Kimi K2.5
Kimi K2.5Alternatives?
CheaperGLM 5.3 FlashmaxOpen×5.5-80%$0.28Defaults to max · Self-hosted+4
BetterGPT-6 Lunamedium+59%-83%$0.017Function calling only with none · Chat Completions+3
CheaperClaude Haiku 5.5xhigh×5.3-83%$0.12Remove sampling parameters+5CheaperGPT-5.6 Lunamax×5-63%$0.18TCheaperInkling SmallxhighOpen×3.3-47%$0.45 / $1.20No strict JSONGLM 5.3 FlashmaxOpen×5.5-80%$0.28Defaults to max · Self-hosted+4Claude Haiku 5.5xhigh×5.3-83%$0.12Remove sampling parameters+5GPT-6 Lunamax×5.1-83%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunamax×5-63%$0.18TInkling SmallxhighOpen×3.3-47%$0.45 / $1.20No strict JSONGPT-6 Lunamedium+59%-83%$0.017Function calling only with none · Chat Completions+3GPT-5.6 Lunahigh×2.5-63%$0.044Claude Haiku 5.5high×3.4-83%$0.079Remove sampling parameters+5GPT-6.1 Sollow×6.4+233%$0.13Remove unsupported parameters+5GPT-6 Sollow×2.1+233%$0.13GLM 5.3 FlashmaxOpen×5.5-80%$0.28Defaults to max · Self-hosted+4
DeepSeek V4 Pro 0813highOpen×5.3+65%$1.32 / $3.96Memory (4-bit): 616 GB → 990 GB+6TInkling SmallxhighOpen×3.3-47%$0.45 / $1.20No strict JSON
Qwen3.8 27BxhighOpen×3.2-20%$1.01max_tokens range · QwenCloud+4TInklingunstatedOpen×3.1+44%$0.95 / $4.05No strict JSONKimi K3maxOpen×5.1—$2.00Memory (4-bit): 616 GB → 1,668 GB+4Kimi K3.1 Pron/a—$2 / $10Kimi K3.1 Pro Highspeedn/a—$4 / $20Kimi K2.7 CodethinkingOpenn/a—$0.54Instant mode is not supported · Self-hosted / vLLM / SGLangKimi K2.6thinkingOpenn/a—$0.80Kimi 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 versionsBenchmarks
in Chat & KnowledgeFAQ
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 GPT-5 Pro?›
On ARC-AGI-2 · public evaluation, Kimi K2.5 scores 12.1 vs 13.3 — lower.
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?›
GLM 5.3 Flash (cheaper), GPT-6 Luna (better).