Pricingby GlyphKimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
Ways to buy 16
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
int4, cheapest · cached $0.039 | $0.39 | $1.8 | $0.39 / $1.8-57% vs list | $0.039 | -57% vs list |
Default region · cached $0.114 | $0.57 | $2.4 | $0.57 / $2.4-40% vs list | $0.114 | -40% vs list |
| Inceptron int4 · cached $0.126 | $0.452 | $2.97 | $0.452 / $2.97-37% vs list | $0.126 | -37% vs list |
fp4 · cached $0.15 | $0.65 | $3.41 | $0.65 / $3.41-22% vs list | $0.15 | -22% vs list |
bf16 · cached $0.35 | $0.7 | $3.5 | $0.7 / $3.5-18% vs list | $0.35 | -18% vs list |
fp8 · cached $0.14 | $0.77 | $3.4 | $0.77 / $3.4-17% vs list | $0.14 | -17% vs list |
fp4 · cached $0.15 | $0.75 | $3.5 | $0.75 / $3.5-16% vs list | $0.15 | -16% vs list |
int4 · cached $0.16 | $0.75 | $3.5 | $0.75 / $3.5-16% vs list | $0.16 | -16% vs list |
int4 · cached $0.16 | $0.75 | $3.5 | $0.75 / $3.5-16% vs list | $0.16 | -16% vs list |
Default region · cached $0.16 | $0.8 | $3.4 | $0.8 / $3.4-15% vs list | $0.16 | -15% vs list |
The lab's own API · cached $0.16 | $0.95 | $4 | $0.95 / $4List price | $0.16 | List price |
| AtlasCloud int4 · cached $0.16 | $0.95 | $4 | $0.95 / $4Same as list | $0.16 | Same as list |
| Baidu fp4 · cached $0.16 | $0.95 | $4 | $0.95 / $4Same as list | $0.16 | Same as list |
Default region · cached $0.16 | $0.95 | $4 | $0.95 / $4Same as list | $0.16 | Same as list |
| StreamLake fp8 · cached $0.16 | $0.95 | $4 | $0.95 / $4Same as list | $0.16 | Same as list |
| Phala Default region · cached $0.37 | $1.09 | $4.6 | $1.09 / $4.6+15% vs list | $0.37 | +15% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $175.00 direct.
Kong AI Gateway$175.00+0%
LiteLLM$175.00+0%
Vercel AI Gateway$175.00+0%
Requesty$183.75+5%
Eden AI$184.63+5.5%
OpenRouter$184.63+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Moonshot AI · 1M | $0.377 | $7.95 | $0.377 / $7.95 | $2.27 | 1M | on Relace (fp4) | · | Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. |
Moonshot AI · 1MCheapest: $2.88 on InferenceNet (us) | $3 | $15 | $3 / $15 | $6 | 1M | $2.88 on InferenceNet (us) | · | Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. |
Moonshot AI · 262KCheapest: $1.2 on CoreWeave (int4) | $0.95 | $4 | $0.95 / $4 | $1.71 | 262K | $1.2 on CoreWeave (int4) | · | MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. |
Moonshot AI · 262K | $0.49 | $2.5 | $0.49 / $2.5 | $0.992 | 262K | on AtlasCloud (int4) | · | Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · | Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. |
Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · | Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. |
About Kimi K2.6
Takes text, image in and returns text. First listed Sep 23, 2026. Up to 236K output tokens. Blended price $1.71 per 1M tokens at 3 input to 1 output. Model id kimi-k2-6.
Price history
List price since Oct 27, 2026, from daily reads of the OpenRouter catalog.
Kimi K2.6
Chutes (int4) cut its price: input $0.45 to $0.39 and output $1.95 to $1.8 per 1M tokens.
Chutes (int4) cut its price: input $0.5 to $0.45 and output $2.85 to $1.95 per 1M tokens.
Inceptron (int4) cut its price: input $0.497 to $0.452 per 1M tokens.
Inceptron (int4) raised its price: input $0.432 to $0.497 and output $2.38 to $2.97 per 1M tokens.
Questions
How much does Kimi K2.6 cost?
$0.95 per million input tokens and $4 per million output tokens, with cached input at $0.16.
What is the context window of Kimi K2.6?
262K tokens, with up to 236K tokens of output.
Where is Kimi K2.6 cheapest?
Of 16 routes tracked, Chutes is cheapest at $0.39 input and $1.8 output per million tokens.
Has Kimi K2.6's price changed?
Yes. The output price went from $1.95 to $1.8, first seen Oct 27, 2026.