xpu liveBETA
Models›Kimi K2.6

Kimi K2.6

Model reference ↗

Model ranking

Arena Score
1455.4256945701
Arena reference rank
49
Evaluation configuration
Kimi K2.6
Source published
2026-11-19
Votes
39440
Confidence lower
1451.0031662511
Confidence upper
1459.8482228892
Last successful check
2026-11-22T14:00:05.877Z
Last value/rank change
2026-11-22T09:30:20.053Z
Methodology
Human preference — Text / overall; checked every six hours.

Source: Arena / LMArena ↗ · CC BY 4.0. Selection and catalog matching by XPU LIVE.

Pricing 1 Model information

Provider prices 1

Lowest input price per billing unit. Conditions in Details.

ProviderPriceProvider model IDStatusContext / max outputSource
Cloudflare Workers AIkimi-k2.6
Input$0.95
Output$4
USD / 1M tokensUpdated 2026-10-20
@cf/moonshotai/kimi-k2.6Catalog-listed
Conditions

Public catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine. Workers Paid or prepaid AI Gateway credits required.

Context tokens 262144Official source ↗2026-10-20

Kimi K2.6 is Moonshot AI’s multimodal mixture-of-experts model for agentic applications. Its checkpoint is distinct from Kimi K3 and the later K2.7 Code deployment.

Kimi K2.6: suitable applications

Consider visual document work, coding agents and conversations that combine tool results with a substantial input history.

Capabilities and technical details

The documented Cloudflare route exposes vision, reasoning and function calling. Separate cached-input tariffs can matter for repeated context.

Kimi K2.6 accepts text, image and returns text. The recorded input reference is 262,144 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are modified-mit; the linked source explains their scope.

Kimi K2.6 limitations and selection

Paid access is required on Cloudflare. The model uses developer-specific license terms, and a large input budget is not a guarantee of reliable long-context recall.

Evaluate visual accuracy and tool execution boundaries together; compare the same request history and reasoning settings when estimating effective cost.

Kimi K2.6 API pricing

Kimi K2.6 pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.

Review the Cloudflare Kimi K2.6 endpoint reference and the Moonshot AI model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.

CONTEXT TOKENS262,144Source not recorded
MAX OUTPUT TOKENSNot suppliedProvider-dependent
PROVIDERS1Linked in this catalog
SOURCE CHECKED2026-10-20Sources reviewed; unknown fields labeled

Specifications

Catalog model ID
moonshotai/kimi-k2.6
Developer model ID / revision
Not verified in cited sources
Context / input token limit
262,144Developer model card / documentation ↗
Maximum output tokens
Not verified in cited sources
API parameters (source-specific)
Not verified in cited sources
Weight license / access terms
modified-mitDeveloper weight license / hosted access terms ↗
Total parameters (billions)
Not verified in cited sources
Active parameters (billions)
Not verified in cited sources
Download size (GB)
Depends on checkpoint and precision; no verified file size
Release date
Not verified in cited sources
Notes
Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the publisher configuration; provider caps can be lower.

Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.