image: repository: huggingface name: chat-ui #nodeSelector: # role-huggingchat: "true" # #tolerations: # - key: "huggingface.co/huggingchat" # operator: "Equal" # value: "true" # effect: "NoSchedule" serviceAccount: enabled: true create: true name: huggingchat-ephemeral ingress: enabled: false ingressInternal: enabled: true path: "/chat" annotations: external-dns.alpha.kubernetes.io/hostname: "*.chat-dev.huggingface.tech" alb.ingress.kubernetes.io/healthcheck-path: "/chat/healthcheck" alb.ingress.kubernetes.io/listen-ports: "[{\"HTTP\": 80}, {\"HTTPS\": 443}]" alb.ingress.kubernetes.io/group.name: "chat-dev-internal-public" alb.ingress.kubernetes.io/load-balancer-name: "chat-dev-internal-public" alb.ingress.kubernetes.io/ssl-redirect: "443" alb.ingress.kubernetes.io/tags: "Env=prod,Project=hub,Terraform=true" alb.ingress.kubernetes.io/target-group-attributes: deregistration_delay.timeout_seconds=30 alb.ingress.kubernetes.io/target-type: "ip" alb.ingress.kubernetes.io/certificate-arn: "arn:aws:acm:us-east-1:707930574880:certificate/bc3eb446-1c04-432c-ac6b-946a88d725da" kubernetes.io/ingress.class: "alb" envVars: TEST: "test" COUPLE_SESSION_WITH_COOKIE_NAME: "token" OPENID_SCOPES: "openid profile inference-api read-mcp read-billing contribute-repos jobs" USE_USER_TOKEN: "true" MCP_FORWARD_HF_USER_TOKEN: "true" AUTOMATIC_LOGIN: "false" ADDRESS_HEADER: "X-Forwarded-For" APP_BASE: "/chat" ALLOW_IFRAME: "false" COOKIE_SAMESITE: "lax" COOKIE_SECURE: "true" EXPOSE_API: "true" METRICS_ENABLED: "true" LOG_LEVEL: "debug" NODE_LOG_STRUCTURED_DATA: "true" OPENAI_BASE_URL: "https://router.huggingface.co/v1" PUBLIC_APP_ASSETS: "huggingchat" PUBLIC_APP_NAME: "HuggingChat" PUBLIC_APP_DESCRIPTION: "Making the community's best AI chat models available to everyone" PUBLIC_ORIGIN: "" PUBLIC_PLAUSIBLE_SCRIPT_URL: "https://plausible.io/js/pa-Io_oigECawqdlgpf5qvHb.js" PUBLIC_FEATURE_ANNOUNCEMENTS: > [{"title": "Kimi K3 is here", "description": "Moonshot's 2.8T open-weight MoE, with native vision and a 1M-token context window.", "link": "/models/moonshotai/Kimi-K3", "cta": "Chat with Kimi K3", "maxDate": "2026-09-15"}, {"title": "New GLM-5.3-Flash", "description": "Z.ai's natively multimodal 320B MoE, outperforming GLM-5.2 at one-tenth the price.", "link": "/models/zai-org/GLM-5.3-Flash", "cta": "Chat with GLM-5.3-Flash", "maxDate": "2026-09-30"}, {"title": "New DeepSeek V4.1 Flash", "description": "DeepSeek's natively multimodal 552B MoE, with frontier-level agentic coding and a 1M-token context window.", "link": "/models/deepseek-ai/DeepSeek-V4.1-Flash", "cta": "Chat with V4.1 Flash", "maxDate": "2026-10-10"}] TASK_MODEL: "meta-llama/Llama-3.1-8B-Instruct" # Tombstone: unread by current code, kept so any old pod still on the pre-#2265 # image (which gated Omni on LLM_ROUTER_ARCH_BASE_URL) keeps registering the alias # during rollout. Safe to remove once every replica is on the new image. LLM_ROUTER_ARCH_BASE_URL: "https://router.huggingface.co/v1" LLM_ROUTER_ROUTES_PATH: "build/client/chat/huggingchat/routes.chat.json" LLM_ROUTER_ENABLE_MULTIMODAL: "true" LLM_ROUTER_MULTIMODAL_MODEL: "deepseek-ai/DeepSeek-V4.1-Flash" LLM_ROUTER_ENABLE_TOOLS: "true" LLM_ROUTER_TOOLS_MODEL: "deepseek-ai/DeepSeek-V4.1-Flash" TRANSCRIPTION_MODEL: "openai/whisper-large-v3-turbo" # ML Intern model set: provider pinned per model from scripts/probe-model.ts runs # (2026-09-02). GLM-5.3-Flash on together recalled 5/5 at 924k tokens; Kimi-K3 on # baseten 6/6 at 1,046k (fireworks-ai is the alternate: 6/6, slower prefill); # GLM-5.3 degrades above ~800k on every provider — novita was the best of them. # DeepSeek-V4-Pro-0813 on together 5/5 at 911k (fireworks-ai equal; novita and # baseten 0/4 at 761k); DeepSeek-V4-Flash-0731 on novita 5/5 at 911k (together # and baseten 0/4 at 761k, deepinfra 0/5 at 910k). # together and fireworks-ai are billing disabled on the router, so DeepSeek-V4-Pro-0813 # stays out until another provider passes the probe ML_ASSISTANT_MODELS: > [{"id": "zai-org/GLM-5.3-Flash", "provider": "novita"}, {"id": "moonshotai/Kimi-K3", "provider": "baseten"}, {"id": "zai-org/GLM-5.3", "provider": "novita"}, {"id": "deepseek-ai/DeepSeek-V4-Flash-0731", "provider": "novita"}, {"id": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "provider": "novita"}] MCP_SERVERS: > [{"name": "Web Search (Exa)", "url": "https://mcp.exa.ai/mcp?tools=web_search_exa,get_code_context_exa,crawling_exa"}, {"name": "Hugging Face", "url": "https://hf.co/mcp?login"}] MCP_TOOL_TIMEOUT_MS: "120000" PUBLIC_LLM_ROUTER_DISPLAY_NAME: "Omni" PUBLIC_LLM_ROUTER_LOGO_URL: "https://cdn-uploads.huggingface.co/production/uploads/5f17f0a0925b9863e28ad517/C5V0v1xZXv6M7FXsdJH9b.png" PUBLIC_LLM_ROUTER_ALIAS_ID: "omni" MODELS: > [ { "id": "omni", "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "description": "Updated V4.1-Flash with stronger agentic coding, vision, and shorter outputs.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "meta-models/Muse-Spark-Open-816B-A42B", "description": "Open-weight 816B Meta MoE with 42B active for multimodal agents.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "inclusionAI/Ling-3.1-flash", "description": "Hybrid-linear 560B MoE with 25B active for agentic coding and 1M context.", "supportsArtifacts": true }, { "id": "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4", "description": "Vision-language NVFP4 Nemotron 120B MoE with 12B active for documents and video.", "supportsArtifacts": true }, { "id": "ibm-granite/granite-4.2-30b", "description": "Flagship 30B Granite reasoner for coding, tool calling, and multilingual dialog.", "supportsReasoning": true }, { "id": "CohereLabs/command-a-plus-05-2026-w4a4", "description": "W4A4 4-bit Command A+ for fast, low-latency multilingual agents.", "supportsArtifacts": true }, { "id": "CohereLabs/command-a-plus-05-2026-fp8", "description": "FP8 Command A+ for efficient inference with multilingual agentic reasoning.", "supportsArtifacts": true }, { "id": "CohereLabs/command-a-plus-05-2026-bf16", "description": "BF16 Command A+ 218B MoE for multilingual enterprise agents and vision.", "supportsArtifacts": true }, { "id": "zai-org/GLM-4.6-FP8", "description": "FP8 GLM-4.6 for efficient inference with 200K context and agentic coding.", "supportsArtifacts": true }, { "id": "CohereLabs/command-a-vision-07-2025", "description": "112B vision-language Command A for enterprise documents, charts, and OCR.", "supportsArtifacts": true }, { "id": "XiaomiMiMo/MiMo-V2.6-Flash-RL", "description": "Fast 310B MoE with 15B active, RL-scaled for agentic coding.", "supportsArtifacts": true }, { "id": "CohereLabs/c4ai-command-r7b-arabic-02-2025", "description": "Compact 7B Command R for Arabic and English enterprise RAG." }, { "id": "tencent/Hy4-preview", "description": "Preview 770B MoE with 49B active params, deep thinking, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-4.7-FP8", "description": "FP8 GLM-4.7 for efficient coding, reasoning, and agentic tool use.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-V4.1-Flash", "description": "Native multimodal 552B MoE for agentic coding, adjustable thinking, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-4.5", "description": "Flagship GLM agent model unifying advanced reasoning, coding, and tool-using capabilities.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "swiss-ai/Apertus-8B-Instruct-2509", "description": "Open, multilingual, trained on compliant data transparent global assistant." }, { "id": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp", "description": "Experimental vision-language V4-Flash for multimodal agents and adjustable thinking.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "inclusionAI/Ling-3.0-flash-VL", "description": "Vision-language Ling-3.0-flash MoE for image, video, and GUI agent tasks.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "inclusionAI/Ling-3.0-flash-Fin", "description": "Finance-tuned Ling-3.0-flash for grounded research, valuation, and spreadsheet workflows.