Kimi Dev 72B Check detailed information and pricing for AI models

Context Length 131,072 tokens, moonshotai from provided

131,072
Context Tokens
$0.29
Prompt Price
$1.15
Output Price
4/16
Feature Support

Model Overview

Kimi-Dev-72B is an open-source large language model fine-tuned for software engineering and issue resolution tasks. Based on Qwen2.5-72B, it is optimized using large-scale reinforcement learning that applies code patches in real repositories and validates them via full test suite execution—rewarding only correct, robust completions. The model achieves 60.4% on SWE-bench Verified, setting a new benchmark among open-source models for software bug fixing and code reasoning.

Basic Information

Developer
moonshotai
Model Series
Other
Release Date
2025-06-16
Context Length
131,072 tokens
Max Completion Tokens
131,072 tokens
Variant
standard

Pricing Information

Prompt Tokens
$0.29 / 1M tokens
Completion Tokens
$1.15 / 1M tokens

Supported Features

Supported (4)

Top K
Frequency Penalty
Response Format
Reasoning

Unsupported (12)

Image Input
Seed
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A

Other Variants

Actual Usage Statistics

No recent usage data available.

Models by Same Author (moonshotai)

Kimi K2 0905
262,144 tokens
$0.30 / $1.19
Kimi K2 0711
63,000 tokens
$0.14 / $2.49
Kimi K2 0711 (free)
32,768 tokens
Free
Kimi VL A3B Thinking (free)
131,072 tokens
Free
Kimi VL A3B Thinking
131,072 tokens
$0.02 / $0.10

Similar Price Range Models

Kimi K2 0905
moonshotai
262,144 tokens
$0.30 / $1.19
ERNIE 4.5 300B A47B
baidu
123,000 tokens
$0.28 / $1.10
Claude 3 Haiku (self-moderated)
anthropic
200,000 tokens
$0.25 / $1.25
Claude 3 Haiku
anthropic
200,000 tokens
$0.25 / $1.25
Mercury Coder
inception
128,000 tokens
$0.25 / $1.00