{"service":"Dellbot LLM API","protocol":"x402","facilitator":"CDP (api.cdp.coinbase.com/platform/v2/x402)","network":"Base mainnet (USDC)","pay_to":"0x234864Febc3AD18Fc99620c576729bdebfb62bCb","endpoint":"https://x402.dellbot.win","tiers":{"/chat-nano":{"price":"$0.001","models":["gemma-4-uncensored","google-gemma-3-27b-it","google-gemma-4-31b-it","llama-3.2-3b","llama-3.3-70b","mistral-small-3-2-24b-instruct","nvidia-nemotron-3-nano-30b-a3b","nvidia-nemotron-cascade-2-30b-a3b","olafangensan-glm-4.7-flash-heretic","openai-gpt-4o-mini-2024-07-18","openai-gpt-oss-120b","qwen3-5-9b","zai-org-glm-4.7-flash"],"default_model":"openai-gpt-oss-120b","description":"Cheapest LLM on CDP x402 Bazaar. OpenAI-compatible chat completion. Default OpenAI GPT-OSS 120B; also offers Llama 3.3 70B, Llama 3.2 3B, Mistral Small 24B, Gemma 3 27B, Qwen3.5 9B, and Nemotron Nano 30B (all via Venice AI). Supports tools/tool_choice and stream:true SSE."},"/chat":{"price":"$0.003","models":["aion-labs-aion-2-0","deepseek-v3.2","gemini-3-flash-preview","google-gemma-4-26b-a4b-it","grok-build-0-1","hermes-3-llama-3.1-405b","kimi-k2-5","mercury-2","minimax-m25","minimax-m27","minimax-m3","mistral-small-2603","qwen3-235b-a22b-instruct-2507","qwen3-235b-a22b-thinking-2507","qwen3-5-35b-a3b","qwen3-6-27b","qwen3-next-80b","qwen3-vl-235b-a22b","venice-uncensored-1-2","venice-uncensored-role-play","zai-org-glm-4.6","zai-org-glm-4.7","zai-org-glm-5"],"default_model":"qwen3-235b-a22b-instruct-2507","description":"Mid-tier OpenAI-compatible chat completion. Qwen3 235B (instruct/thinking/VL/next), DeepSeek V3.2, venice-uncensored 1.2, GLM 4.6/4.7, Kimi K2.5, Mistral Small 2603, MiniMax M27, Gemma 4 26B. Supports tools/tool_choice and stream:true SSE."},"/chat-pro":{"price":"$0.01","models":["arcee-trinity-large-thinking","claude-sonnet-4-5","claude-sonnet-4-6","deepseek-v4-flash","deepseek-v4-pro","gemini-3-1-pro-preview","gemini-3-5-flash","grok-4-20","grok-4-20-multi-agent","grok-4-3","kimi-k2-6","openai-gpt-4o-2024-11-20","openai-gpt-52","openai-gpt-52-codex","openai-gpt-53-codex","openai-gpt-54","openai-gpt-54-mini","qwen-3-6-plus","qwen-3-7-max","qwen3-5-397b-a17b","qwen3-coder-480b-a35b-instruct-turbo","z-ai-glm-5-turbo","z-ai-glm-5v-turbo","zai-org-glm-5-1"],"default_model":"kimi-k2-6","description":"Pro-tier reasoning & code. Kimi K2.6, Qwen3-Coder 480B, Qwen3.6 Plus, Grok-4 family (4-20, 4-3), DeepSeek V4 Flash, Arcee Trinity Large Thinking, OpenAI gpt-54-mini and gpt-53-codex. OpenAI-compatible. Supports tools/tool_choice and stream:true SSE."},"/chat-max":{"price":"$0.20","models":["claude-opus-4-5","claude-opus-4-6","claude-opus-4-7","claude-opus-4-8","openai-gpt-55"],"default_model":"claude-opus-4-8","description":"Frontier-flagship reasoning. Claude Opus 4.5 / 4.6 / 4.7 / 4.8 and OpenAI gpt-55. Output is hard-capped at 4096 tokens to keep the fixed price margin-safe on $30-$37.50/1M models. OpenAI-compatible. Supports tools/tool_choice and stream:true SSE."},"/tts-nano":{"price":"$0.005","models":["tts-kokoro"],"default_model":"tts-kokoro","description":"Cheapest TTS on x402 Bazaar. POST text, get back MP3 audio. tts-kokoro (open-weights, fast, multi-voice). 1000-char input cap. Returns audio/mpeg binary directly — no JSON wrapper to decode."