Kimi models in Quad Chat

Kimi models in Quad Chat at a glance

Quad Chat includes 2 Moonshot AI model families with 2 selectable variants, from Kimi K3 to Kimi K2.7 Code. Each variant below lists the plan that opens it, its context window, the longest reply it can write and the provider's API price per million tokens. 1 of the 2 variants is on the Free plan, which needs no credit card: Kimi K2.7 Code. The remaining 1 needs a paid plan. Context windows run from 256K tokens (Kimi K2.7 Code) to 1M tokens (Kimi K3). At provider list prices, input costs $0.95 to $3.00 and output $4.00 to $15.00 per million tokens across the family; Kimi K2.7 Code is the cheapest. API prices are the model provider's list prices per million tokens, shown for comparison only. Quad Chat plans have a flat monthly price and draw usage from shared credits, so you are not billed per token.

Every Kimi variant: plan, context and API price

One row per selectable variant. Click a header to sort; each name opens its model page. Context and output are in tokens; prices are provider list prices per million tokens. Variants and plans: Kimi K3 (Go, 1M context, $3.00 in / $15.00 out); Kimi K2.7 Code (Free, 256K context, $0.95 in / $4.00 out).

Which plan unlocks which Kimi model

Plans are cumulative: a higher plan opens everything the lower ones do. Free: Kimi K2.7 Code. Go ($8/month): Kimi K3. Monthly shared credits by plan: Free 100, Go 1,200, Pro 2,000, Ultra 5,000, Max 25,000.

How to choose between Kimi models

These pointers come straight from the catalog data above, not from benchmarks. The fastest way to decide is to send one prompt to two variants in the same chat. Lowest API cost: Kimi K2.7 Code at $0.95 in / $4.00 out per million tokens, on the Free plan. Highest tier by plan: Kimi K3, which needs the Go ($8/month) plan and lists at $3.00 in / $15.00 out. Largest context window: 1M tokens on Kimi K3. Longest single reply: 128K tokens on Kimi K3. Reasoning: every Kimi variant here can reason before it answers; Kimi K3 offer adjustable effort. Image input: every variant accepts images, so you can attach screenshots, photos and scans. Privacy: every variant runs on the Quad Chat Private Lane with Zero Data Retention routing.

Prices and credits in Quad Chat

API prices are the model provider's list prices per million tokens, shown for comparison only. Quad Chat plans have a flat monthly price and draw usage from shared credits, so you are not billed per token. Cheaper variants use fewer credits per message than frontier ones, so a plan's credits do not map to a fixed number of messages. Running out of credits does not lock you out: you can wait for the next period, upgrade, or buy a one-time credit pack.

Frequently asked questions

Which Kimi models are free in Quad Chat?

1 of the 2 Kimi variants is on the Free plan, which needs no credit card: Kimi K2.7 Code. The rest needs a paid plan. Free accounts get 100 shared credits a month across every model.

Which plan do I need for Kimi K3?

Kimi K3 is the highest-tier Kimi variant in Quad Chat and needs the Go ($8/month) plan or higher. Every plan shares one monthly credit balance across all models, and paying yearly is up to 15% less than paying monthly.

What is the largest Kimi context window in Quad Chat?

Kimi K3 has the largest context window in the Kimi lineup here at 1M tokens, according to the model catalog Quad Chat routes through. Files, pasted text and earlier messages all count toward the window. The smallest is 256K tokens.

How much do Kimi models cost per million tokens?

At provider list prices, input tokens range from $0.95 to $3.00 per million and output tokens from $4.00 to $15.00 per million across these variants; Kimi K2.7 Code is the cheapest overall. Quad Chat does not bill per token: plans are a flat monthly price with shared credits.

Can I use Kimi models next to models from other labs?

Yes. Every Kimi model in Quad Chat can be switched with any other model in the same conversation without losing your files or context, and you can send one prompt to several models and compare the answers side by side. See the full model comparison table to line them up against other labs.

Does Quad Chat give me the official Moonshot AI app?

No. Quad Chat gives you Moonshot AI's models inside Quad Chat's own workspace, with its search, files, projects and image and video tools. It does not include Moonshot AI's own apps or account-level features, and the model list changes as new versions ship.