VENICE ATLAS · MODEL DOSSIER · KIMI K2.6

Model overview

Kimi K2.6

Name: Kimi K2.6
Brand: venice.ai
Price: 0.7500 USD
Availability: InStock

Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with 256K context windows.

kimi-k2-6 · venice.ai

Text · Venice catalog$0.75 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.75 per 1M tokensper 1M tokens

Context window256KMax tokens

Benchmarks28Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Biology#1435.19 rating Chemistry#1635.46 rating Coding#3232.95 rating Vision#3428.91 rating Frontend Development#1127.69 rating Math#2636.71 rating Multimodal#2431.45 rating Physics#1635.46 rating Reasoning#3943.72 rating Search#926.40 rating

Agents3 results

Finance Agent v2finance-agent-v2 · agents

44.9%

ReportedOct 2026

MCP-Markmcp-mark · agents

55.9%

ReportedOct 2026

Toolathlontoolathlon · agents

50.0%

ReportedOct 2026

Coding2 results

Claw-Evalclaw-eval · code

80.9%

ReportedOct 2026

FrontierSWEfrontierswe · code

27.0%

ReportedOct 2026

Math5 results

AIME 2026aime-2026 · math

96.4%

ReportedOct 2026

HMMT Feb 26hmmt-feb-26 · math

92.7%

ReportedOct 2026

IMO-AnswerBenchimo-answerbench · math

86.0%

ReportedOct 2026

LiveBenchlivebench · math

72.2%

ReportedOct 2026

MathVisionmathvision · math

93.2%

ReportedOct 2026

Multimodal1 result

OSWorld-Verifiedosworld-verified · multimodal

73.1%

ReportedOct 2026

Reasoning12 results

APEX-Agentsapex-agents · reasoning

27.9%

ReportedOct 2026

BrowseCompbrowsecomp · reasoning

86.3%

ReportedOct 2026

CharXiv-Rcharxiv-r · reasoning

86.7%

ReportedOct 2026

GPQAgpqa · reasoning

90.5%

ReportedOct 2026

Humanity's Last Examhumanity's-last-exam · reasoning

36.4%

ReportedOct 2026

LiveCodeBench v6livecodebench-v6 · reasoning

89.6%

ReportedOct 2026

OJBenchojbench · reasoning

60.6%

ReportedOct 2026

SciCodescicode · reasoning

52.2%

ReportedOct 2026

SWE-bench Multilingualswe-bench-multilingual · reasoning

76.7%

ReportedOct 2026

SWE-Bench Proswe-bench-pro · reasoning

58.6%

ReportedOct 2026

SWE-Bench Verifiedswe-bench-verified · reasoning

80.2%

ReportedOct 2026

Terminal-Bench 2.0terminal-bench-2 · reasoning

66.7%

ReportedOct 2026

Search2 results

DeepSearchQAdeepsearchqa · search

83.0%

ReportedOct 2026

WideSearchwidesearch · search

80.8%

ReportedOct 2026

Vision3 results

BabyVisionbabyvision · vision

68.5%

ReportedOct 2026

MMMU-Prommmu-pro · vision

80.1%

ReportedOct 2026

V*v-star · vision

96.9%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.75
Output price per 1M tokens: $3.50
Cache read price per 1M tokens: $0.16
Blended price per 1M tokens (50/50): $2.13

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionWeb search

Endpoint metadata

Privacy: private
Quantization: int4
Maximum completion tokens: 66K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: int4
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: high
Reasoning Effort Options: none, low, medium, high
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from moonshotai

kimi-k2-5Kimi K2.5$0.56 input per 1M tokens ↗kimi-k2-7-codeKimi K2.7 Code$0.75 input per 1M tokens ↗kimi-k3Kimi K3$3.75 input per 1M tokens ↗