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "Qwen/Qwen3.5-122B-A10B", "description": "Multimodal MoE excelling at agentic tool use with 1M context and 201 languages.", "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } }, { "id": "speakleash/Bielik-11B-v3.0-Instruct", "description": "Polish-language 11B instruction model for chat, writing, and comprehension." }, { "id": "zai-org/GLM-5.3", "description": "Post-trained 744B MoE for complex coding and long-horizon agentic tasks.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-5.3-BF16", "description": "BF16 GLM-5.3 for full-precision agentic coding and long-horizon tasks.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "Qwen/Qwen3.8-27B", "description": "Dense 27B vision-language Qwen with thinking control and 262K context.", "supportsReasoning": true }, { "id": "zai-org/GLM-5.3-Flash", "description": "Natively multimodal 320B MoE with 18B active params for coding and agents.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-5.3-Flash-BF16", "description": "BF16 GLM-5.3-Flash for full-precision multimodal coding and agents.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "inclusionAI/Ling-3.0-flash", "description": "Hybrid-linear 124B MoE with 5.1B active params and fast thinking.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "ibm-granite/granite-4.2-8b", "description": "Mid-size 8B Granite with built-in thinking and reasoning-augmented tool calling.", "supportsReasoning": true }, { "id": "ibm-granite/granite-4.2-3b", "description": "Compact 3B Granite reasoner for fast multilingual chat and tool use.", "supportsReasoning": true }, { "id": "deepseek-ai/DeepSeek-V4-Pro-0813", "description": "Updated V4-Pro flagship with stronger agentic coding and adjustable thinking.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "Qwen/Qwen3.8-2.4T-A95B", "description": "Flagship 2.4T MoE with 95B active params, always-on thinking, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "meta-models/Muse-Glimmer-30B", "description": "Vision-language 30B agent for local tool use, coding, and screenshot understanding.", "supportsReasoning": true }, { "id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "description": "BF16 hybrid Mamba-Transformer MoE with 3B active params for long-running agents." }, { "id": "CohereLabs/command-a-translate-08-2025", "description": "111B Command A specialist for machine translation across 23 languages.", "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-V4-Flash-0731", "description": "Updated V4-Flash with adjustable thinking, stronger coding, and agentic tool use.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "thinkingmachines/Inkling-Small", "description": "Compact multimodal 276B MoE with 12B active params and adjustable reasoning effort.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "NousResearch/Hermes-3-Llama-3.1-70B", "description": "Steerable 70B Llama fine-tune for roleplay, agents, and function calling.", "supportsArtifacts": true }, { "id": "Qwen/Qwen3-30B-A3B", "description": "Efficient hybrid 30B MoE with 3B active params and switchable thinking mode." }, { "id": "moonshotai/Kimi-K3", "description": "2.8T MoE with native vision, 1M context, and always-on thinking.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "tencent/Hy3", "description": "295B MoE for deep reasoning, agentic coding, and 256K context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "XiaomiMiMo/MiMo-V2.5", "description": "310B omnimodal MoE handling text, image, video, and audio at 1M context.", "supportsArtifacts": true }, { "id": "Qwen/Qwen2.5-VL-72B-Instruct", "description": "Vision-language Qwen for documents, charts, and long video understanding.", "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "description": "Distilled Qwen with R1 stepwise reasoning in mid-size footprint." }, { "id": "thinkingmachines/Inkling", "description": "Multimodal 975B MoE with 41B active params and adjustable reasoning effort.