Moonshot AI

Kimi K2.7 Code

Tool callingStructured outputReasoningImage inputVideo input
Kimi K2.7 Code model card cover

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Context
262K
Released
4mo ago
Parameters
1T
Input / 1M tokens
$0.67
Output / 1M tokens
$3.35
Cached input / 1M tokens
$0.18

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

DeepSWE 1.1

Primary coding-agent benchmark · 113 tasks · Data generated 2026-09-22

Official leaderboard
30.5%
pass@1 · highest published configuration
mini-swe-agent
pass@4
61.1%
Average cost / attempt
$2.82
Benchmark runs
4

pass@1 is the success rate across scored attempts; pass@4 is the share of tasks solved in at least one of four attempts. Costs are reported by DeepSWE for each configuration. These results are not directly comparable to evaluations using different harnesses. Official source JSON.

Other published benchmarks

EvaluationReported score and source
FrontierMath-Tier-4-v2-Private
12.2%
Epoch AI · kimi-k2.7-code
Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private
54.0%
Epoch AI · kimi-k2.7-code
Epoch AI evaluation
GPQA diamond
87.9%
Epoch AI · kimi-k2.7-code
Epoch AI evaluation
OTIS Mock AIME 2024-2025
95.6%
Epoch AI · kimi-k2.7-code
Epoch AI evaluation
SimpleQA Verified
36.5%
Epoch AI · kimi-k2.7-code
Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer
Moonshot AI
Model family
Kimi
Type
Language model
Predecessor
—
Successor
—
Released
June 12, 2026
Model ID
moonshotai/kimi-k2.7-code
Openness
Open weights
License
—
Parameters
1T
Architecture
kimi-k2
Families
kimi-k2
Input modalities
text, image
Output modalities
text
Modality
text+image->text
Native context
262K
Tokenizer
Other
Max output tokens
236K
Knowledge cutoff
2025-01
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

1 builds
VariantParametersTypeQuantizationSizeContextInput
kimi-k2.7-code:cloud1Tcloud——256Ktext + image
Additional source evidence
Source model
moonshotai/kimi-k2.7-code
Source family
kimi-k2
Last updated
2026-06-12
Knowledge cutoff
2025-01
Model context
262K
Model output limit
262K
Open weights
Yes
File attachments
Yes
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Temperature control
No

Downloadable weights

Published benchmarks

BenchmarkScoreEvaluation detailsEvidence
Kimi Code Bench62Kimi Code CLI · v2 · 2026-06-12Source
Program Bench53.6Kimi Code CLI · 2026-06-12Source
MLS Bench Lite35.1Kimi Code CLI · 2026-06-12Source
MCP Atlas76 · success rateKimi Code CLI · 2026-06-12Source
MCP Mark Verified81.1 · success rateKimi Code CLI · 2026-06-12Source
Kimi Claw 24/7 Bench46.9Kimi Code CLI · 2026-06-12Source
Complete source record (JSON)
{
  "id": "moonshotai/kimi-k2.7-code",
  "name": "Kimi K2.7 Code",
  "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
  "family": "kimi-k2",
  "last_updated": "2026-06-12",
  "knowledge": "2025-01",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": false,
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 262144
  },
  "benchmarks": [
    {
      "name": "Kimi Code Bench",
      "score": 62,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "harness": "Kimi Code CLI",
      "version": "v2",
      "date": "2026-06-12"
    },
    {
      "name": "Program Bench",
      "score": 53.6,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "harness": "Kimi Code CLI",
      "date": "2026-06-12"
    },
    {
      "name": "MLS Bench Lite",
      "score": 35.1,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "harness": "Kimi Code CLI",
      "date": "2026-06-12"
    },
    {
      "name": "MCP Atlas",
      "score": 76,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "metric": "success rate",
      "harness": "Kimi Code CLI",
      "date": "2026-06-12"
    },
    {
      "name": "MCP Mark Verified",
      "score": 81.1,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "metric": "success rate",
      "harness": "Kimi Code CLI",
      "date": "2026-06-12"
    },
    {
      "name": "Kimi Claw 24/7 Bench",
      "score": 46.9,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
      "harness": "Kimi Code CLI",
      "date": "2026-06-12"
    }
  ],
  "release_date": "2026-06-12",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/moonshotai/Kimi-K2.7-Code"
    }
  ]
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Inceptroninceptron/int4262K$0.67$3.35$0.18—99.86%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

CoreWeavecoreweave/int4262K$0.71$3.50$0.15—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

StreamLakestreamlake256K$0.71$3.00$0.14—99.75%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Venicevenice/int4256K$0.75$3.50$0.16—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

SiliconFlowsiliconflow/fp8262K$0.86$3.80$0.18—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Novitanovita/int4262K$0.91$3.84$0.18—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Alibabaalibaba/fp8262K$0.95$4.00$0.19—99.17%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Cloudflarecloudflare262K$0.95$4.00$0.19—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

GMICloudgmicloud/fp8262K$0.95$4.00$0.19—86.67%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Moonshot AImoonshotai/int4262K$0.95$4.00$0.19—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Nebiusnebius/fp4262K$0.95$4.00——100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Phalaphala262K$0.95$4.00$0.19—98.69%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Moonshot AImoonshotai/highspeed262K$1.90$8.00$0.38—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware