{"total":4,"page":0,"limit":25,"items":[{"chute_id":"b048fe26-0352-5c46-acf7-335e527e7f3d","name":"zai-org/GLM-5.1-TEE","tagline":"","readme":"zai-org/GLM-5.1-FP8","public":true,"version":"aa3e7843-576d-5531-a408-f383ea7d49d4","tool_description":null,"slug":"chutes-zai-org-glm-5-1-tee","standard_template":"vllm","cords":null,"jobs":[],"cord_ref_id":"a2076977-e258-5d73-afc1-b52d9c36ff25","created_at":"2026-04-07T16:39:00.393893Z","updated_at":"2026-10-12T13:35:05.235648Z","image":{"image_id":"695a2917-f652-5131-9986-11986b5c3e8a","name":"sglang","readme":"## SGLang v0.5.21 (CUDA 13.0.3, system Python / uv pip)","tag":"0.5.21","public":true,"status":"built and pushed","created_at":"2026-10-05T15:34:43.894739Z","build_started_at":"2026-10-05T15:34:51.242402Z","build_completed_at":"2026-10-05T15:48:48.676660Z","user":{"username":"chutes","user_id":"dff3e6bb-3a6b-5a2b-9c48-da3abcd5ca5f","logo_id":"24ef9084-7739-400c-aab6-135463a8c2d9","created_at":"2024-12-03T11:31:39.181725Z","logo":"https://logos.chutes.ai/logos/24ef9084-7739-400c-aab6-135463a8c2d9.webp"},"logo_id":null,"patch_version":"initial","chutes_version":"0.6.11.rc2","logo":null},"user":{"username":"chutes","user_id":"dff3e6bb-3a6b-5a2b-9c48-da3abcd5ca5f","logo_id":"24ef9084-7739-400c-aab6-135463a8c2d9","created_at":"2024-12-03T11:31:39.181725Z","logo":"https://logos.chutes.ai/logos/24ef9084-7739-400c-aab6-135463a8c2d9.webp"},"supported_gpus":["h200"],"node_selector":{"dynamic":false,"exclude":null,"include":["h200"],"gpu_count":8,"min_vram_gb_per_gpu":16,"max_hourly_price_per_gpu":null,"compute_multiplier":4.888888888888889,"supported_gpus":["h200"]},"invocation_count":86516,"current_estimated_price":{"per_million_tokens":{"input":{"usd":0.98,"tao":0.003850897946881971},"output":{"usd":3.08,"tao":0.01210282211877191},"input_cache_read":{"usd":0.09799999999999998,"tao":0.00038508979468819706}},"usd":{"hour":22.0,"second":0.006111111111111111},"tao":{"hour":0.08644872941979935,"second":0.000024013535949944264}},"instances":[{"instance_id":"ff310448-d9cc-4a2b-a64d-9bf942288df1","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-23T15:11:52.280274Z"},{"instance_id":"d6e61485-de19-4e3c-8944-3964ac4afcf9","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-22T13:55:14.932881Z"},{"instance_id":"e334b348-d524-4f8b-ac1a-d7beeb7a8fa7","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-16T18:43:11.768972Z"},{"instance_id":"23a74521-9a69-4542-aa51-91b62da8cde7","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-16T21:42:16.772576Z"},{"instance_id":"1dcd93a1-9ff5-43ad-9f72-23bc9b0ce6a7","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-23T15:23:12.778002Z"},{"instance_id":"33cc062e-f97a-437f-96bc-78d42b79d60e","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-17T20:28:43.941164Z"}],"logo_id":"ef6a6d6b-cb92-4aa5-a5a2-4aa96bd9e282","openrouter":true,"chutes_version":"0.6.11.rc2","revision":"f396cf805182f4ca10fa675e1a99815b3ca384db","concurrency":32,"boost":1.75,"max_instances":null,"scaling_threshold":null,"shutdown_after_seconds":null,"preemptible":true,"allow_external_egress":false,"tee":true,"lock_modules":true,"effective_compute_multiplier":23.1,"compute_multiplier_factors":{"base":4.888888888888889,"urgency_boost":1.75,"manual_boost":1.2,"tee":2.25},"bounty":null,"execution_backend":"hosted","disabled":false,"logo":"https://logos.chutes.ai/logos/ef6a6d6b-cb92-4aa5-a5a2-4aa96bd9e282.webp","hot":true},{"chute_id":"08901219-159f-55a7-87cf-9d0d02744668","name":"zai-org/GLM-5.2-TEE","tagline":"","readme":"nvidia/GLM-5.2-NVFP4","public":true,"version":"cc44b944-4f69-56b8-a4bc-afeaf7a222bf","tool_description":null,"slug":"chutes-zai-org-glm-5-2-tee","standard_template":"vllm","cords":null,"jobs":[],"cord_ref_id":"afcf6afd-ec4a-55f6-b2bc-de0149df2cf1","created_at":"2026-06-17T08:11:42.793271Z","updated_at":"2026-07-17T10:16:50.953665Z","image":{"image_id":"e5589f58-64d3-51f6-8a3d-146b1cd77940","name":"sglang","readme":"## SGLang with extra libs for broader model support.","tag":"0.5.15-post1a","public":true,"status":"built and pushed","created_at":"2026-07-15T20:32:46.894490Z","build_started_at":"2026-07-15T20:35:56.208941Z","build_completed_at":"2026-07-15T20:45:12.163711Z","user":{"username":"chutes","user_id":"dff3e6bb-3a6b-5a2b-9c48-da3abcd5ca5f","logo_id":"24ef9084-7739-400c-aab6-135463a8c2d9","created_at":"2024-12-03T11:31:39.181725Z","logo":"https://logos.chutes.ai/logos/24ef9084-7739-400c-aab6-135463a8c2d9.webp"},"logo_id":null,"patch_version":"initial","chutes_version":"0.6.11.rc2","logo":null},"user":{"username":"chutes","user_id":"dff3e6bb-3a6b-5a2b-9c48-da3abcd5ca5f","logo_id":"24ef9084-7739-400c-aab6-135463a8c2d9","created_at":"2024-12-03T11:31:39.181725Z","logo":"https://logos.chutes.ai/logos/24ef9084-7739-400c-aab6-135463a8c2d9.webp"},"supported_gpus":["b200"],"node_selector":{"dynamic":false,"exclude":null,"include":["b200"],"gpu_count":8,"min_vram_gb_per_gpu":16,"max_hourly_price_per_gpu":null,"compute_multiplier":8.0,"supported_gpus":["b200"]},"invocation_count":56273,"current_estimated_price":{"per_million_tokens":{"input":{"usd":1.25,"tao":0.004911859626124964},"output":{"usd":3.95,"tao":0.015521476418554885},"input_cache_read":{"usd":0.12499999999999997,"tao":0.0004911859626124962}},"usd":{"hour":36.0,"second":0.01},"tao":{"hour":0.14146155723239895,"second":0.00003929487700899971}},"instances":[{"instance_id":"93369192-77fe-4a65-beb1-ecf563249c50","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-20T00:06:54.524424Z"},{"instance_id":"a2b33719-c684-4c83-a05b-9714f690a2d4","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-21T21:06:02.098201Z"},{"instance_id":"1736e829-c93c-43b6-8ecd-ee5da88d076f","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-18T03:28:04.222395Z"},{"instance_id":"ad9e0d6c-7333-4f49-a48c-efe887a701ff","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-20T15:28:00.137244Z"}],"logo_id":"1aa8be00-494e-45a9-81fe-7c3ab8acbd44","openrouter":true,"chutes_version":"0.6.11.rc2","revision":"aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa","concurrency":32,"boost":1.75,"max_instances":null,"scaling_threshold":null,"shutdown_after_seconds":null,"preemptible":true,"allow_external_egress":false,"tee":true,"lock_modules":true,"effective_compute_multiplier":37.800000000000004,"compute_multiplier_factors":{"base":8.0,"urgency_boost":1.75,"manual_boost":1.2,"tee":2.25},"bounty":null,"execution_backend":"hosted","disabled":false,"logo":"https://logos.chutes.ai/logos/1aa8be00-494e-45a9-81fe-7c3ab8acbd44.webp","hot":true},{"chute_id":"0754972a-019d-5d9e-bfc3-fb1c8e8df36c","name":"GLM-4.7-Flash-NVFP4-TEE","tagline":"GLM-4.7-Flash NVFP4 — 30B MoE, 3B active, tools + reasoning, MIT","readme":"## GLM-4.7-Flash NVFP4 — TEE on Chutes\n\nOpenAI-compatible **/v1/chat/completions** hosting [Unsloth GLM-4.7-Flash Dynamic NVFP4](https://huggingface.co/unsloth/GLM-4.7-Flash-NVFP4) via SGLang on a single **RTX PRO 6000 Blackwell**, TEE-enabled.