Moonshot AI: Kimi K2.5

Public pricingIntelligence 82/100Large memoryVisionRéflexion approfondieOutils

MoonshotAI: Kimi K2.5 est un modèle multimodal conçu pour codage, génie logiciel et workflows agentiques. Il associe la gestion multimodale des entrées et de bonnes performances en codage, un contexte de 262K tokens et un profil à coût équilibré pour un travail fiable sur codage, génie logiciel et workflows agentiques.

Input

$0.44/1M

Output

$2.00/1M

Cached

$0.22/1M

Batch

$0.30/1M

Calculate your Kimi K2.5 bill.

Set your workload — see cost at your exact volume.

What would Kimi K2.5 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Kimi K2.5 at a glance.

Memory

262,144

tokens

Max reply

65,535

tokens

Memory tier

Large

an entire book or large codebase

Tokenizer

—

Released

Jan 2026

Training cutoff

Oct 2025

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • aa_intelligence_index

    47

  • frontiermath_tier_4

    4.2

  • gpqa_diamond

    87.6

  • humanitys_last_exam

    24.37

  • swe_bench_verified

    76.8

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 Kimi K2.5

  • Multi-step reasoning, research agents, or hard math.
  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • Long documents, full codebases, or extensive chat histories.

When to look elsewhere

  • Very latency-sensitive, real-time apps where every millisecond counts.

Alternatives

Similar models to compare.

FAQ

Kimi K2.5 — 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, Kimi K2.5 costs roughly $113 per month. Input is $0.44 /1M tokens and output is $2.00 /1M tokens.
Kimi K2.5 has a 262,144-token context window (large memory — an entire book or large codebase). That means you can fit about 49,152 words of input and history in a single call.
Beyond text generation, Kimi K2.5 supports understanding images, deep step-by-step reasoning, calling functions / tools, strict JSON output. It streams replies by default.
Kimi K2.5 was released in January 2026, with training data cut off around October 2025.
Models in a similar class include Gemini 3 Flash Preview, Gemini 2.5 Flash, Gemini 3.1 Flash Lite Preview. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Kimi K2.5 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