Last refreshed 2026-05-19. Next refresh: weekly.
Why use Mercury 2 on OpenRouter?
OpenRouter offers Mercury 2 with pay-as-you-go pricing at $0.25/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.
Compare Mercury 2 across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: inception/mercury-2inception/mercury-2Request example
inception/mercury-2.Gotchas
- Use provider model ID "inception/mercury-2", not the LLMReference slug "mercury-2".
Compare Mercury 2 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.25 | $0.75 |
| Vercel AI Gateway | $0.25 | $0.75 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.25 |
| Output tokens | $0.75 |
Capabilities
About Mercury 2
Inception Labs' Mercury 2 is a commercial-scale diffusion-based language model (dLLM) released February 2026. Unlike autoregressive transformers, Mercury uses a diffusion architecture for faster inference. Designed for code generation, reasoning, and analysis tasks. Proprietary, available via the Inception API.
FAQ
What does Mercury 2 cost on OpenRouter?
On OpenRouter, Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens.
What is the context window for Mercury 2 on OpenRouter?
Mercury 2 supports a 128k token context window on OpenRouter.
How does OpenRouter compare to other Mercury 2 providers?
Mercury 2 is available from 2 providers. The cheapest input pricing is $0.25/1M tokens from OpenRouter.
What API model ID do I use for Mercury 2 on OpenRouter?
Use the model ID inception/mercury-2 when calling OpenRouter's API.
Who created Mercury 2?
Mercury 2 was created by Inception Labs as part of the Mercury model family.
Is Mercury 2 open source?
Mercury 2 is not open source; the seed data lists it as proprietary.