\n\n### What it does\n\nGLM-4.7-Flash is a ~31B MoE (3B active) from Z.ai: MLA attention, 202k context, tool calling, and a thinking mode. MIT licensed. This chute serves Unsloth's mixed NVFP4 checkpoint — W4A4 on expert FFNs, FP8/BF16 on sensitive layers — on SM120 tensor cores. Not a Marlin W4A16 decompress.\n\n### Modalities\n\n| Direction | Supported |\n|-----------|-----------|\n| **In** | Text |\n| **Out** | Text, with separate `reasoning_content` and tool calls |\n\n### Runtime\n\n- **Context:** 131,072 tokens (BF16 KV; NVFP4 weights). Sampling: temperature 1.0, top_p 0.95, repeat penalty off.\n- **Parsers:** `--reasoning-parser glm45`, `--tool-call-parser glm47`\n- **Thinking:** always a real JSON bool, default `true` (GLM card). Playground / API `enable_thinking` or `chat_template_kwargs.enable_thinking` turn it off. Off closes `<think>` and adds a direct-answer instruction so CoT does not spill into `content` and loop. On: injects a brief-thinking system line (a few sentences of CoT, then answer); think tokens go to `reasoning_content` until the model emits `</think>`. Chutes playground only paints `content` — give `max_tokens` room for the think block plus the answer. Unset `max_tokens` defaults to **4096**; hard-capped at **8192** (single-GPU product limits).\n- **GPU:** 1x RTX PRO 6000 (SM120), >=80 GB VRAM, TEE\n","public":true,"version":"6db20d78-c55a-5745-a5f6-4d1869b0cf36","tool_description":null,"slug":"vonkaiser-glm-4-7-flash-nvfp4-tee","standard_template":"vllm","cords":null,"jobs":[],"cord_ref_id":"cfed2a57-a48a-5a22-a209-187afad6de01","created_at":"2026-09-15T17:19:24.478842Z","updated_at":"2026-09-15T17:19:24.478842Z","image":{"image_id":"e124b308-2806-5e16-b0f7-0abe79976a9a","name":"glm47flash","readme":"SGLang (chutes fork) + GLM-4.7-Flash NVFP4 on SM120","tag":"0.1.2","public":true,"status":"built and pushed","created_at":"2026-08-23T00:09:47.354373Z","build_started_at":"2026-08-23T00:09:53.102162Z","build_completed_at":"2026-08-23T00:33:51.438327Z","user":{"username":"vonkaiser","user_id":"c2e8a78e-ba27-52d9-a2dc-3d55d96dcc69","logo_id":"907bf599-3324-4eae-b722-edf206ffaa98","created_at":"2025-02-11T17:19:50.028828Z","logo":"https://logos.chutes.ai/logos/907bf599-3324-4eae-b722-edf206ffaa98.webp"},"logo_id":null,"patch_version":"initial","chutes_version":"0.6.11.rc2","logo":null},"user":{"username":"vonkaiser","user_id":"c2e8a78e-ba27-52d9-a2dc-3d55d96dcc69","logo_id":"907bf599-3324-4eae-b722-edf206ffaa98","created_at":"2025-02-11T17:19:50.028828Z","logo":"https://logos.chutes.ai/logos/907bf599-3324-4eae-b722-edf206ffaa98.webp"},"supported_gpus":["pro_6000"],"node_selector":{"dynamic":false,"exclude":null,"include":["pro_6000"],"gpu_count":1,"min_vram_gb_per_gpu":80,"max_hourly_price_per_gpu":null,"compute_multiplier":0.4,"supported_gpus":["pro_6000"]},"invocation_count":25,"current_estimated_price":{"per_million_tokens":{"input":{"usd":0.0245,"tao":0.00009627244867204929},"output":{"usd":0.0978,"tao":0.00038430389714801713},"input_cache_read":{"usd":0.0024499999999