Mercury 2.5

by InceptionChat

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception

Context
260K tokens
Max output
65,536 tokens
Released
2026-09-08
Weights
Closed

Feed

inception/mercury-2-5 · also seen as inception/mercury-2.5-20260908

Specifications

Full facts as recorded, incl. what is unknown.

Released
2026-09-08
Weights
Closed
Input
Text
Output
Text
Context window
260,000 max across endpoints
Max output
65,536
Providers
3 + 3 gateways, not counted as providers
Epoch Capabilities Index
not evaluated
Direct price range
$0.040–$0.275 in · $0.15–$1.03 out per 1M tokens · across all 3 providers
More details
Last updated
2026-09-10
Knowledge cutoff
2025-11-01

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured output
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt caching
  • Web searchunknown
  • Computer useunknown
  • System messages
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

Atom feed

No change since 19 Oct 2026. The cheapest direct price has been $0.04 in / $0.15 out per 1M tokens at Inception on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

Similarly priced models

Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).

ModelBlended/1MIn/1MOut/1MContextvs Mercury 2.5
Seed 1.6 VisionByteDance Seed$0.292$0.12$1.15256K+0%
deepseek-v3-0324DeepSeek$0.295$0.20$0.77164K+1%
Qwen-VL MaxAlibaba (Qwen)$0.288$0.23$0.58131K−1% cheaper
Seed 1.6 VisionByteDance Seed$0.286$0.114$1.14256K−2% cheaper
GLM 5.3 Flash UncensoredZ.ai (Zhipu AI)$0.30$0.20$0.801.05M+3%
DeepSeek V3.1DeepSeek$0.283$0.20$0.70164K−3% cheaper
Qwen3.5 397B-A17BAlibaba (Qwen)$0.301$0.164$0.986262K+3%
Qwen3.6 FlashAlibaba (Qwen)$0.303$0.165$0.991M+4%

More from Inception

Newest Inception models in the catalogue. All Inception models

ModelReleasedContextListed price
Mercury Decide2026-09-3065.5Kunpriced
Mercury 2.5 Preview2026-09-01260K$0.04 via NanoGPT
Mercury Edit 22026-03-3032Kfrom $0.25
Mercury 22026-02-24128Kfrom $0.25
Mercury Coder Small Beta2024-01-0132.8K$0.25 via NanoGPT
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model