LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mercury 2

inception·inception/mercury-2·GA·Closed·mercury series
Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Inception
$0.25 / $0.75
Blended $0.38 · Cache read $0.025
Lowest paid·InceptionGateway
$0.25 / $0.75
Blended $0.38 · 1× spread
Context
128,000
Output limit
50,000
Knowledge cutoff
2025-01-01
Released / updated
2026-02-24 / 2026-02-24
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text

Mercury 2 by inception is offered by 2 providers on this page. Its official list price is $0.25 per 1M input tokens and $0.75 per 1M output tokens. No paid channel is priced below the official list price.

Median output speed is 563 tokens per second, with 8.59s to the first token.

The context window is 128,000 tokens, with an output limit of 50,000 tokens. It supports reasoning, tool use, and structured output. Its training knowledge cuts off at 2025-01-01.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed563 tok/s
TTFT8.59 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • InceptionOfficialGateway
    $0.25 / $0.75
    Cache read $0.025Context 128,000Output limit 50,000
  • NanoGPTGateway
    $0.25 / $0.75
    Cache read $0.025Context 128,000Output limit 50,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
InceptionOfficialGateway$0.25$0.75$0.025—128,00050,000
NanoGPTGateway$0.25$0.75$0.025—128,00050,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = high

1 / 2 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Inception · Official$60.50
2NanoGPT$60.50
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.75$02026-08-052026-08-13
2026-08-13Input list $0.25Output list $0.75Min blended $0.38

Related models

Mercury 3same series$0.10 / $0.35Mercury 2.5same series$0.20 / $0.75Mercury 2.5 Previewsame series—Claude Haiku 5.5cheaper alternative$0.10 / $0.50Gemma 4 31B ITcheaper alternative$0 / $0GPT-6 Lunacheaper alternative$0.10 / $0.50MiMo-V2.6-Flashcheaper alternative$0.14 / $0.28Mercury Coder Smallsame lab—
Data partly from models.dev (MIT) · Inception official docs ↗