Kimi K3 API pricing

7 providers serve Kimi K3. Kimi K3 is a proprietary API model, up to 1049K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-08-28 · list prices from provider APIs
Input floor $2.85/1M at DeepInfra Output floor $14.25/1M at DeepInfra Find your workload winner →

About Kimi K3

Kimi K3 was listed on the marketplace 2026-07-16 by Moonshotai. It is a text+image+video → text model with a 1049K-token context window. The weights are published as Kimi K3 on Hugging Face.

Provider Input $/1M Output $/1M Cache read $/1M Context
DeepInfra $2.85 $14.25output floor $0.285 1049K Use
Databricks $3.00 $15.00 $0.300 1000K Use
Moonshot $3.00 $15.00 $0.300 1049K Use
Together AI $3.00 $15.00 $0.300 1049K Use
Fireworks AI $3.00 $15.00 $0.300 1049K Use
Novita AI $3.00 $15.00 $0.300 1049K Use
OpenRouter marketplace quote $3.00 $15.00 $0.300 1049K Use

Price since listing

First tracked input floor: $3.00/1M on 2026-07-17. Latest: $2.85/1M on 2026-08-28 (43 days tracked).

The cheapest way to run Kimi K3

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $627/month, at DeepInfra. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Kimi K2 $0.500 $2.00 11
Kimi K2.5 $0.450 $2.25 10
Kimi K2.6 $0.650 $3.40 9
Kimi K2 Thinking $0.600 $1.20 9
Kimi K2.7 Code $0.660 $3.40 8
MoonshotAI Kimi Latest $2.00 $5.00 2

FAQ

What is the cheapest API for Kimi K3?

As of 2026-08-28, the lowest input price for Kimi K3 is DeepInfra at $2.85 per 1M input tokens. The lowest output price is DeepInfra at $14.25 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Databricks at $3.00, a 5% difference.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON