Skip to content
Sovyron

Kimi K2.8 Preview

kimi1.0M context1.0M max outputreleased Sep 11, 2026ReasoningTool calling

As of Nov 22, 2026, the cheapest Kimi K2.8 Preview API price is $1 per 1M input tokens (DevPass (LLM Gateway)) and $4 per 1M output tokens (DevPass (LLM Gateway)). Kimi K2.8 Preview is offered by 4 providers in the kimi family, reasoning enabled. One provider lists it as a free-tier offer.

Cheapest input
$1
Cheapest output
$4
Official
—
output per 1M tokens
Providers
4
offering this model
Spread
1.0×
max / min output
Free offers
1
free-tier offer

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Kimi K2.8 Preview API prices by provider in USD per 1M tokens, updated Nov 22, 2026
DevPass (LLM Gateway)kimi-k2.8-previewCheapest$1Cheapest$4$0.25—1.0M
LLM Gatewaytencent/kimi-k2.8-preview$1$4$0.25—1.0M
Kimi For Coding (kimi.com)freekimi-for-codingfreefreefreefree1.0M

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Volcengine Ark Coding Planplanfreefree1.0M

Kimi K2.8 Preview pricing FAQ

What is the cheapest Kimi K2.8 Preview API?

As of Nov 22, 2026, DevPass (LLM Gateway) has the lowest Kimi K2.8 Preview output price at $4 per 1M tokens, and DevPass (LLM Gateway) has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Kimi K2.8 Preview?

4 providers list Kimi K2.8 Preview on Sovyron; 2 of them sell it at a metered per-token price.

Is Kimi K2.8 Preview free?

One provider lists a free-tier offer: Kimi For Coding (kimi.com). Free tiers usually have rate limits.

What is the context window of Kimi K2.8 Preview?

Kimi K2.8 Preview supports a 1.0M-token context window and up to 1.0M output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—