Kimi K2 0711

Official publisher releaseRestricted license

Moonshot AI·#173 of 504 in the all-versions archive

Kimi K2 0711 is a language model from Moonshot AI. It ranks #173 of 504 in ModelCap's all-versions archive, with an Index score of 54.5, modeled from the publisher's launch results against measured models. Its score range of 42.2–66.8 spans positions #104–#250. It is listed at $0.57 per million input tokens and $2.30 per million output tokens from one provider. It reads up to 131K tokens of context, and its weights are downloadable under a use-restricted licence.

Figures as of 6 Nov 2026, 13:52 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive

54.5#173

Modeled from the publisher's launch results against measured models · range 42.2–66.8

Market Gravity

35.80.1

Secondary market signal

Superseded by Kimi K3. It no longer holds a current-board position; its all-versions archive rank is #173.

Input

$0.57

per 1M tokens

Output

$2.30

per 1M tokens

Context

131K

tokens

Providers

endpoint

Providers

Uptime measured over the last 30 minutes

Provider	Input	Output	Context	Quant	Uptime
Novitafp8	$0.57	$2.30	131K	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	$0.57	$2.30	131K	844 ms	45.3 tok/s	tools
featherless-ai live	—	—	—	—	—	—

Reported evaluation leads (6)

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. Rows marked as used were laddered against independently measured peers inside the launch-card channel of this model's modeled placement, with the replay-measured optimism haircut applied; the others played no part.

Dataset / task	Metric	Value	Revision	Provenance
harborframework/terminal-bench-2.0 terminalbench_2	—	27.8	Unpinned `not published`	Reported Not used in launch estimate
mercor/apex-agents apex-agents	—	4.1	Unpinned `not published`	Reported Not used in launch estimate
mercor/APEX-SWE apex-swe	—	11.2	Unpinned `not published`	Reported Not used in launch estimate
ScaleAI/SWE-bench_Pro SWE_Bench_Pro	—	27.67	Unpinned `not published`	Reported Not used in launch estimate
SWE-bench/SWE-bench_Multilingual swe_bench_multilingual_%_resolved	—	47.3	Unpinned `not published`	Reported Used in launch estimate
TIGER-Lab/MMLU-Pro mmlu_pro	—	81	Unpinned `not published`	Reported Used in launch estimate

Other versions (4)

ModelCap Index · All-versions archive

Methodology

54.5

Modeled from the publisher's launch results against measured models

All-versions archive

#173 of 504

Score range: 42.2–66.8
Rank range: #104–#250

Technical details

Public rank basis: Modeled · peer benchmarks (architecture)
Evidence label: Modeled · peer benchmarks · publisher-corpus-prior over 210 held-out anchors (16%); launch card against 3 resolved peers on 16 rows (84%); exceeds every named peer on 12 of 16 rows; optimism haircut 4.56 from cross-lab-probe; shrunk 3.5 up toward the measured corpus
Index support: 40.0% · limited
Identity binding: Exact catalogue product · moonshotai/moonshotai/kimi-k2/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata moonshotai/Kimi-K2-Instruct@fd1984e2b7a3350dbf7305fe73a4ede25c14de50 (not the evaluation revision)
Index observations used: 0
Qualified Index evidence point: 54.5

How this position was produced · fused launch placement

No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.

Fused estimate: 54.5 ± 9.6
Independent share: 0%
Shrink toward corpus: +3.5
Peer ceiling share: 75%
Optimism haircut: −4.6 points · cross lab probe, 2 probes
Method: precision-weighted-v1

Channels fused into this model’s launch placement
Channel	Estimate	Share
Publisher corpus prior · not independent publisher-corpus-prior over 210 held-out anchors	72.3 ± 23.8	16%
Launch card against resolved peers · not independent launch card against 3 resolved peers on 16 rows	51.0 ± 10.5	84%

· Launch card row aime-2024: claims above every resolved peer
· Launch card row aime-2025: claims above every resolved peer
· Launch card row gpqa-diamond: claims above every resolved peer
· Launch card row hle: inside the resolved peer range
· Launch card row hmmt-2025: claims above every resolved peer
· Launch card row ifeval: claims above every resolved peer
· Launch card row livecodebench-v-6: claims above every resolved peer
· Launch card row math-500: claims above every resolved peer
· Launch card row mmlu-pro: inside the resolved peer range
· Launch card row mmlu-redux: claims above every resolved peer
· Launch card row mmlu: inside the resolved peer range
· Launch card row swe-bench-multilingual: claims above every resolved peer
· Launch card row swe-bench-verified: claims above every resolved peer
· Launch card row tau-2-bench-airline: claims above every resolved peer
· Launch card row tau-2-bench-retail: inside the resolved peer range
· Launch card row tau-2-bench-telecom: claims above every resolved peer

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): 6.5
Liquidity (providers × uptime): 95.8
Open reach (HF downloads): —
Surface (context / tools / modalities): 45.2
Freshness: 15.9

· OpenRouter popularity #232
· 1 live provider
· Catalogue: context 131072, tools
· First seen 2025-07-11

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

44.9

30.9–59.0 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

62.0

partial · 71% metadata coverage

Not capability

Artifact reproducibility: 85.0
Access & legal clarity: 67.5
Deployability: 76.5
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: 35.8
OpenRouter weekly popularity: #232 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%: 6.5
Liquidity25%: 95.8
Open reach15%: 50.0
Freshness5%: 15.9

Specification

Model ID: moonshotai/kimi-k2
Context window: 131K 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: 11 Jul 2025
Knowledge cutoff: 2024-12-31

Capabilities

Not supported: Reasoning
Supported: Tool use
Not supported: Structured output
Not 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: fd1984e2b7a3
Parameters: 1026.4B
Architecture: DeepseekV3ForCausalLM
Model type: kimi_k2
Hugging Face downloads (30d): 300K
Downloads (all time): 4.7M
Likes: 3K
Repository: moonshotai/Kimi-K2-Instruct
Repository updated: 23 Apr 2026, 02:08 UTC

Kimi K2 0711: common questions

How does Kimi K2 0711 rank among AI models?

Kimi K2 0711 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 0711 cost per 1M tokens?

Kimi K2 0711 is listed at $0.57 per 1M input tokens and $2.30 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 $2.29 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 0711?

Kimi K2 0711 has a published context window of 131K tokens (131,072). 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 0711 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 on Hugging Face.

Which API providers serve Kimi K2 0711?

One provider serves Kimi K2 0711 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 0711 released?

Kimi K2 0711 first appeared in the catalogue on 11 Jul 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.