Kimi K2.5
Kimi K2.5Alternatives?
CheaperGemini 3 Flash Previewunstatedwins 55%-6%$0.50 / $3
BetterGPT-6.1 Solmaxwins 55%+233%$0.72Remove unsupported parameters+5
OpenGLM 5.2maxwins 54%+79%$1.47No image input
CheaperMiMo v2.6 ProunstatedOpenwins 53%-55%$0.43 / $0.87Pass back reasoning_content+3CheaperGemini 3.5 Flash Liteunstatedsame-29%$0.30 / $2.50Gemini 3 Flash Previewunstatedwins 55%-6%$0.50 / $3MiMo v2.6 ProunstatedOpenwins 53%-55%$0.43 / $0.87Pass back reasoning_content+3Gemini 3.5 Flash Liteunstatedsame-29%$0.30 / $2.50GLM 5.3 FlashunstatedOpensame-80%$0.15 / $0.50Defaults to max · Self-hosted+4MiMo v2.5 ProunstatedOpensame-55%$0.43 / $0.87No image inputGPT-6.1 Solmaxwins 55%+233%$0.72Remove unsupported parameters+5
Muse Spark 1.2xhighwins 53%+67%$0.97Only auto tool_choice is supported+1GPT-6 Solmaxwins 52%+233%$1.04GPT-5.6 Solxhighwins 57%+567%$1.18Gemini 3.8 Flashhighwins 59%+25%*$1.24Sampling parameters are ignored+1GLM 5.2maxOpenwins 54%+79%$1.47No image inputGLM 5.3maxOpenwins 54%+79%$2.01No image input+4GLM 5unstatedOpenwins 54%+29%$1 / $3.20Context: 256K → 203K+1GLM 5.1unstatedOpenwins 53%+79%$1.40 / $4.40Context: 256K → 203K+1
DeepSeek V4 Pro 0813highOpenwins 53%+65%$1.32 / $3.96Memory (4-bit): 616 GB → 990 GB+6Kimi K3maxOpenwins 55%—$2.00Memory (4-bit): 616 GB → 1,668 GB+4Kimi K2.6unstatedOpensame—$0.95 / $4Kimi K2.7 CodethinkingOpenn/a—$0.54Instant mode is not supported · Self-hosted / vLLM / SGLangKimi K2 ThinkingthinkingOpenn/a—$0.47 / $2No image inputKimi K2 0905non-thinkingOpenn/a—$0.40 / $2No image inputKimi K2 0711non-thinkingOpenn/a—$0.50 / $2Context: 256K → 128K+2All Moonshot AI models →Run it yourself
estimateHistory
5 versionsFAQ
How much does Kimi K2.5 cost?›
$0.60 per 1M input tokens and $3 per 1M output tokens; cached input $0.10 per 1M; cheapest via DeepInfra at $0.45 / $2.25.
Is Kimi K2.5 free to use?›
There is no free API; the cheapest paid price is $0.45 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Kimi K2.5, and what is it best at?›
#76 of 334 in Chat & Knowledge, #56 of 97 in Coding, #96 of 175 in Agents & Tool Use, #51 of 195 in Writing & Language, #47 of 124 in Vision & Documents. Strongest at: Tool calling, Reasoning, Science, Long context, Instructions.
Is Kimi K2.5 better than MiMo v2 Pro?›
On Arena Text · creative writing, Kimi K2.5 scores 1,423 vs 1,424 — about the same.
How can I use Kimi K2.5?›
Through the API of AWS Bedrock, Amazon Bedrock, AtlasCloud, Azure AI Foundry, DeepInfra and 3 more.
What is the context window of Kimi K2.5?›
256K tokens, with up to 262K output tokens.
When was Kimi K2.5 released? Is there a newer version?›
Released 2026-01-27. It has been superseded by Kimi K2.6.
Is Kimi K2.5 open source?›
Yes, the weights are open (modified-mit licence).
Can I run Kimi K2.5 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Kimi K2.5 read images?›
It accepts text and images as input.
What is Kimi K2.5?›
Kimi K2.5 is an open-weights language model from Moonshot AI, released Jan 2026, the successor to Kimi K2 0905.
What are the best alternatives to Kimi K2.5?›
Gemini 3 Flash Preview (cheaper), GPT-6.1 Sol (better), GLM 5.2 (open weights).