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "prism-ml/Ternary-Bonsai-27B-AWQ-4bit", "description": "AWQ 4-bit ternary Qwen3.6 27B with vision for single-GPU serving." }, { "id": "prism-ml/Ternary-Bonsai-27B-gguf", "description": "Ternary GGUF Qwen3.6 27B for on-device reasoning at 1.7 bits." }, { "id": "CohereLabs/tiny-aya-fire", "description": "Regional Aya for South Asian languages with efficient on-device inference." }, { "id": "XiaomiMiMo/MiMo-V2.5-Pro", "description": "1T MoE with 42B active params, hybrid attention, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "description": "BF16 hybrid Mamba-Transformer 550B MoE with 55B active params for agentic reasoning.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "stepfun-ai/Step-3.7-Flash", "description": "Vision-language 198B MoE with 11B active params, reasoning modes, and 256K context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "google/gemma-3-12b-it", "description": "Dense 12B multimodal Gemma with 128K context and multilingual support." }, { "id": "google/gemma-3-4b-it", "description": "Compact 4B multimodal Gemma with 128K context for lightweight tasks." }, { "id": "microsoft/phi-4", "description": "Dense 14B model with strong math, reasoning, and coding density." }, { "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } }, { "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } }, { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "Qwen/Qwen3.6-27B", "description": "Dense 27B hybrid with DeltaNet attention and 1M context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "description": "Native multimodal 17B MoE with 16 experts and very long context."}, { "id": "CohereLabs/c4ai-command-r7b-12-2024", "description": "Compact 7B Command R for multilingual RAG, tool use, and agents." }, { "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-V4-Flash", "description": "Compact 284B MoE with 13B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true }, { "id": "deepseek-ai/DeepSeek-V3.2", "description": "Stable 671B MoE with sparse attention for agentic reasoning and long contexts.", "supportsArtifacts": true }, { "id": "stepfun-ai/Step-3.5-Flash", "description": "Sparse 197B MoE agent with multi-token prediction and 256K context.", "supportsArtifacts": true }, { "id": "Qwen/Qwen3.6-35B-A3B", "description": "Hybrid 35B MoE with 3B active params, DeltaNet attention, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "zai-org/GLM-4.7-Flash", "description": "Compact 30B MoE for agentic coding with 128K context and tool use.", "supportsReasoning": true, "supportsArtifacts": true }, { "id": "moonshotai/Kimi-K2.6", "description": "Native multimodal 1T MoE for long-horizon coding and 300-sub-agent swarms.", "supportsArtifacts": true }, { "id": "MiniMaxAI/MiniMax-M2.7", "description": "Self-evolving 230B MoE agent for frontier coding, reasoning, and tool use." , "supportsReasoning": true, "supportsArtifacts": true }, { "id": "google/gemma-4-31B-it", "description": "Dense multimodal Gemma with 256K context, reasoning, and function calling.", "supportsArtifacts": true}, { "id": "google/gemma-4-26B-A4B-it", "description": "Efficient multimodal MoE Gemma with 4B active params and 256K context."}, { "id": "Qwen/Qwen3.5-9B", "description": "Dense multimodal hybrid with 262K context excelling at reasoning on-device."}, { "id": "CohereLabs/tiny-aya-global", "description": "Tiny multilingual assistant covering 70+ languages for on-device deployment." }, { "id": "CohereLabs/tiny-aya-earth", "description": "Regional Aya for African languages with culturally tuned on-device inference." }, { "id": "CohereLabs/tiny-aya-water", "description": "Regional Aya for Asia-Pacific and European multilingual on-device tasks." }, { "id": "Qwen/Qwen3.5-35B-A3B", "description": "Compact multimodal MoE with hybrid DeltaNet, 1M context, and 201 languages.", "supportsArtifacts": true }, { "id": "Qwen/Qwen3.5-27B", "description": "Dense multimodal hybrid with top-tier reasoning density and 1M context."