Mercury 2
Mercury 2 is Inception's reasoning diffusion language model. It refines tokens in parallel with tunable reasoning depth, native tool use, and a context window of 128K tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'inception/mercury-2', prompt: 'Why is the sky blue?'})Playground
Try out Mercury 2 by Inception. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Mercury 2
Ask Mercury 2 anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Inception | 128K | 0.4s | $0.25/M | $0.75/M | Read:$0.03/M Write:— | — | — | +1 | 02/24/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
About Mercury 2
Mercury 2 departs from the autoregressive strategy that defines most large language models (LLMs). Instead of producing one token at a time left to right, Mercury 2 operates on a diffusion principle. It starts with a rough draft of the full response and refines multiple tokens in parallel across a small number of steps. Mercury 2 generates faster than autoregressive approaches. Live metrics on this page show current rates.
Mercury 2 supports tunable reasoning depth. You adjust refinement steps up or down to trade latency for quality on each request. Native tool use and schema-aligned JSON output let you embed it in function-calling pipelines and structured extraction workflows without extra parsing layers.
With a context window of 128K tokens, OpenAI API compatibility, and pricing of $0.25 input / $0.75 output per million tokens, Mercury 2 fits production-scale agentic workloads where inference runs dozens of times per task. Teams building multi-step coding assistants, retrieval-augmented generation (RAG) pipelines, or real-time voice interfaces gain headroom to run more refinement iterations within a fixed latency budget.
What To Consider When Choosing a Provider
- Configuration: Mercury 2's diffusion architecture generates tokens in parallel rather than sequentially. Latency differs from autoregressive models, so factor that into timeout and streaming configurations for latency-sensitive pipelines.
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Mercury 2
Best For
- Sequential agent loops: Chains of many inference calls need low per-step latency
- Real-time voice backends: Response delay is perceptible to end users
- High-throughput coding assistants: Many simultaneous requests processed concurrently
- Fast structured RAG: Retrieval summarization returned as JSON output
- Token cost optimization: Diffusion-based parallel token refinement reduces per-token inference cost compared to autoregressive models
Consider Alternatives When
- Very long outputs: Tasks push against the cap of 128K tokens
- Domain-specific benchmarks: Evaluation prioritizes specific benchmarks over raw throughput
- Token-by-token streaming: Pipeline assumes autoregressive generation patterns
- Multimodal input required: You need image or audio input alongside text reasoning
Conclusion
Mercury 2 brings a different execution model to production reasoning workloads. Diffusion-based parallel refinement keeps throughput high while preserving tool calling, structured output, and tunable reasoning depth. If inference latency or per-call cost limits how you scale your product, use Mercury 2 on Vercel AI Gateway. Open https://ai-sdk.dev/playground/inception:mercury-2 to try it interactively.