{"data":[{"schema_version":"2.4","id":"qwen38","name":"Qwen3.8 27B","hugging_face_id":"Qwen/Qwen3.8-27B","description":"Qwen3.8 27B in NVFP4 with the multi-token prediction head, served on dedicated GPUs. Full 262k context. Prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"qwen/qwen3.8-27b"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000010500"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000800"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":4000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000010500"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":32768},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000031500"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"qwen38-unc","name":"Qwen3.8 27B Uncensored","hugging_face_id":"huihui-ai/Huihui-Qwen3.8-27B-abliterated","description":"Qwen3.8 27B Uncensored, NVFP4 build with the multi-token prediction head, served on dedicated GPUs in the European Economic Area. Context up to 1M tokens, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"qwen/qwen3.8-27b-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004887"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000626"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":32000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004887"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":235929},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000021700"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"qwen38-obl","name":"Qwen3.8 27B Obliterated","hugging_face_id":"OBLITERATUS/Qwen3.8-27B-OBLITERATED","description":"Qwen3.8 27B Obliterated served as an NVFP4 Qwen3.8-27B base with the variant's weight delta applied as a LoRA adapter on dedicated GPUs in the European Economic Area. Full 512k context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"qwen/qwen3.8-27b-obliterated"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002100"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001890"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":4000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002100"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":32768},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000014700"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"qwen38-queen","name":"Qwen3.8 27B Queen","hugging_face_id":"aifeifei798/Qwen3.8-Queen-27B","description":"Qwen3.8 27B Queen served as an NVFP4 Qwen3.8-27B base with the variant's weight delta applied as a LoRA adapter on dedicated GPUs in the European Economic Area. Full 512k context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"qwen/qwen3.8-27b-queen"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000500"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":4000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":32768},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000006100"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"qwen38-fable","name":"Qwen3.8 27B Fable","hugging_face_id":"TeichAI/Qwen3.8-27B-Fable-Distill","description":"Qwen3.8 27B Fable served as an NVFP4 Qwen3.8-27B base with the variant's weight delta applied as a LoRA adapter on dedicated GPUs in the European Economic Area. Full 512k context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"qwen/qwen3.8-27b-fable"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000500"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":4000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":32768},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000006100"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"mimo-v26-flash-unc","name":"MiMo V2.6 Flash Uncensored","hugging_face_id":"dealignai/MiMo-V2.6-Flash-RL-UNCENSORED","description":"MiMo-V2.6-Flash-MOPD Uncensored (dealignai weight-level refusal removal carried over to the MOPD weights), NVFP4 experts with the DFlash speculative-decoding head, served on dedicated GPUs. 1M context, vision input, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"xiaomi/mimo-v2.6-flash-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004624"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001474"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004624"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000014999"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"mimo-v26-flash","name":"MiMo V2.6 Flash","hugging_face_id":"XiaomiMiMo/MiMo-V2.6-Flash-MOPD","description":"MiMo-V2.6-Flash-MOPD (official Xiaomi weights; the MOPD update of Flash-RL with fewer repeated tool calls in agent loops), NVFP4 experts with the DFlash speculative-decoding head, served on dedicated GPUs. 1M context, vision input, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"xiaomi/mimo-v2.6-flash"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000005000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002000"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000005000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000015000"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"mimo-v26-flash-abl","name":"MiMo V2.6 Flash Abliterated","hugging_face_id":"MorinoNushi/MiMo-V2.6-Flash-RL-Uncensored-Heretic-LoRA-GGUF","description":"MiMo-V2.6-Flash-MOPD Abliterated: the refusal direction (Heretic directional ablation) removed from the attention output projections, applied as a LoRA adapter on an NVFP4 base with the DFlash speculative-decoding head, served on dedicated GPUs. 1M context, vision input, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"xiaomi/mimo-v2.6-flash-abliterated"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000005000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002700"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000005000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000015000"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"cyberheabsy","name":"CyberHeabsy","hugging_face_id":"heabsy/CyberHeabsy","description":"CyberHeabsy is a high-performance language model purpose-built for cybersecurity, code analysis, and vulnerability research.\n\nKey Features:\n\nCybersecurity Focus: Tailored specifically for red-teaming, security auditing, reverse engineering, and advanced malware analysis.\n\nDeep Analytical Reasoning: Employs integrated, step-by-step cognitive processing to solve complex, multi-stage infrastructure challenges.\n\nTarget Audience: Security researchers, penetration testers, security engineers, and developers requiring a secure, strictly private AI assistant for advanced threat analysis.","tokenizer":"Other","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"heabsy/cyberheabsy"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000015000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002700"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000015000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000045000"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","description":"DeepSeek-V4.1-Flash, FP8, served on dedicated GPUs. 1M context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"US","hosting":"heabsy","eea_available":false,"compliance":{"zdr":true},"openrouter":{"slug":"deepseek/deepseek-v4.1-flash"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002583"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000052"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000010330"}]}],"quantization":"fp8"},{"schema_version":"2.4","id":"deepseek-v4.1-flash-unc","name":"DeepSeek V4.1 Flash