}, { "id": "Qwen/Qwen3.5-397B-A17B", "description": "Native multimodal MoE with hybrid attention, 1M context, and 201 languages.", "parameters": { "max_tokens": 32768 } }, { "id": "MiniMaxAI/MiniMax-M2.5", "description": "Frontier 230B MoE agent for top-tier coding, tool calling, and fast inference." , "supportsReasoning": true }, { "id": "zai-org/GLM-5", "description": "Flagship 745B MoE for agentic reasoning, coding, and creative writing."}, { "id": "Qwen/Qwen3-VL-235B-A22B-Instruct", "description": "Flagship Qwen3 vision-language MoE for visual agents, documents, and GUI automation." }, { "id": "moonshotai/Kimi-K2.5", "description": "Native multimodal agent with agent swarms for parallel tool orchestration." }, { "id": "zai-org/GLM-4.7", "description": "Flagship GLM MoE for coding, reasoning, and agentic tool use." , "supportsReasoning": true }, { "id": "zai-org/AutoGLM-Phone-9B-Multilingual", "description": "Mobile agent for multilingual Android device automation." }, { "id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "description": "Flagship Qwen3 vision-language model for high-accuracy image, text, and video reasoning." }, { "id": "aisingapore/Qwen-SEA-LION-v4-32B-IT", "description": "SEA-LION v4 Qwen optimized for Southeast Asian languages and regional enterprise workloads." }, { "id": "openai/gpt-oss-safeguard-20b", "description": "Safety-focused gpt-oss variant for content classification, policy enforcement, and LLM output filtering." , "supportsReasoning": true }, { "id": "zai-org/GLM-4.5V-FP8", "description": "FP8 vision-language GLM-4.5V for efficient multilingual visual QA, understanding, and hybrid reasoning."}, { "id": "zai-org/GLM-4.6", "description": "Next-gen GLM with very long context and solid multilingual reasoning; good for agents and tools."}, { "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "description": "Refined V3.1 variant optimized for reliability on long contexts, structured outputs, and tool use."}, { "id": "zai-org/GLM-4.6V", "description": "106B vision-language model with 128K context and native tool calling for multimodal agents.", "parameters": { "max_tokens": 8192 }}, { "id": "zai-org/GLM-4.6V-Flash", "description": "9B lightweight vision model for fast local inference with tool calling and UI understanding."}, { "id": "zai-org/GLM-4.6V-FP8", "description": "FP8-quantized GLM-4.6V for efficient multimodal deployment with native tool use."}, { "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "description": "Deliberative text-only 235B Qwen variant for transparent, step-by-step reasoning on hard problems."}, { "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "description": "Instruction tuned Qwen for multilingual reasoning, coding, long contexts." }, { "id": "moonshotai/Kimi-K2-Instruct-0905", "description": "Instruction MoE strong coding and multi step reasoning, long context." }, { "id": "openai/gpt-oss-20b", "description": "Efficient open model for reasoning and tool use, runs locally." , "supportsReasoning": true }, { "id": "openai/gpt-oss-120b", "description": "High performing open model suitable for large scale applications." , "supportsReasoning": true, "supportsArtifacts": true }, { "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "description": "Code specialized Qwen long context strong generation and function calling." }, { "id": "meta-llama/Llama-3.1-8B-Instruct", "description": "Instruction tuned Llama efficient conversational assistant with improved alignment." }, { "id": "deepseek-ai/DeepSeek-R1", "description": "MoE reasoning model excels at math, logic, coding with steps."}, { "id": "Qwen/Qwen3-4B-Instruct-2507", "description": "Compact instruction Qwen great for lightweight assistants and apps." }, { "id": "Qwen/Qwen3-4B-Thinking-2507", "description": "Small Qwen that emits transparent step by step reasoning."