AI Agent StoreInception · Catalog verified
Mercury 3
A text model designed for responsive chat and tool-driven tasks. Compare it on your own examples before choosing it for a speed-sensitive workflow.
Released 2026-10-19 · Catalog added 2026-10-16 UTC · Checked 2026-11-03. Catalog addition and provider launch are separate dates.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: inception/mercury-3. Text input and output, tool calling and structured answers. OpenRouter lists none/low/medium/high and defaults to medium. The native API instead names its fastest setting instant and defaults to low; choose the setting explicitly when comparing services.
Available thinking settings: none, low, medium, high. We do not yet have comparable independent results for these settings. The documented OpenRouter default is medium when effort is omitted. A default is not a recommendation for every task.
Available through Inception and hosted providers. Native instant/low/medium/high options do not establish equivalent behavior to OpenRouter’s none setting. Vendor speed claims and partner testimonials are not matched independent measurements.
Native, Gateway and OpenRouter list a 1,000,000-token context and up to 131,072 output tokens.
The current hosted quote matches the native launch discount: $0.10 input, $0.01 cached input and $0.35 output per million tokens. Native regular rates are $0.20/$0.02/$0.70; no end date for the discount is verified. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Inspect the exact catalog model ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