Mercury 2
inception/mercury-2POST /v1/chat/completionsMercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
1 provider serves this model
Multigrid picks between them on every request using your policy. Each price is what that route costs us, and we add no spread of our own to it.
| Provider | Upstream model id | In / 1M | Out / 1M | Billing |
|---|---|---|---|---|
| OpenRouter | inception/mercury-2 | $0.2500 | $0.7500 | Credit |
We hold no direct key for inception, so every route above goes through OpenRouter. We do not buy tokens from them — we buy their credit, and a dollar of it costs $1.055. The rate shown here is their price with that 5.5% included, because that is what the route costs us. We add nothing on top of it.
The consequence, plainly: for this model we cannot be cheaper than OpenRouter. Their fee sits underneath ours. What you get here instead is one balance and one key across the whole catalogue, failover, spend caps and the audit trail — and if you already hold a inception contract, bring that key and we take nothing at all.
Call it
Same request shape as every other model in the catalogue.
const res = await client.chat.completions.create({
model: "inception/mercury-2",
messages: [{ role: "user", content: "Hello" }],
reasoning: { effort: "medium" },
});Send Mercury 2 a real request
Signing up takes no card and commits you to nothing — you start at a zero balance, so nothing can be charged until you decide to add credit. The playground opens on Mercury 2 and prices every answer as it arrives, at the rate shown above — what the route costs us, with nothing of ours added. Already have an account? The second button skips the form.