ModelPriceWatch.com
Last scan 2026-09-22 Models tracked 266 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Kimi K2.6

by Fireworks

Current mid tier open weights mid tier

Today's price · per 1M tokens

Input

$0.950

per 1M tokens

Output

$4.00

per 1M tokens

Blended

$1.71

blended $/1M — 3:1 weighted input:output

Cached input

$0.160

17% of input — prompt caching

Source: official Fireworks pricing · read MODELPRICEWATCH.COM · 2026-09-22

Price receipt

We read Fireworks's own pricing page on and found Kimi K2.6 listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 4f5353269c.

Kimi K2.6 is available on 2 hosts. See the full cheapest-first comparison on the consolidated Kimi K2.6 page →

Overview

Kimi K2.6 on Fireworks. $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

struck through = not supported
Input 3/4
Text Image Audio Video
Output
Text
Features 4/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score76.2%
Perf per $/Mtok44.5
GPQA Diamond
90.5%
SWE-Bench Verified vendor
40%
BrowseComp
83.2%
OSWorld-Verified
73.1%
Humanity's Last Exam
54%
ARC-AGI 2 vendor
22%
AIME 2025 vendor
62%
MMMLU vendor
76%
BFCL vendor
65%
HumanEval
80.2%
MATH 500 vendor
72%
AIME 2026 *
96.4%
Independent composite scores
  • AA Intelligence Index: 45.1 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA-Omniscience Index: 5.3 (−100–100)
How it stacks up
  • Ranks #21 of 84 benchmarked models by average score
  • Ranks #48 of 181 comparably-measured models by percentile score, across 7 independent measurements
  • Ranks #80 of 181 comparably-tested models by normalized performance per dollar
  • Strongest at Humanity's Last Exam — 54%, #13 of 65

90 tokens/sec output

Source: Artificial Analysis, Vellum LLM Leaderboard, Moonshot model card · updated · See full rankings →

Specifications

Provider
Fireworks
Context window
256K tokens
Modality
text, image, video
Parameters
Proprietary
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
open-weightsmid-tiercachingmultimodal

Availability verified: listed on Fireworks's own page