Uncensored","hugging_face_id":"diffbot/DeepSeek-V4.1-Flash-EXL3-2.0bpw-2x-RTX-PRO-6000","description":"DeepSeek-V4.1-Flash Uncensored: dealignai's DeepSeek-V4.1-Flash-UNCENSORED weights with refusal removal baked into the weights (no adapter), FP8, served on dedicated GPUs. 1M context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"US","hosting":"heabsy","eea_available":false,"compliance":{"zdr":true},"openrouter":{"slug":"deepseek/deepseek-v4.1-flash-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000400"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000014000"}]}],"quantization":"fp8"},{"schema_version":"2.4","id":"glm53-flash-unc","name":"GLM 5.3 Flash Uncensored","hugging_face_id":"dealignai/GLM-5.3-Flash-UNCENSORED-FP8","description":"GLM-5.3-Flash Uncensored (dealignai weight-level refusal removal baked into the weights, no adapter), NVFP4 experts with the multi-token prediction head, served on dedicated GPUs. Full 1M context window, vision input, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"z-ai/glm-5.3-flash-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000641"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":3000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000008001"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"deepseek-v4.1-flash-cloud","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1000000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002800"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000090"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002800"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":384000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000010400"}]}]},{"schema_version":"2.4","id":"glm-5.3-flash","name":"GLM 5.3 Flash","description":"GLM 5.3 Flash served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"z-ai/glm-5.3-flash"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000375"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000006000"}]}]},{"schema_version":"2.4","id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"DeepSeek V4 Flash served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"deepseek/deepseek-v4-flash"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002800"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000042"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":384000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000005600"}]}]},{"schema_version":"2.4","id":"glm-5.3","name":"GLM 5.3","description":"GLM 5.3 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000012000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000003000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000044000"}]}]},{"schema_version":"2.4","id":"kimi-k3","name":"Kimi K3","description":"Kimi K3 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"moonshotai/kimi-k3"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000040000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000003000"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000040000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000200000"}]}]},{"schema_version":"2.4","id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"deepseek/deepseek-v4-pro"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000022000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001650"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":384000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000044000"}]}]},{"schema_version":"2.4","id":"glm-5.2","name":"GLM 5.2","description":"GLM 5.2 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"z-ai/glm-5.2"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000008400"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001170"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000026400"}]}]},{"schema_version":"2.4","id":"mimo-v2.6-pro","name":"MiMo V2.6 Pro","description":"MiMo V2.6 Pro served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"xiaomi/mimo-v2.6-pro"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000008700"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000054"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000008700"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000017400"}]}]},{"schema_version":"2.4","id":"minimax-m3","name":"MiniMax M3","description":"MiniMax M3 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"minimax/minimax-m3"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":512000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000006000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000900"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000006000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":80000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000024000"}]}]},{"schema_version":"2.4","id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen3.8 Flash served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"qwen/qwen3.8-flash"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":991808}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002800"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000240"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002800"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000008400"}]}]},{"schema_version":"2.4","id":"gpt-oss-120b","name":"GPT OSS 120B","description":"GPT OSS 120B served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-oss-120b"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":128000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000007000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000005250"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":16384}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000015000"}]}]},{"schema_version":"2.4","id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek V3.2 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"deepseek/deepseek-v3.2"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":163000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000005600"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000004200"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000008400"}]}]},{"schema_version":"2.4","id":"hy4-preview","name":"Tencent Hy4 Preview","description":"Tencent Hy4 Preview served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"tencent/hy4-preview"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000016680"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000630"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":64000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000050020"}]}]},{"schema_version":"2.4","id":"claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude Opus 5.5 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"anthropic/claude-opus-5.5"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1000000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000048000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002400"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000048000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000240000"}]}]},{"schema_version":"2.4","id":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Claude Sonnet 5.5 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"anthropic/claude-sonnet-5.5"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1000000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001200"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000120000"}]}]},{"schema_version":"2.4","id":"claude-opus-5","name":"Claude