Mercury Coder

Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haik

Creator: Inception Labs
Lifecycle: Deprecated
Context: 128.0K
Max output: 32.0K
Released: Apr 30, 2025
Status: unknown

Input: $0.25 / 1M tokens
Output: $0.75 / 1M tokens
Cached read: $0.03 / 1M tokens
Cached write: — / 1M tokens
Batch discount: —%
Source: OpenRouter
Verified: Apr 5, 2026 (High)

Capabilities

Modalities: text→text
Capabilities: promptCachingfunctionCallingstructuredOutputs

Official Links

Intro

https://openrouter.ai/inception/mercury-coder

Docs

https://openrouter.ai/inception/mercury-coder

Pricing

https://openrouter.ai/models

Benchmark Coverage

Benchmark	Version	Score	Date	Source	Notes

Release History

Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
Mercury Coder	inception-mercury-coder	Deprecated	Apr 30, 2025	Apr 15, 2026	—	Model available via OpenRouter.

Host Coverage

Host	Type	Context	Pricing Note	Differences
OpenRouter	aggregator	128.0K	$0.25/1M in · $0.75/1M out via OpenRouter	—

Migration Guidance

Change Events

Date	Type	Title	Description	Source
Apr 30, 2025	family_added	Mercury Coder published	Model made available via OpenRouter.	OpenRouter

Other models from Inception Labs

Mercury, Mercury 2