Kimi K2 0905

Official publisher releaseRestricted license

Kimi K2 0905 is a language model from Moonshot AI. It has been superseded and no longer holds a position on ModelCap's current board. It is listed at $0.60 per million input tokens and $2.50 per million output tokens from one provider. It reads up to 262K tokens of context, and its weights are downloadable under a use-restricted licence.

Figures as of 6 Nov 2026, 20:32 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive

—

Index position pending

Market Gravity

36.80.2

Secondary market signal

Superseded by Kimi K3. It no longer holds a current-board position.

Input

$0.60

per 1M tokens

Output

$2.50

per 1M tokens

Context

262K

tokens

Providers

endpoint

Providers

Uptime measured over the last 30 minutes

Provider	Input	Output	Context	Quant	Uptime
Novitafp8	$0.60	$2.50	262K	fp8	100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

Provider	Input	Output	Context	TTFT	Throughput	Features
novita live	$0.60	$2.50	262K	742 ms	44.2 tok/s	tools · structured

Reported evaluation leads (1)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / task	Metric	Value	Revision	Provenance
FutureMa/EvasionBench evasion_bench	—	66.68	Unpinned `not published`	Reported Quarantined

Other versions (4)

ModelCap Index · All-versions archive

Methodology

—

Index position pending

Technical details

Public rank basis: Index position pending (abstained)
Evidence label: Index position pending · insufficient shared rows
Index support: 0.0% · not applicable
Identity binding: Exact catalogue product · moonshotai/moonshotai/kimi-k2-0905/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata moonshotai/Kimi-K2-Instruct-0905@ac6c49f04883bd0a0598b790693a72061c676629 (not the evaluation revision)
Index observations used: 0
Architecture fallback: abstained · 0% coverage · 0 anchors

Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability: —
Evidence status: No admitted measured evidence
General preference: —
Coding: —
Agents & tools: —
Reasoning: —
Evidence breadth: 0%
Evidence coverage: 0%

Market and catalogue signals · secondary, never the language Index rank

Usage (OpenRouter popularity): 8.0
Liquidity (providers × uptime): 95.8
Open reach (HF downloads): —
Surface (context / tools / modalities): 50.3
Freshness: 19.6

· OpenRouter popularity #213
· 1 live provider
· Catalogue: context 262144, tools
· First seen 2025-09-04

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy

48.4

34.2–62.5 uncertainty interval

Excluded from rank

Confidence: 78%
Training support: 218 models · 128 lineages
Out-of-domain check: in domain
Feature coverage: 100%
Lineage-held-out error: 8.3 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index

63.0

partial · 71% metadata coverage

Not capability

Artifact reproducibility: 85.0
Access & legal clarity: 67.5
Deployability: 80.0
Evaluation provenance: 0.0

Not yet published: the base model it derives from, a link to the licence terms, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage

Market Gravity: 36.8
OpenRouter weekly popularity: #213 of 339

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%: 8.0
Liquidity25%: 95.8
Open reach15%: 50.0
Freshness5%: 19.6

Specification

Model ID: moonshotai/kimi-k2-0905
Context window: 262K tokens
Declared output cap: 98K tokens
OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
Inputs: Text
Outputs: Text
Tokenizer: Other
Cached input tokens: Not offered
First seen on OpenRouter: 4 Sept 2025
Knowledge cutoff: 2024-12-31

Capabilities

Not supported: Reasoning
Supported: Tool use
Supported: Structured output
Supported: Response format
Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access: Restricted license
Licence: modified-mit
Pinned revision: ac6c49f04883
Parameters: 1026.4B
Architecture: DeepseekV3ForCausalLM
Model type: kimi_k2
Hugging Face downloads (30d): 9K
Downloads (all time): 5.2M
Likes: 790
Repository: moonshotai/Kimi-K2-Instruct-0905
Repository updated: 30 Jan 2026, 04:50 UTC

Kimi K2 0905: common questions

How does Kimi K2 0905 rank among AI models?

Kimi K2 0905 is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Kimi K2 0905 cost per 1M tokens?

Kimi K2 0905 is listed at $0.60 per 1M input tokens and $2.50 per 1M output tokens as of 6 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $2.45 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Kimi K2 0905?

Kimi K2 0905 has a published context window of 262K tokens (262,144). The snapshot lists a 98,304 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.

Is Kimi K2 0905 open-weight?

Restricted license (modified-mit). Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment. The repository is moonshotai/Kimi-K2-Instruct-0905 on Hugging Face.

Which API providers serve Kimi K2 0905?

One provider serves Kimi K2 0905 through OpenRouter as of 6 November 2026: Novita. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

When was Kimi K2 0905 released?

Kimi K2 0905 first appeared in the catalogue on 4 Sept 2025, with a published knowledge cutoff of 2024-12-31. It has since been superseded by Kimi K3. Rank and price movements since then are recorded on the site's changes feed.