Skip to content
LLMs
Inception logo

Inception: Mercury 2.5

by Inception

Inception: Mercury 2.5 is a large language model from Inception. It costs $0.040 per million input tokens and $0.150 per million output tokens. Its context window is 260K tokens.

ReasoningTool callingStructured outputPrompt caching
Input / 1M tokens
$0.040
Output / 1M tokens
$0.150
Cached input / 1M
$0.0040

On repeated prefixes

Context window
260K

tokens

Who serves it cheapest

1 hosts serve Mercury 2.5. Same weights, same API - the price difference is pure margin and routing.

Providers serving Inception: Mercury 2.5, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
InceptionCheapest$0.040$0.150260K-100.0%

About Mercury 2.5

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...

Specifications

Inception: Mercury 2.5 specifications
Model IDinception/mercury-2.5
ProviderInception
Context window260K tokens
Max output66K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsNo
ReleasedSeptember 8, 2026

Cheaper alternatives

Models that cost less than Mercury 2.5 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Inception: Mercury 2.5 cost?

$0.040 per million input tokens and $0.150 per million output tokens. Cached input reads cost $0.0040 per million tokens.

What is the context window of Inception: Mercury 2.5?

260K tokens, with up to 66K tokens of output per request.