Kimi API pricing: every model, every rate

By the aitokensai editors · Verified 2026-11-01 Sources: Moonshot platform docs

Kimi built its reputation on very long context windows. Several tiers below include dedicated coding and high-speed variants.

Full rate card

18 billable models in total, 12 of them text models. On those text models: 0 of 12 carry a rate verified against Moonshot's own published pricing, the remaining 12 are gateway rates only. USD per 1M tokens, checked 2026-11-01.

On Moonshot the Out/In column runs 4.0× to 5.2×, median 4.2×, it outweighs the input price as soon as output dominates your bill.

Across 12 priced text models the blended rate spans $1.5 (kimi-k2) to $33.5 (kimi-k2.7-code-highspeed) per 1M tokens (a 22× spread). At 22× between its own cheapest and dearest, picking the wrong tier inside Moonshot costs more than picking the wrong vendor.

How these rates were verified

Moonshot publishes no USD rate card we could confirm against, so none of the 18 prices above is cross-checked with vendor documentation — every figure is a gateway rate read from the live rate config on 2026-11-01. That is the reason no discount percentage appears anywhere on this page: without a published list to compare against, a "saving" would be a number we made up. Read these as an observed snapshot of what the endpoint charges today, and treat the reason to route Moonshot through one endpoint as access and consolidated billing rather than a discount.

What Moonshot costs at three usage levels

Priced on kimi-k3.1-pro at $1 in / $5 out per 1M tokens, with a 5:1 input-to-output ratio, roughly what an interactive workload produces.

This is the model we cover in depth for this vendor. Swap in your own token split in the calculator.

Same budget, other vendors

3 models from 3 other vendors priced within 35% of kimi-k3.1-pro on a blended rate (the cheapest, the dearest and one in between). This is the horizontal check a Moonshot rate page on its own cannot give you.

Blended comparison (input + output per 1M tokens). Price is one axis, none of these is a Moonshot model, so treat them as candidates to test side by side at this budget rather than drop-in substitutes.

Why the output rate decides the bill

Across the 12 priced Moonshot text models, the output rate runs from 4.0× to 5.2× the input rate, with a median of 4.2×. On Moonshot that multiple lands on the smaller half of the token count and the larger half of the bill, because output is what a chat or agent turn actually produces.

Worked out: at a 4.2× multiple, a job whose token count is 80% input still spends 51% of its cost on the output it generates. Setting Moonshot beside any other vendor on the input rate alone hides that.

What Moonshot is good at

Kimi is the usual pick when you need a long context window without frontier-model pricing.

Detailed pages for Moonshot models

The models we cover in depth, each with worked cost at three usage levels and a comparison against similarly priced alternatives.

• Kimi K3.1 Pro — $1 / $5 per 1M tokens
• Kimi K3 — $1.5 / $7.5 per 1M tokens

Routing these rates into your tools

Every model above is reachable from the same OpenAI-compatible endpoint, so the rates on this page apply wherever you already work. These are the tools we have profiled end to end — Moonshot models included:

Every one of these takes the same two values (a base URL and a key) and none of them require changing your code beyond where the client is constructed. Pointed at Moonshot, that is the whole change. The differences that matter are in each tool's defaults, which is what each guide covers.

Other vendors

Every rate card here is built the same way, from the same price snapshot (2026-11-01), so the numbers are comparable across vendors:

Anthropic · OpenAI · Google · DeepSeek · Alibaba · xAI · Zhipu · Meta · MiniMax · ByteDance

FAQ

Create free account

See all 38 models → or use the cost calculator with your own token split.