Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for inception

Inception: Mercury 2.5

inception/mercury-2.5

Compare

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs. It delivers a 10+ point jump in intelligence over Mercury 2, comparable quality to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5. Mercury 2.5 supports tunable reasoning levels, parallel tool calls, and schema-aligned JSON output. It's built for production workloads where latency compounds: search agents, voice pipelines, and coding subagents. Read more in the blog postOpens in new tab.

Modalities
In / Out Price
80% off
$0.04 / $0.15per 1M
Context
260K
Released
Sep 8, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Inception: Mercury 2.5 (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisMercury 2.5 Intelligence Index12.3
Artificial AnalysisMercury 2.5 HLE11.8%
Artificial AnalysisMercury 2.5 AA-LCR71.7%
Artificial AnalysisMercury 2.5 GDPval-AA0.0%
Artificial AnalysisMercury 2.5 CritPt0.0%
Artificial AnalysisMercury 2.5 SciCode38.5%
Artificial AnalysisMercury 2.5 AA-Omniscience Accuracy22.7%
Artificial AnalysisMercury 2.5 AA-Omniscience Non-Hallucination Rate19.7%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
80% off
$0.20$0.04$0.75$0.15$0.02$0.0041.23s112 tps
100.00%
Throughput
112tok/s

P50, best across providers

Latency
1.23s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
96.00%

Availability over the last 3 days

Last 72 hours
Availability 96.00%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
96.42%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
11Btokens
2.
Favicon for https://omp.sh/
omp
new
4.68Btokens
3.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
2.95Btokens
4.
Favicon for https://postqode.ai/
PostQode
new
2.91Btokens
5.
Favicon for https://decodingtrust-agent.com/
DecodingTrust Agent Platform - jevagent
new
2.18Btokens

Frequently asked questions

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs.

Mercury 2.5 costs $0.04/M input tokens and $0.15/M output tokens, with separate rates for Cache Read at $0.004/M tokens.

Mercury 2.5 has a 260,000 token context window. It supports up to 65,536 completion tokens.

Yes. Mercury 2.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Mercury 2 is another text model from Inception.

Mercury 2.5 was released on September 8, 2026.

More models from inception

Mercury 2.5 Preview

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs. It delivers a 10+ point jump in intelligence over Mercury 2, comparable quality to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5. Mercury 2.5 supports tunable reasoning levels, parallel tool calls, and schema-aligned JSON output. It's built for production workloads where latency compounds: search agents, voice pipelines, and coding subagents.

Text260K context
Mercury 2

Mercury 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 >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. Mercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the blog post.

Text128K context$0.25 / $0.75
Mercury

Mercury 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 GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the [blog post] (https://www.inceptionlabs.ai/blog/introducing-mercury) here.

Text128K context
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 Haiku and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the blog post here.

Text128K context