999995,"tao":9.627244867204925e-6}},"usd":{"hour":1.8,"second":0.0005},"tao":{"hour":0.007073077861619948,"second":1.9647438504499855e-6}},"instances":[{"instance_id":"947965c3-d789-47bd-b841-40e8bf01c02b","region":"n/a","active":false,"verified":true,"last_verified_at":"2026-10-24T04:08:40.772954Z"},{"instance_id":"24d36146-6f4f-4005-ba36-ca57aef7c65b","region":"n/a","active":true,"verified":true,"last_verified_at":"2026-10-23T20:11:27.189157Z"}],"logo_id":"d748496a-6ffd-4724-9295-5e6ad20a7c85","openrouter":false,"chutes_version":"0.6.11.rc2","revision":"98b0362133bda9ee3b1b875636636c07861f5947","concurrency":7,"boost":1.0,"max_instances":null,"scaling_threshold":null,"shutdown_after_seconds":null,"preemptible":true,"allow_external_egress":false,"tee":true,"lock_modules":true,"effective_compute_multiplier":0.9,"compute_multiplier_factors":{"base":0.4,"urgency_boost":1.0,"tee":2.25},"bounty":null,"execution_backend":"hosted","disabled":false,"logo":"https://logos.chutes.ai/logos/d748496a-6ffd-4724-9295-5e6ad20a7c85.webp","hot":true},{"chute_id":"3005fc0c-b352-5a6d-acb6-d26385ac718f","name":"glmbbb/affine-20-5Ehayv8U8eKkFENkesSSQadEyvFY2QjRgjYAj8DUcfEc2pST","tagline":"","readme":"glmbbb/affine-20-5Ehayv8U8eKkFENkesSSQadEyvFY2QjRgjYAj8DUcfEc2pST","public":false,"version":"d63db219-9018-5bf7-9b3e-38e1bc8b9c30","tool_description":null,"slug":"affine-gamma-10-glmbbb-affine-20-5ehayv8u8ekkfenkesssqadey","standard_template":"vllm","cords":null,"jobs":[],"cord_ref_id":"55360f02-be18-5cba-affa-796e57596b47","created_at":"2026-01-20T17:59:56.660453Z","updated_at":"2026-04-29T13:41:01.015569Z","image":{"image_id":"20be83dc-d918-5b4d-8b70-7069634c1ead","name":"sglang","readme":"SGLang is a fast serving framework for large language models and vision language models. It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.","tag":"nightly-2026030401","public":true,"status":"built and pushed","created_at":"2026-03-04T15:12:39.039885Z","build_started_at":"2026-03-04T15:12:41.314519Z","build_completed_at":"2026-03-04T15:37:12.961968Z","user":{"username":"chutes","user_id":"dff3e6bb-3a6b-5a2b-9c48-da3abcd5ca5f","logo_id":"24ef9084-7739-400c-aab6-135463a8c2d9","created_at":"2024-12-03T11:31:39.181725Z","logo":"https://logos.chutes.ai/logos/24ef9084-7739-400c-aab6-135463a8c2d9.webp"},"logo_id":null,"patch_version":"86e4b33c1bdb","chutes_version":"0.5.17","logo":null},"user":{"username":"affine_gamma_10","user_id":"80a9ee12-6e39-57a3-b6d5-ac00cbffc796","logo_id":null,"created_at":"2026-01-01T22:22:59.531241Z","logo":null},"supported_gpus":["pro_6000"],"node_selector":{"dynamic":false,"exclude":["mi300x"],"include":["pro_6000"],"gpu_count":8,"min_vram_gb_per_gpu":80,"max_hourly_price_per_gpu":null,"compute_multiplier":3.2,"supported_gpus":["pro_6000"]},"invocation_count":0,"current_estimated_price":{"per_million_tokens":{"input":{"usd":0.1957,"tao":0.0007690007430661243},"output":{"usd":0.7826,"tao":0.003075217074724317},"input_cache_read":{"usd":0.019569999999999997,"tao":0.00007690007430661242}},"usd":{"hour":14.4,"second":0.004},"tao":{"hour":0.05658462289295958,"second":0.000015717950803599884},"hourly_price_range":{"usd":{"min":14.4,"max":14.4},"tao":{"min":0.05658462289295958,"max":0.05658462289295958}}},"instances":[],"logo_id":null,"openrouter":false,"chutes_version":"0.5.17","revision":"83f45