Mercury

Model API

Family of diffusion large language models (Mercury 2.5, Mercury Voice, Mercury Router) served by an OpenAI-compatible API at over 1,000 tokens per second, priced per million tokens, for coding, agents, support and voice.

Find alternatives to Mercury

TypeModel API

RoleHosted model API

Bought forBuild on a hosted model API

AvailabilitySold

DeploymentSaaS

Intended forDeveloper, Enterprise

SecurityNot recorded

StatusActive

Sold withinSold on its own

PricingFreemium, Usage-based, Enterprise quote — official pricing ↗

Pricing, Deployment, Sold within — inceptionlabs.ai · 11 Oct 2026

What it does

Text generation
Model inference
Code generation

Features 3

Mercury RouterUnderstands user prompts and routes tasks to the best models by quality, speed and cost.
OpenAI-compatible APIModels are OpenAI compatible and work as a drop-in replacement for traditional LLMs.
Tool use and structured outputThe Mercury 2.5 model lists reasoning, tool use and structured output among its features.

inceptionlabs.ai

Sources

Pricing

Pricing page · 11 Oct 2026

Models page read 2026-10-11: Mercury 2.5 input $0.04 and output $0.15 per 1M tokens (80% off list); Free plan with 100 million tokens; Developer usage-based; Enterprise custom.

Description

Official documentation · 11 Oct 2026

Models page: "Inception's diffusion LLMs (dLLMs) deliver frontier LLM quality at 5x greater speed"; "OpenAI compatible and a drop-in replacement for traditional LLMs".

What it does

Official documentation · 11 Oct 2026

Models page: "Inception's diffusion LLMs (dLLMs) deliver frontier LLM quality at 5x greater speed"; "OpenAI compatible and a drop-in replacement for traditional LLMs".

Sold within