Kimi K2 0711
Kimi K2 0711Rankingin non-thinking mode?
Alternatives?
CheaperMiniMax M3thinkingOpen+21%-40%$0.51Deployment status experimental · Self-hosted
BetterGPT-5.6 Lunalow+9%-49%$0.01
OpenQwen3.8 2.4T A95Bthinking+22%+243%$2.16Memory (4-bit): 616 GB → 1,468 GB+5CheaperQwen3.8 FlashthinkingOpen+21%-74%$0.37max_tokens range · QwenCloud+5
CheaperGLM 5.3 FlashmaxOpen+19%-73%$0.28Defaults to max · Self-hosted+4MiniMax M3thinkingOpen+21%-40%$0.51Deployment status experimental · Self-hostedQwen3.8 FlashthinkingOpen+21%-74%$0.37max_tokens range · QwenCloud+5GLM 5.3 FlashmaxOpen+19%-73%$0.28Defaults to max · Self-hosted+4GPT-5.6 Lunamax+19%-49%$0.18
Agnes 2.5 Pro Beta+18%-83%$0.10 / $0.30GPT-5.6 Lunalow+9%-49%$0.01
MiMo v2.5thinkingOpen+11%-80%$0.019GPT-5 Minihigh+8%-21%$0.053MiMo v2.5 ProthinkingOpen+13%-38%$0.054
Muse Glimmer 30BhighOpen+9%-43%$0.058Qwen3.8 2.4T A95BthinkingOpen+22%+243%$2.16Memory (4-bit): 616 GB → 1,468 GB+5MiniMax M3thinkingOpen+21%-40%$0.51Deployment status experimental · Self-hosted
DeepSeek V4 Pro 0813maxOpen+21%+126%$0.67Memory (4-bit): 616 GB → 990 GB+5Qwen3.8 FlashthinkingOpen+21%-74%$0.37max_tokens range · QwenCloud+5GLM 5.3maxOpen+20%+146%$2.01Reasoning cannot be disabled+3Kimi K3maxOpen+22%—$2.00Memory (4-bit): 616 GB → 1,668 GB+4Kimi K2.6thinkingOpen+19%—$0.80Kimi K2.7 CodethinkingOpen+17%—$0.54Instant mode is not supported · Self-hosted / vLLM / SGLangKimi K2.5thinkingOpen+15%—$0.60 / $3Kimi K2 ThinkingthinkingOpen+9%—$0.47 / $2Kimi K2 0905non-thinkingOpensame—$0.40 / $2Kimi K3.1 Pron/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 0711 cost?›
$0.50 per 1M input tokens and $2 per 1M output tokens (cheapest host: DeepInfra).
Is Kimi K2 0711 free to use?›
There is no free API; the cheapest paid price is $0.50 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Kimi K2 0711, and what is it best at?›
#216 of 334 in Chat & Knowledge, #41 of 44 in Coding, #101 of 242 in Agents & Tool Use, #43 of 95 in Writing & Language.
Is Kimi K2 0711 better than Kimi K2 0905?›
On GPQA Diamond, Kimi K2 0711 scores 76.6 vs 76.7 — about the same.
How can I use Kimi K2 0711?›
Through the API of DeepInfra, Featherless, Novita.
What is the context window of Kimi K2 0711?›
128K tokens, with up to 98K output tokens.
When was Kimi K2 0711 released? Is there a newer version?›
Released 2025-07-11. It has been superseded by Kimi K2 0905.
Is Kimi K2 0711 open source?›
Yes, the weights are open (modified-mit licence).
Can I run Kimi K2 0711 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Kimi K2 0711 read images?›
No, it accepts text only.
What is Kimi K2 0711?›
Kimi K2 0711 is an open-weights language model from Moonshot AI, released Jul 2025.
What are the best alternatives to Kimi K2 0711?›
MiniMax M3 (cheaper), GPT-5.6 Luna (better), Qwen3.8 2.4T A95B (open weights).