b48223aaa6ea0f64726d64350d093786f1a","concurrency":16,"boost":1.0,"max_instances":1,"scaling_threshold":0.5,"shutdown_after_seconds":36000,"preemptible":false,"allow_external_egress":false,"tee":true,"lock_modules":null,"effective_compute_multiplier":21.6,"compute_multiplier_factors":{"base":3.2,"private_tee":3,"tee":2.25},"bounty":null,"execution_backend":"hosted","disabled":false,"logo":null,"hot":false}],"cord_refs":{"a2076977-e258-5d73-afc1-b52d9c36ff25":[{"path":"/chat_stream","method":"POST","stream":true,"function":"chat_stream","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion_stream","method":"POST","stream":true,"function":"completion_stream","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/chat","method":"POST","stream":false,"function":"chat","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion","method":"POST","stream":false,"function":"completion","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/get_models","method":"GET","stream":false,"function":"get_models","passthrough":true,"public_api_path":"/v1/models","public_api_method":"GET","output_content_type":null}],"afcf6afd-ec4a-55f6-b2bc-de0149df2cf1":[{"path":"/chat_stream","method":"POST","stream":true,"function":"chat_stream","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion_stream","method":"POST","stream":true,"function":"completion_stream","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/chat","method":"POST","stream":false,"function":"chat","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion","method":"POST","stream":false,"function":"completion","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/get_models","method":"GET","stream":false,"function":"get_models","passthrough":true,"public_api_path":"/v1/models","public_api_method":"GET","output_content_type":null}],"cfed2a57-a48a-5a22-a209-187afad6de01":[{"path":"/chat_stream","method":"POST","stream":true,"function":"chat_stream","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion_stream","method":"POST","stream":true,"function":"completion_stream","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/chat","method":"POST","stream":false,"function":"chat","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion","method":"POST","stream":false,"function":"completion","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/get_models","method":"GET","stream":false,"function":"get_models","passthrough":true,"public_api_path":"/v1/models","public_api_method":"GET","output_content_type":null}],"55360f02-be18-5cba-affa-796e57596b47":[{"path":"/chat_stream","method":"POST","stream":true,"function":"chat_stream","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion_stream","method":"POST","stream":true,"function":"completion_stream","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/chat","method":"POST","stream":false,"function":"chat","passthrough":true,"public_api_path":"/v1/chat/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/completion","method":"POST","stream":false,"function":"completion","passthrough":true,"public_api_path":"/v1/completions","public_api_method":"POST","output_content_type":"application/json"},{"path":"/get_models","method":"GET","stream":false,"function":"get_models","passthrough":true,"public_api_path":"/v1/models","public_api_method":"GET","output_content_type":null}]}}