Kimi K2.6
Kimi K2.6Alternatives?
CheaperGPT-6.1 Solxhigh×4-44%$0.39Remove unsupported parameters+5BetterGPT-6 Lunamedium+32%-98%$0.017Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking×3.3-81%$0.13Pass back reasoning_content+3CheaperGPT-6.1 Terramax×3.5-43%$0.40CheaperGPT-6 Solxhigh×3.5-26%$0.52GPT-6.1 Solxhigh×4-44%$0.39Remove unsupported parameters+5GPT-6.1 Terramax×3.5-43%$0.40GPT-6 Solxhigh×3.5-26%$0.52GPT-5.6 Terraxhigh×3.4-11%$0.63Prompts with >272K input tokensMiMo v2.6 ProthinkingOpen×3.3-81%$0.13Pass back reasoning_content+3GPT-6 Lunamedium+32%-98%$0.017Function calling only with none · Chat Completions+3GPT-5.6 Lunahigh×2.1-94%$0.044
Claude Haiku 5.5medium+61%-93%$0.047Remove sampling parameters+5GPT-6.1 Terralow+89%-92%$0.055MiMo v2.6 FlashthinkingOpen+50%-91%$0.062Pass back reasoning_content+3MiMo v2.6 ProthinkingOpen×3.3-81%$0.13Pass back reasoning_content+3
DeepSeek V4.1 Flash 1017maxOpen×3-63%$0.26Pass back reasoning_content · Chat Completions+4
Step 5 PreviewthinkingOpen×2.6+45%$1.03web_search not available · Chat Completions+2
GLM 5.2maxOpen×2.6+82%$1.28No image input
Qwen3.8 2.4T A95BthinkingOpen×2.5+205%$2.16Memory (4-bit): 616 GB → 1,468 GB+6Kimi K3maxOpen×2.9+183%$2.00Memory (4-bit): 616 GB → 1,668 GB+4Kimi K2.7 CodethinkingOpen+25%-23%$0.54Instant mode is not supported · Self-hosted / vLLM / SGLangKimi K2.5thinkingOpen-61%—$0.60 / $3Kimi K2 ThinkingthinkingOpen-68%—$0.47 / $2No image inputKimi K2 0905non-thinkingOpen-100%—$0.40 / $2No image inputKimi K2 0711non-thinkingOpen-100%—$0.50 / $2Context: 256K → 128K+2Kimi K3.1 Prohighn/a—$2 / $10Kimi K3.1 Pro Highspeedn/a—$4 / $20All Moonshot AI models →Run it yourself
estimateHistory
5 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Kimi K2.6 cost?›
$0.95 per 1M input tokens and $4 per 1M output tokens; cached input $0.16 per 1M; cheapest via Chutes at $0.45 / $1.95. A typical benchmark task costs about $0.71 at default effort.
Is Kimi K2.6 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 K2.6, and what is it best at?›
#57 of 336 in Chat & Knowledge, #65 of 134 in Coding, #75 of 135 in Agents & Tool Use, #40 of 197 in Writing & Language, #24 of 125 in Vision & Documents. Strongest at: Tool calling, Reasoning, Science, Long context, Knowledge, Instructions, Vision.
Is Kimi K2.6 better than Kimi K2.5?›
On CritPt (physics), Kimi K2.6 scores 8 vs 3.1 — higher.
How can I use Kimi K2.6?›
Through the API of AtlasCloud, Azure AI Foundry, Chutes, Cloudflare, CoreWeave and 9 more.
What is the context window of Kimi K2.6?›
256K tokens, with up to 236K output tokens.
When was Kimi K2.6 released? Is there a newer version?›
Released 2026-04-20. It has been superseded by Kimi K3.
Is Kimi K2.6 open source?›
Yes, the weights are open (modified-mit licence).
Can I run Kimi K2.6 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Kimi K2.6 read images?›
It accepts text and images as input.
What is Kimi K2.6?›
Kimi K2.6 is an open-weights language model from Moonshot AI, released Apr 2026, the successor to Kimi K2.5.
What are the best alternatives to Kimi K2.6?›
GPT-6.1 Sol (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).