LIVE Cheapest paid: Granite 4.0 Micro $0.017/Mtok in 173 models tracked Updated Jul 10, 2026
Jul 10, 2026
ModelPriceWatch$/Mtok
Pricing / Moonshot / Kimi K2.6

Kimi K2.6

by Moonshot

Current mid tier Open weights mid tier

Pricing · per 1M tokens

Input
$0.950
per million tokens
Output
$4.00
per million tokens
Cached input$0.160/Mtok (17% of input — prompt caching)
Blended avg cost*$2.48/Mtok

Available on 2 hosts · cheapest first

Kimi K2.6 is sold by 2 providers. Prices are per 1M tokens (blended = avg of input & output). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

Host Input Output Blended vs first-party
Fireworks details → $0.950 $4.00 $2.48 0%
Moonshot first-party $0.950 $4.00 $2.48

Each host links to its provider page and official pricing. Prices refresh twice daily.

Overview

Kimi's latest multimodal model. $0.95/$4.00 per 1M; cached $0.16.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

Input 3/5
Text ✓ Image ✓ Audio Video ✓ PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 4/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal ✓ Web search Realtime

Benchmark performance

GPQA Diamond
60%
AIME 2025
62%
SWE-Bench
40%
Humanity's Last Exam
20%
ARC-AGI 2
22%
MMMLU
76%
HumanEval
82%
MATH 500
72%
BFCL
65%
Independent composite scores
  • LMSYS Chatbot Arena: 1461.2 ELO (human preference)
  • Artificial Analysis Intelligence Index: 42.8
How it stacks up
  • Strongest at AIME 2025 — 62%, #30 of 58
Inference speed: 90 tokens/sec

Source: Moonshot model card · Updated Apr 1, 2026 · See full rankings →

Specifications

ProviderMoonshot
Context window262K tokens
Modalitytext, image, video
ParametersProprietary
Open sourceYes — open weights available
ReleasedOct 1, 2025
StatusCurrent
Last updatedJun 25, 2026
Tagsopen-weights mid-tier caching multimodal

Cost calculator

1K tokens (in)$0.00095
1K tokens (out)$0.004
100K tokens (in)$0.095
100K tokens (out)$0.400
1M tokens (in)$0.950
1M tokens (out)$4.00
10M tokens (blended)$24.75
Full calculator →

At a glance

Input$0.950/M
Output$4.00/M
Blended$2.48/M
Context262K
Tiermid

Embed this price

A live, auto-updating badge for your README or docs:

Kimi K2.6 live API price

Price history

Last updated: Jul 10, 2026 · price links to the official provider pricing page (source above)

No price changes detected — this model's pricing has been stable since we began tracking it.

Compare Kimi K2.6

Related models