{"schema":"postcutoff/model@1","as_of":"2026-10-20T07:28:00+02:00","url":"https://postcutoff.com/m/mercury-3/","md":"https://postcutoff.com/m/mercury-3/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"mercury-3","name":"Mercury 3","org":"Inception","family":"Mercury","released":"2026-10-19","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":1000000,"max_output":131072,"knowledge_cutoff":null,"pricing":{"input":0.2,"output":0.7,"unit":"per 1M tokens (list price; 50% launch discount brings it to $0.10 / $0.35, end date not stated; cached input $0.02, $0.01 at launch)","source":"https://docs.inceptionlabs.ai/get-started/models"},"price_line":"$0.20 in, $0.70 out per 1M tokens","access":[{"provider":"Inception API (OpenAI-compatible)","model_id":"mercury-3","endpoint":"https://api.inceptionlabs.ai/v1/chat/completions","docs":"https://docs.inceptionlabs.ai/get-started/models"},{"provider":"OpenRouter","model_id":"inception/mercury-3","url":"https://openrouter.ai/inception/mercury-3"},{"provider":"Baseten","url":"https://www.baseten.co/"},{"provider":"Vercel","url":"https://vercel.com/"},{"provider":"Web app","url":"https://chat.inceptionlabs.ai"}],"capabilities":[{"name":"Diffusion LLM with 1M-token context","detail":"Generates and refines many tokens in parallel; Inception claims 1,068 tokens/s on Nvidia GPUs, 4–8x faster than GPT-6 Luna and Claude Haiku 5.5, with a 1M-token context (up from 260K in Mercury 2.5).","first":false,"discovered":"launch","source":"https://www.inceptionlabs.ai/blog/introducing-mercury-3"},{"name":"Reasoning effort levels and tool calling","detail":"instant, low, medium and high reasoning effort; tool calling and structured outputs; temperature 0.5–1.0 (Inception docs).","first":false,"discovered":"launch","source":"https://docs.inceptionlabs.ai/get-started/models"}],"entry":"2026-10-19-inception-mercury-3","notes":"Inception says it beats GPT-6 Luna and Claude Haiku 5.5 on \"a range of benchmarks\" but published no scores; independent numbers not yet available on Oct 20. OpenRouter lists 1M context at $0.10/$0.35 (launch price). 100M free API tokens for new accounts.","verified":"2026-10-20","body_md":"Fast, cheap model for agent sub-calls, search pipelines and voice, where latency matters more than peak intelligence.\n\nSources: [Inception blog](https://www.inceptionlabs.ai/blog/introducing-mercury-3) ·\n[Inception docs](https://docs.inceptionlabs.ai/get-started/models) ·\n[The Deep View](https://www.thedeepview.com/articles/why-inception-s-mercury-3-upends-ai-economics)","page_url":"https://postcutoff.com/m/mercury-3/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":2,"you_url":"https://postcutoff.com/you/mercury-3/","briefings":null}