{"name":"hivecompute-mcp","version":"1.0.0","description":"OpenAI-compatible inference router — pay per token in USDC on Base L2.","endpoint":"/mcp","transport":"streamable-http","protocol":"2024-11-05","homepage":"https://hivecompute-g2g7.onrender.com","icon":"https://www.thehiveryiq.com/favicon.ico","tools":[{"name":"compute.chat","description":"Run inference via Hive's OpenAI-compatible router. Submit a prompt or message array to any available model. Billed per input+output token in USDC on Base L2. Hive routes to the cheapest available model meeting your latency and quality spec."},{"name":"compute.embed","description":"Generate vector embeddings via Hive's embedding router. Billed per 1K input tokens in USDC on Base L2. Returns a float array suitable for semantic search, clustering, or RAG pipelines."},{"name":"compute.list_models","description":"Browse all models available through the Hive inference router — including per-token pricing in USDC, context window size, latency tier, and provider. No authentication required."},{"name":"compute.estimate_cost","description":"Estimate the USDC cost for a prompt before running inference. Returns cost breakdown by input tokens, output tokens, and routing fee. Helps agents budget before committing a payment."},{"name":"compute.get_usage","description":"Get an agent's compute usage history — total tokens consumed, total USDC spent, breakdown by model, and inference call log with timestamps."}],"prompts":[{"name":"find_cheapest_model","description":"Find the cheapest model available on HiveCompute that meets a given quality or capability requirement."},{"name":"estimate_inference_budget","description":"Estimate how many inferences an agent can run for a given USDC budget and prompt size."},{"name":"review_usage_spend","description":"Review recent compute spend and token usage for an agent on HiveCompute."}]}