{"apiVersion":"2026-07-26.4","description":"Low-price, agent-native x402 gateway. One wallet, one OpenAI-compatible API, many AI models. Pay per call in USDC — cheaper than BlockRun. No API keys, no accounts.","documentation":{"openapi":"https://api.clervo.dev/openapi.json","llms":"https://api.clervo.dev/llms.txt","quickstart":"https://api.clervo.dev/quickstart.md","skill":"https://api.clervo.dev/skill.md","prompt":"https://api.clervo.dev/prompt.txt","models":"https://api.clervo.dev/v1/models","catalog":"https://api.clervo.dev/v1/catalog"},"name":"Clervo x402 Gateway","network":"mainnet","payment":{"chain":"eip155:8453","facilitator":"coinbase-cdp","network":"base","scheme":"exact","token":"USDC","tokenAddress":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"},"resource":{"description":"Clervo x402 Gateway API","mimeType":"application/json","url":"https://api.clervo.dev"},"resources":["POST /v1/chat/completions","POST /v1/chat/completions/x402","GET /v1/models","GET /v1/catalog","GET /openapi.json","GET /llms.txt","GET /quickstart.md"],"services":[{"description":"OpenAI-compatible chat completions. 17 free models (no payment needed) + 19 paid models via x402 USDC.","endpoint":"/v1/chat/completions","freeModels":[{"capabilities":["text","json"],"description":"Low-latency general text and JSON alias. Provider routing may change without changing the public model ID.","id":"clervo/fast","latencyMs":170,"name":"Clervo Fast"},{"capabilities":["text","json","reasoning"],"description":"Balanced reasoning and instruction-following alias for general agent workloads.","id":"clervo/smart","latencyMs":475,"name":"Clervo Smart"},{"capabilities":["text","json","reasoning"],"description":"Deeper reasoning alias for tasks where quality matters more than latency.","id":"clervo/deep","latencyMs":1073,"name":"Clervo Deep"},{"capabilities":["text","json"],"description":"Ultra-fast open model via Groq. 170ms latency. Free during launch.","id":"groq/llama-3.1-8b-instant","latencyMs":170,"name":"Llama 3.1 8B Instant (Groq)"},{"capabilities":["text","json","reasoning"],"description":"Large open model via Groq. Fast inference, strong reasoning.","id":"groq/llama-3.3-70b","latencyMs":800,"name":"Llama 3.3 70B (Groq)"},{"capabilities":["text","json","reasoning"],"description":"Large open model via SambaNova. Free tier.","id":"sambanova/llama-3.3-70b","latencyMs":1500,"name":"Llama 3.3 70B (SambaNova)"},{"capabilities":["text","json","reasoning"],"description":"Qwen 3.6 27B (Groq) — fast inference via Groq. Free during beta.","id":"groq/qwen3.6-27b","latencyMs":213,"name":"Qwen 3.6 27B (Groq)"},{"capabilities":["text","json","reasoning","code"],"description":"GPT-OSS 120B (Groq) — fast inference via Groq. Free during beta.","id":"groq/gpt-oss-120b","latencyMs":419,"name":"GPT-OSS 120B (Groq)"},{"capabilities":["text","json"],"description":"GPT-OSS 20B (Groq) — fast inference via Groq. Free during beta.","id":"groq/gpt-oss-20b","latencyMs":181,"name":"GPT-OSS 20B (Groq)"},{"capabilities":["text","json","reasoning","code"],"description":"Nemotron 3 Ultra 550B (Nvidia) — hosted on Nvidia NIM. Free during beta.","id":"nvidia/nemotron-ultra-550b","latencyMs":674,"name":"Nemotron 3 Ultra 550B (Nvidia)"},{"capabilities":["text","json","reasoning"],"description":"Nemotron 3 Super 120B (Nvidia) — hosted on Nvidia NIM. Free during beta.","id":"nvidia/nemotron-super-120b","latencyMs":766,"name":"Nemotron 3 Super 120B (Nvidia)"},{"capabilities":["text","json","reasoning"],"description":"Nemotron 3 Nano 30B (Nvidia) — hosted on Nvidia NIM. Free during beta.","id":"nvidia/nemotron-nano-30b","latencyMs":1082,"name":"Nemotron 3 Nano 30B (Nvidia)"},{"capabilities":["text","json","reasoning","code"],"description":"DeepSeek V4 Flash (Nvidia) — hosted on Nvidia NIM. Free during beta.","id":"nvidia/deepseek-v4-flash","latencyMs":13000,"name":"DeepSeek V4 Flash (Nvidia)"},{"capabilities":["text","json","code"],"description":"Meta Llama 4 Maverick 17B 128-expert MoE — hosted on Nvidia NIM. Free during beta.","id":"nvidia/llama-4-maverick-17b","latencyMs":426,"name":"Llama 4 Maverick 17B (Nvidia)"},{"capabilities":["text","json","code"],"description":"Google Gemma 4 31B instruction-tuned — hosted on Nvidia NIM. Free during beta.","id":"nvidia/gemma-4-31b","latencyMs":532,"name":"Gemma 4 31B (Nvidia)"},{"capabilities":["text","json","code"],"description":"Mistral Small 4 119B — hosted on