Kimi K2 0905
Kimi K2 0905Rankingin non-thinking mode?
Alternatives?
CheaperMiMo v2.6 ProthinkingOpen×3-32%$0.13Pass back reasoning_content+3
BetterGPT-6 Lunalow+41%-75%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×2.9-34%$0.26Pass back reasoning_content · Chat Completions+4
CheaperLing 3.1 Flash 1019×2.9-44%$1.49
CheaperClaude Haiku 5.5max×2.8-75%$0.21Remove sampling parameters+5MiMo v2.6 ProthinkingOpen×3-32%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×2.9-34%$0.26Pass back reasoning_content · Chat Completions+4Ling 3.1 Flash 1019×2.9-44%$1.49Claude Haiku 5.5max×2.8-75%$0.21Remove sampling parameters+5
MiniMax M3.1 Flashthinking×2.8-67%$0.22No strict JSON+1GPT-6 Lunalow+41%-75%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+37%-44%$0.01Claude Haiku 5.5low+93%-75%$0.024Remove sampling parameters+5Ling 3.0 FlashthinkingOpen+32%-89%$0.028MiMo v2.5thinkingOpen+43%-78%$0.042MiMo v2.6 ProthinkingOpen×3-32%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×2.9-34%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×2.9+169%$2.01Reasoning cannot be disabled+3
Step 5 PreviewthinkingOpen×2.9+78%$1.03web_search not available · Chat Completions+2GLM 5.3 FlashmaxOpen×2.7-70%$0.28Defaults to max · Self-hosted+4Kimi K3maxOpen×2.9—$2.00Memory (4-bit): 616 GB → 1,668 GB+4Kimi K2.6thinkingOpen+76%—$0.71Kimi K2.7 CodethinkingOpen+69%—$0.54Instant mode is not supported · Self-hosted / vLLM / SGLangKimi K2.5thinkingOpen+53%—$0.60 / $3Kimi K2 ThinkingthinkingOpen+44%—$0.47 / $2Kimi K2 0711non-thinkingOpen-17%—$0.50 / $2Context: 256K → 128K+1Kimi K3.1 Prohighn/a—$2 / $10Kimi K3.1 Pro Highspeedn/a—$4 / $20All Moonshot AI models →Run it yourself
estimateHistory
5 versionsBenchmarks
all categoriesFAQ
How much does Kimi K2 0905 cost?›
$0.40 per 1M input tokens and $2 per 1M output tokens (cheapest host: DeepInfra).
Is Kimi K2 0905 free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Kimi K2 0905, and what is it best at?›
#239 of 336 in Chat & Knowledge, #81 of 239 in Coding, #90 of 242 in Agents & Tool Use, #49 of 96 in Writing & Language.
Is Kimi K2 0905 better than Kimi K2 0711?›
On AA Intelligence Index 4.3.2, Kimi K2 0905 scores 15.3 vs 12.7 — higher.
How can I use Kimi K2 0905?›
Through the API of DeepInfra, Featherless, Novita.
What is the context window of Kimi K2 0905?›
256K tokens, with up to 98K output tokens.
When was Kimi K2 0905 released? Is there a newer version?›
Released 2025-09-05. It has been superseded by Kimi K2.5.
Is Kimi K2 0905 open source?›
Yes, the weights are open (modified-mit licence).
Can I run Kimi K2 0905 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Kimi K2 0905 read images?›
No, it accepts text only.
What is Kimi K2 0905?›
Kimi K2 0905 is an open-weights language model from Moonshot AI, released Sep 2025, the successor to Kimi K2 0711.
What are the best alternatives to Kimi K2 0905?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).