Bitcoin.com AI logo

Kimi K2.7 Code High-Speed

Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.

  • Reasoning
  • Vision
  • Tool Calling
  • Parallel Tool Calls

Added Jun 15, 2026

Pricing

Auto routing · per 1M tokens
Input
$1.90
Output
$8.00
Cache read
$0.32
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
1T / 32B
Total / active
Avg output (7d)
1.3K tokens
Longer than 81% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

25.8

Better than 80% of models compared

Coding Index

60.8

Better than 72% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

24.5%

Better than 45% of models compared

Harvey LAB-AA

Legal agentic work criterion pass rate

85.0%

Better than 38% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

859 Elo

Better than 37% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1040 Elo

Better than 48% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

11.2%

Better than 45% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

79.3%

Better than 83% of models compared

MLCR-AA

Medical long-context reasoning

16.1%

Better than 54% of models compared

Reasoning

HLE

Humanity's Last Exam

35.0%

Better than 82% of models compared

IFBench

Instruction-following benchmark

63.1%

Better than 74% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

1.0%

Better than 42% of models compared

SciCode

Python programming for scientific computing

47.8%

Better than 45% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

89.6%

Better than 88% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

44.7%

Better than 92% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

90.1%

Better than 84% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

79.3%

Better than 83% of models compared

Last updated Oct 14, 2026

Artificial Analysis

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Loading provider options…