Nvidia NIM. Free during beta.","id":"nvidia/mistral-small-4-119b","latencyMs":563,"name":"Mistral Small 4 119B (Nvidia)"},{"capabilities":["text","json","reasoning","code"],"description":"MiniMax M3 reasoning model — hosted on Nvidia NIM. Free during beta.","id":"nvidia/minimax-m3","latencyMs":1139,"name":"MiniMax M3 (Nvidia)"}],"method":"POST","name":"Multi-Model Chat Completions","paidModels":[{"capabilities":["text","json","code"],"description":"Code generation and software-engineering alias with replaceable provider routing.","id":"clervo/code","latencyMs":2600,"name":"Clervo Code","price":{"amount":0.015,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.4-mini","latencyMs":3000,"name":"GPT 5.4 Mini (QuickAI label)","price":{"amount":0.005,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.4","latencyMs":3000,"name":"GPT 5.4 (QuickAI label)","price":{"amount":0.018,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.5","latencyMs":3000,"name":"GPT 5.5 (QuickAI label)","price":{"amount":0.035,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.6-luna","latencyMs":3000,"name":"GPT 5.6 Luna (QuickAI label)","price":{"amount":0.007,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.6-terra","latencyMs":3000,"name":"GPT 5.6 Terra (QuickAI label)","price":{"amount":0.018,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Provider-reported model label observed in a bounded authenticated QuickAI test.","id":"quickai/gpt-5.6-sol","latencyMs":3000,"name":"GPT 5.6 Sol (QuickAI label)","price":{"amount":0.035,"currency":"USD","unit":"request"}},{"capabilities":["text","json","fast"],"description":"Fast affordable Claude model. 10% below BlockRun pricing.","id":"tongkhokr/claude-haiku-4.5","latencyMs":1017,"name":"Claude Haiku 4.5","price":{"amount":0.002,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Balanced Claude model. 10% below BlockRun pricing.","id":"tongkhokr/claude-sonnet-5","latencyMs":2600,"name":"Claude Sonnet 5","price":{"amount":0.015,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Most powerful Claude model. 10% below BlockRun pricing.","id":"tongkhokr/claude-opus-5","latencyMs":2700,"name":"Claude Opus 5","price":{"amount":0.084,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Balanced Claude model. Great for coding and reasoning.","id":"tongkhokr/claude-sonnet-4.6","latencyMs":2500,"name":"Claude Sonnet 4.6","price":{"amount":0.015,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Powerful Claude for complex reasoning. 1M context.","id":"tongkhokr/claude-opus-4.7","latencyMs":2800,"name":"Claude Opus 4.7","price":{"amount":0.084,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Anthropic Claude Opus 4.8 via TongKhokr gateway. 10% below BlockRun pricing.","id":"tongkhokr/claude-opus-4.8","latencyMs":2000,"name":"Claude Opus 4.8","price":{"amount":0.084,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Flagship reasoning and code model. Highest capability tier for hard problems and long-horizon agent work.","id":"clervo/opus-5","latencyMs":2700,"name":"Clervo Opus 5","price":{"amount":0.084,"currency":"USD","unit":"request"}},{"capabilities":["text","json","reasoning","code"],"description":"Balanced high-capability model for production reasoning, code and general agent workloads.","id":"clervo/sonnet-5","latencyMs":2600,"name":"Clervo Sonnet 5","price":{"amount":0.015,"currency":"USD","unit":"request"}},{"capabilities":["text","json","fast"],"description":"Cheapest paid tier. Fast, capable model for high-volume agent tasks.","id":"clervo/haiku-4.5","latencyMs":1017,"name":"Clervo Haiku 4.5","price":{"amount":0.002,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Budget GPT-class model for everyday completions and tool calls.","id":"clervo/gpt-mini","latencyMs":3000,"name":"Clervo GPT Mini","price":{"amount":0.005,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Full GPT-class model for general reasoning and generation.","id":"clervo/gpt","latencyMs":3000,"name":"Clervo GPT","price":{"amount":0.018,"currency":"USD","unit":"request"}},{"capabilities":["text","json"],"description":"Highest GPT-class tier for demanding generation and analysis.","id":"clervo/gpt-max","latencyMs":3000,"name":"Clervo GPT Max","price":{"amount":0.035,"currency":"USD","unit":"request"}}]}],"version":1,"x402Features":["exact-payment","per-request-pricing","idempotency","receipts","operation-tracking"],"x402Version":2}