Inception: Mercury 2

Public pricingIntelligence 79/100Medium memoryगहरी सोच

Inception: Mercury 2 एक टेक्स्ट मॉडल है, जिसे तर्क और समस्या समाधान के लिए बनाया गया है। यह गहरी तर्कशक्ति और योजना، कम latency और efficient inference, 128K tokens का context और कम लागत profile जोड़कर reasoning, analysis, and hard problem solving में भरोसेमंद काम करता है। यह तब व्यावहारिक विकल्प है जब latency, cost और throughput महत्वपूर्ण हो, खासकर उन टीमों के लिए जिन्हें स्थिर output,

Input

$0.25/1M

Output

$0.75/1M

Cached

$0.03/1M

Batch

$0.10/1M

Calculate your Mercury 2 bill.

Set your workload — see cost at your exact volume.

What would Mercury 2 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Mercury 2 at a glance.

Memory

128,000

tokens

Max reply

50,000

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

—

Released

Jan 2026

Training cutoff

Sep 2025

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Mercury 2

  • Multi-step reasoning, research agents, or hard math.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.
  • You need tool-use / function calling for agent workflows.

Alternatives

Similar models to compare.

FAQ

Mercury 2 — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Mercury 2 costs roughly $49 per month. Input is $0.25 /1M tokens and output is $0.75 /1M tokens.
Mercury 2 has a 128,000-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,000 words of input and history in a single call.
Beyond text generation, Mercury 2 supports deep step-by-step reasoning, strict JSON output. It streams replies by default.
Mercury 2 was released in January 2026, with training data cut off around September 2025.
Models in a similar class include Seed 1.6, Seed-2.0-Lite, Gemini 3.1 Flash Lite Preview. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Mercury 2 against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard