Question 1

What is Mercury 2.5?

Accepted Answer

Mercury 2.5 is a model from Inception, released on Sep 8, 2026. 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...

Question 2

How much does Mercury 2.5 cost?

Accepted Answer

On the Respan gateway, input starts at $0.04 per 1M tokens on OpenRouter, and output starts at $0.15 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Mercury 2.5 on Respan?

Accepted Answer

Mercury 2.5 is served by OpenRouter.

Question 4

What is Mercury 2.5's context window?

Accepted Answer

Mercury 2.5 accepts up to 260K tokens of context.

Question 5

How do I use Mercury 2.5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "mercury-2.5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Mercury 2.5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 138 tokens per second, and the lowest response latency was 20.3 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Mercury 2.5 score on benchmarks?

Accepted Answer

Mercury 2.5 has 1 published benchmark score, including Terminal-Bench 4.0 0%. Each score links to where it was published; the data is collected by llmmetric.com.

Mercury 2.5

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Certified where it counts.

Coding1

Apps

Mercury 2.5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.