4 26B","parent":null,"pricing":{"prompt":"0.0000001","completion":"0.0000003","off_peak":{"prompt":"0.00000001","completion":"0.00000003","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":256000,"quota_multiplier":0.1,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"quantization":"FP8"},{"id":"Nemotron-3-120B","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Nemotron-3-120B","parent":null,"pricing":{"prompt":"0.0000005","completion":"0.0000015","off_peak":{"prompt":"0.00000005","completion":"0.00000015","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":256000,"max_output_tokens":131072,"quota_multiplier":0.1,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","medium","low"]}},{"id":"GPT-OSS-120B","object":"model","created":0,"owned_by":"openference","permission":[],"root":"GPT-OSS-120B","parent":null,"pricing":{"prompt":"0.00000035","completion":"0.00000075","off_peak":{"prompt":"0.000000035","completion":"0.000000075","discount_percent":90,"windows_utc":[{"start_hour":0,"end_hour":24}]}},"context_length":131072,"quota_multiplier":0.1,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"display_name":"GPT-OSS 120B","description":"OpenAI open-weight 120B model for high reasoning, agentic tasks, and production use.","quantization":"FP8","reasoning":{"supported":true,"control":"effort","supported_efforts":["high","medium","low"]}},{"id":"MiMo-V2.6-Pro","object":"model","created":0,"owned_by":"openference","permission":[],"root":"MiMo-V2.6-Pro","parent":null,"pricing":{"prompt":"0.000000435","completion":"0.00000087","cache_read":"0.0000000036"},"context_length":1048576,"max_output_tokens":131072,"quota_multiplier":2,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":true,"attachment":true},"description":"MiMo V2.6 Pro — 1M context, vision, tools, deep thinking, and streaming.","quantization":"BF16","reasoning":{"supported":true,"control":"toggle"}},{"id":"Auto","object":"model","created":0,"owned_by":"openference","permission":[],"root":"Auto","parent":null,"pricing":{"prompt":"0.0000003675","completion":"0.000001"},"context_length":131072,"max_output_tokens":131072,"quota_multiplier":1,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tool_calling":true,"vision":false,"attachment":false},"description":"Automatically selects the optimal model based on performance and speed.","reasoning":{"supported":true,"control":"toggle"}}]}