model comparison

vs

Mercury 3 vs Mercury 2.5

two Inception models, compared on listed price, real workload cost, context and capabilities.

the short answer

  • Mercury 3 lists lower input and output prices.
  • Mercury 3 offers the larger context window.
  • Mercury 3 reads cached input for less ($0.01/M against Mercury 2.5's $0.02/M), which decides the bill for agents that resend long context.
  • Mercury 2.5 retired on 4 November 2026; its numbers are kept for reference.

side-by-side specs

specMercury 3Mercury 2.5
providerInceptionInception
input price$0.1/M$0.2/M
output price$0.35/M$0.75/M
cached input$0.01/M$0.02/M
blended price (3:1)$0.163/M$0.338/M
context window1M tokens260k tokens
max output131.072k tokens65.536k tokens
inputtexttext
structured outputyesyes
weightsclosedclosed
releasedOctober 2026September 2026
availabilityretires 28 December 2026retired 4 November 2026

same work, both models

workloadMercury 3Mercury 2.5
one chat reply3,000 tokens in, 500 outMercury 2.5 costs 2.1× as much as Mercury 3$0.00048$0.00098
summarise a 100-page report50,000 tokens in, 1,500 out, one requestMercury 2.5 costs 2.0× as much as Mercury 3$0.0055$0.01
1,000 classification calls500 tokens in, 20 out, per call$0.06$0.12
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$0.22$0.45
same session, cached85% of input read from the prompt cache, the rest written to it$0.07$0.14

at listed rates. token counts are typical sizes, not measurements.

Mercury 3 pricing notes

  • the listed price is Inception's 50% launch rate; the standard rate is $0.20 / $0.70, and no end date is announced.
  • cached input bills at $0.01 per 1M tokens, 90% off the input rate.

Mercury 2.5 pricing notes

  • the 80% launch rate ($0.04 / $0.15) has ended; the listed price is Inception's standard rate.
  • prompt caching is automatic; cached input bills at $0.02 per 1M tokens.

when to pick which

Mercury 3

Inception's Mercury 3 is a text-only diffusion llm with selectable reasoning effort and a 1M-token context window. it replaces Mercury 2.5 at lower input and output rates, with the window up from 260K tokens.

pick it if

  • you need low-cost text work across contexts up to 1M tokens
  • latency matters; Inception cites 1,068 tokens/s on NVIDIA GPUs
  • your prompts repeat, so cached input bills at a tenth of input

skip it if

  • you need image input
  • you need stable long-term rates; the launch discount has no announced end date

Mercury 2.5

Inception's previous-generation diffusion llm from September 2026, text-only, with tunable reasoning and a 260K context window. it retires on 2026-11-04; Mercury 3, the current generation, has lower input and output rates.

pick it if

  • you need fast text generation with reasoning and schema-aligned JSON
  • your prompts repeat, so cached input bills at a tenth of input

skip it if

  • Mercury 3 costs less on both rates and has a 1M window
  • you need image input

faq

which is cheaper, Mercury 3 or Mercury 2.5?

Mercury 3 lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Mercury 3 costs $0.22 and Mercury 2.5 $0.45.

which has the larger context window?

Mercury 3 offers the larger context window. Mercury 3: 1M tokens; Mercury 2.5: 260k tokens.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18