Opus 5","description":"Claude Opus 5 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"anthropic/claude-opus-5"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1000000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000060000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000006000"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000060000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000300000"}]}]},{"schema_version":"2.4","id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Claude Sonnet 5 served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"anthropic/claude-sonnet-5"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1000000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002400"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000120000"}]}]},{"schema_version":"2.4","id":"gpt-6-sol","name":"GPT 6 Sol","description":"GPT 6 Sol served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-6-sol"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002400"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000120000"}]}]},{"schema_version":"2.4","id":"gpt-6.1-sol","name":"GPT 6.1 Sol","description":"GPT 6.1 Sol served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-6.1-sol"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001200"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000120000"}]}]},{"schema_version":"2.4","id":"gpt-6-astra","name":"GPT 6 Astra","description":"GPT 6 Astra served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-6-astra"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000120000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000012000"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000120000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000600000"}]}]},{"schema_version":"2.4","id":"gpt-6-luna","name":"GPT 6 Luna","description":"GPT 6 Luna served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-6-luna"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001200"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000120"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001200"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000006000"}]}]},{"schema_version":"2.4","id":"gpt-5.6-sol","name":"GPT 5.6 Sol","description":"GPT 5.6 Sol served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-5.6-sol"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000002400"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000024000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000120000"}]}]},{"schema_version":"2.4","id":"gpt-5.6-luna","name":"GPT 5.6 Luna","description":"GPT 5.6 Luna served through a partner inference provider, not on Heabsy hardware; no zero data retention. Supports vision input, reasoning, tool calling, structured output.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":false},"openrouter":{"slug":"openai/gpt-5.6-luna"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1050000}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002400"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000240"}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002400"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":128000}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000014400"}]}]},{"schema_version":"2.4","id":"qwen38-unc-fast","name":"Qwen3.8 27B Uncensored Fast by Heabsy","hugging_face_id":"heabsy/Qwen3.8-27B-Uncensored-Fast","description":"Heabsy's own build of Qwen3.8 27B Uncensored: weights we quantized and calibrated ourselves, served on our inference stack. Refusal behaviour is removed, and quality matches the original Qwen3.8 27B (benchmarks on the model card). Reasoning comes back in a separate field, tool calling works, context is 524k tokens. Served only by Heabsy, in the European Economic Area; prompts and completions are not stored in request logs.","tokenizer":"Qwen","is_ready":true,"deployment_region":"EU","hosting":"heabsy","eea_available":true,"compliance":{"zdr":true},"openrouter":{"slug":"heabsy/qwen3.8-27b-uncensored-fast"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000008299"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000001500"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":32000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000008299"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":235929},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000026200"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"glm-5.3-uncensored","name":"GLM 5.3 Uncensored","hugging_face_id":"dealignai/GLM-5.3-UNCENSORED-NVFP4","description":"GLM-5.3 Uncensored: GLM-5.3 with dealignai's weight-level refusal removal (no adapter), served through a partner inference provider with zero data retention, not on Heabsy hardware. Context up to 1M tokens, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"global","hosting":"partner","eea_available":false,"compliance":{"zdr":true},"openrouter":{"slug":"z-ai/glm-5.3-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000015750"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000003780"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":131072}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000028350"}]}],"quantization":"nvfp4"},{"schema_version":"2.4","id":"deepseek-v4.1-flash-1017-unc","name":"DeepSeek V4.1 Flash 1017 Uncensored","hugging_face_id":"dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8","description":"DeepSeek-V4.1-Flash Uncensored: dealignai's DeepSeek-V4.1-Flash-UNCENSORED weights with refusal removal baked into the weights (no adapter), FP8, served on dedicated GPUs. 1M context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":false,"deployment_region":"US","hosting":"heabsy","eea_available":false,"compliance":{"zdr":true},"openrouter":{"slug":"deepseek/deepseek-v4.1-flash-1017-uncensored"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004000"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000400"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]},{"type":"image","supported_inputs":{"formats":{"type":"enum","values":["image/png","image/jpeg","image/webp"]}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000004000"}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536},"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"frequency_penalty":{"type":"range","min":-2,"max":2},"presence_penalty":{"type":"range","min":-2,"max":2},"stop":{"type":"array"},"seed":{"type":"integer"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000014000"}]}],"quantization":"fp8"},{"schema_version":"2.4","id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","description":"DeepSeek-V4.1-Flash 1017, FP8, served on dedicated GPUs. 1M context, reasoning returned separately, tool calling enabled. Prompts and completions are not stored in request logs.","tokenizer":"Other","is_ready":true,"deployment_region":"US","hosting":"heabsy","eea_available":false,"compliance":{"zdr":true},"openrouter":{"slug":"deepseek/deepseek-v4.1-flash-1017"},"input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":1048576}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000002583"},{"type":"cached_prompt","unit":"token","cost_usd":"0.0000000052"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":2000000}]}],"output_modalities":[{"type":"text","streaming":true,"supported_parameters":{"max_tokens":{"type":"integer","min":1,"max":65536}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.0000010330"}]}],"quantization":"fp8"}]}