}, { "id": "moonshotai/Kimi-K2-Instruct", "description": "MoE assistant strong coding, reasoning, agentic tasks, long context." }, { "id": "zai-org/GLM-4.5V", "description": "Vision language MoE state of the art multimodal reasoning."}, { "id": "deepseek-ai/DeepSeek-V3.1", "description": "Supports direct and thinking style reasoning within one model."}, { "id": "Qwen/Qwen3-8B", "description": "Efficient Qwen assistant strong multilingual skills and formatting." }, { "id": "google/gemma-3-27b-it", "description": "Multimodal Gemma long context strong text and image understanding." }, { "id": "zai-org/GLM-4.5-Air", "description": "Efficient GLM strong reasoning and tool use at lower cost."}, { "id": "Qwen/Qwen3-32B", "description": "General purpose Qwen strong for complex queries and dialogues." }, { "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "description": "Flagship instruction Qwen near state of the art across domains." }, { "id": "meta-llama/Llama-3.3-70B-Instruct", "description": "Improved Llama alignment and structure powerful complex conversations." }, { "id": "Qwen/Qwen3-235B-A22B", "description": "Qwen base at flagship scale ideal for custom fine tuning." }, { "id": "Qwen/Qwen2.5-Coder-32B-Instruct", "description": "Code model strong generation and tool use bridges sizes." }, { "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "description": "Distilled Qwen excels at stepwise logic in compact footprint."}, { "id": "deepseek-ai/DeepSeek-V3", "description": "General language model direct answers strong creative and knowledge tasks." }, { "id": "deepseek-ai/DeepSeek-V3-0324", "description": "Updated V3 better reasoning and coding strong tool use." }, { "id": "deepseek-ai/DeepSeek-R1-0528", "description": "R1 update improved reasoning, fewer hallucinations, adds function calling.", "parameters": { "max_tokens": 32000 }}, { "id": "Qwen/Qwen3-14B", "description": "Balanced Qwen good performance and efficiency for assistants." }, { "id": "MiniMaxAI/MiniMax-M1-80k", "description": "Long context MoE very fast excels at long range reasoning and code."}, { "id": "Qwen/Qwen2.5-Coder-7B-Instruct", "description": "Efficient coding assistant for lightweight programming tasks." }, { "id": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "description": "Gemma SEA LION optimized for Southeast Asian languages or enterprise." }, { "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "description": "FP8 Maverick efficient deployment retains top multimodal capability." }, { "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "description": "Llama distilled from R1 strong reasoning and structured outputs."}, { "id": "Qwen/Qwen2.5-72B-Instruct", "description": "Accurate detailed instruction model supports tools and long contexts." }, { "id": "meta-llama/Llama-Guard-4-12B", "description": "Safety guardrail model filters and enforces content policies." }, { "id": "Sao10K/L3-8B-Stheno-v3.2", "description": "Community Llama variant themed tuning and unique conversational style." }, { "id": "CohereLabs/c4ai-command-r-08-2024", "description": "Cohere Command variant instruction following with specialized tuning." }, { "id": "CohereLabs/aya-expanse-32b", "description": "Aya Expanse large comprehensive knowledge and reasoning capabilities." }, { "id": "CohereLabs/c4ai-command-a-03-2025", "description": "Updated Command assistant improved accuracy and general usefulness." }, { "id": "CohereLabs/command-a-reasoning-08-2025", "description": "Command variant optimized for complex multi step logical reasoning." }, { "id": "alpindale/WizardLM-2-8x22B", "description": "Multi expert WizardLM MoE approach for efficient high quality generation." }, { "id": "CohereLabs/aya-vision-32b", "description": "Larger Aya Vision advanced vision language with detailed reasoning." }, { "id": "Qwen/Qwen2.5-Coder-3B-Instruct", "description": "Tiny coding assistant basic code completions and explanations." } ] infisical: enabled: true env: "ephemeral-us-east-1" replicas: 1 autoscaling: enabled: false resources: requests: cpu: 2 memory: 4Gi limits: cpu: 4 memory: 8Gi