},"/tts-pro":{"price":"$0.08","models":["tts-chatterbox-hd","tts-elevenlabs-turbo-v2-5","tts-inworld-1-5-max","tts-orpheus","tts-xai-v1"],"default_model":"tts-elevenlabs-turbo-v2-5","description":"Premium TTS. ElevenLabs Turbo v2.5 (default), Orpheus, Chatterbox HD, Grok xAI voice, Inworld 1.5 Max. 500-char input cap. Returns audio/mpeg binary."},"/image-nano":{"price":"$0.02","models":["chroma","lustify-sdxl","lustify-v7","lustify-v8","qwen-image","venice-sd35","wai-Illustrious","z-image-turbo"],"default_model":"venice-sd35","description":"Cheapest image generation on x402 Bazaar. Stable Diffusion 3.5 (default), Lustify SDXL/v7/v8, Qwen Image, Chroma, WAI Illustrious, Z-Image Turbo. Returns JSON {images: [base64-webp]}."},"/image-pro":{"price":"$0.15","models":["flux-2-max","flux-2-pro","hunyuan-image-v3","imagineart-1.5-pro","qwen-image-2","qwen-image-2-pro","recraft-v4","seedream-v4","seedream-v5-lite","wan-2-7-pro-text-to-image","wan-2-7-text-to-image"],"default_model":"flux-2-pro","description":"Premium image generation. Flux 2 Pro (default) / Flux 2 Max, Hunyuan v3, Qwen Image 2 / 2-Pro, Recraft v4, Seedream v4 / v5-Lite, Wan 2.7 / Wan 2.7 Pro, ImagineArt 1.5 Pro. Returns JSON {images: [base64]}."},"/embeddings":{"price":"$0.005","models":["text-embedding-3-large","text-embedding-3-small","text-embedding-bge-en-icl","text-embedding-bge-m3","text-embedding-multilingual-e5-large-instruct","text-embedding-nemotron-embed-vl-1b-v2","text-embedding-qwen3-0-6b","text-embedding-qwen3-8b"],"default_model":"text-embedding-bge-m3","description":"Text embeddings on x402 Bazaar. OpenAI-compatible /embeddings. POST {input, model?} where input is a string or array of strings (combined length capped at 24000 chars). Default BGE-M3; also Qwen3 8B/0.6B, multilingual E5, Nemotron VL, OpenAI text-embedding-3 small/large, BGE-en-icl. Returns JSON {data:[{embedding:[...]}], usage}."},"/upscale":{"price":"$0.15","models":["upscaler"],"default_model":"upscaler","description":"AI image upscale & enhance. POST {image (base64), scale 1-4, enhance?, enhanceCreativity?, enhancePrompt?, replication?}. Scale 1 requires enhance=true (enhancer-only). Returns binary image/png. Source image must be >= 65536px and < 25MB."},"/background-remove":{"price":"$0.06","models":["bria-bg-remover"],"default_model":"bria-bg-remover","description":"AI background removal. POST {image (base64)} or {image_url}. Returns a binary image/png with transparent background. Source < 25MB."},"/transcribe":{"price":"$0.05","models":["fal-ai/wizper","nvidia/parakeet-tdt-0.6b-v3","openai/whisper-large-v3","stt-xai-v1"],"default_model":"openai/whisper-large-v3","description":"Speech-to-text on x402 Bazaar. POST multipart/form-data with a `file` audio upload (WAV/FLAC/M4A/MP3/OGG/WEBM). Whisper Large v3 (default), NVIDIA Parakeet, fal Wizper, xAI STT. Optional model/response_format/timestamps/language fields. Returns JSON {text, duration, timestamps?}. Hard cap 300s of audio per request (longer → 400, so check duration before paying)."}},"usage":"POST to any tier with OpenAI-compatible body {messages, model?, max_tokens?, temperature?, tools?, tool_choice?, stream?}","streaming":"stream:true is accepted and SSE is passed through from Venice. CDP facilitator behavior with streaming responses is untested; payment is settled after the upstream response begins.","docs":"/docs"}