Skip to content
Sovyron

Kimi K3.1 Pro Highspeed

kimi-pro1.0M context1.0M max outputreleased Oct 23, 2026Open weightsReasoningTool calling4 subscription plans →

As of Nov 22, 2026, the cheapest Kimi K3.1 Pro Highspeed API price is $3.6 per 1M input tokens (Wallaby) and $18 per 1M output tokens (Wallaby). Kimi K3.1 Pro Highspeed is offered by 14 providers in the kimi-pro family, open weights, reasoning enabled. Moonshot AI's own rate is $20 per 1M output tokens. 2 providers list it as a free-tier offer. It is also included in 4 flat-rate subscription plans, Moonshot AI Kimi Code Moderato from $19/mo.

Cheapest input
$3.6
Cheapest output
$18
Official (Moonshot AI)
$20
output per 1M tokens
Providers
14
offering this model
Spread
1.4×
max / min output
Free offers
2
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

Kimi K3.1 Pro Highspeed API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Wallabyopenmoonshotai/kimi-k3.1-pro-highspeedCheapest$3.6Cheapest$18$0.18—1.0M—
DevPass (LLM Gateway)kimi-k3.1-pro-highspeed$3.8$19$0.19$41.0M5d agoout −5%
Moonshot AI (China)openkimi-k3.1-pro-highspeed$3.8874$20.3342$0.1944$3.88741.0M—
Amazon Bedrockglobalopenglobal.moonshotai.kimi-k3.1$4$20$0.2$51.0M—
Kilo Gatewaymoonshotai/kimi-k3.1-pro-highspeed$4$20$0.2$51.0M—
LLM Gatewaymoonshot/kimi-k3.1-pro-highspeed$4$20$0.2$41.0M—
Moonshot AIopenkimi-k3.1-pro-highspeed$4$20$0.2$41.0M—
NanoGPTmoonshotai/kimi-k3.1-pro-highspeed$4$20$0.2$41.0M—
Novita AIopenmoonshotai/kimi-k3.1-pro-highspeed$4$20$0.2$41.0M—
Requestyopenkimi-k3.1-pro-highspeed$4$20$0.2$41.0M—
Vercel AI Gatewaymoonshotai/kimi-k3.1-pro-highspeed$4$20$0.2$51.0M—
Amazon Bedrockusopenus.moonshotai.kimi-k3.1$4.4$22$0.22$5.51.0M—
Venice AIkimi-k3-1-pro-highspeed$5$25$0.375—1.0M17d agoout −33.3%
Kimi For Coding (kimi.ai)freek3.1-pro-highspeedfreefreefreefree1.0M—
Kimi For Coding (kimi.com)freek3.1-pro-highspeedfreefreefreefree1.0M—

Kimi K3.1 Pro Highspeed price history

Output price per 1M tokens since tracking began on Oct 24, 2026, for the 2 providers whose rate moved. Each step is a recorded change. All recent price changes.

Kimi K3.1 Pro Highspeed output price per 1M tokens by provider, Oct 24, 2026 to Nov 22, 2026$0$12.5$25$37.5$50Oct 24, 2026Nov 8, 2026Nov 22, 2026
DevPass (LLM Gateway)$19Venice AI$25
Kimi K3.1 Pro Highspeed price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
DevPass (LLM Gateway)$4 → $3.8$20 → $19−5%
Venice AI$7.5 → $5$37.5 → $25−33.3%
Venice AI$6 → $7.5$30 → $37.5+25%

Kimi K3.1 Pro Highspeed pricing FAQ

What is the cheapest Kimi K3.1 Pro Highspeed API?

As of Nov 22, 2026, Wallaby has the lowest Kimi K3.1 Pro Highspeed output price at $18 per 1M tokens, and Wallaby has the lowest input price at $3.6 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does Kimi K3.1 Pro Highspeed cost on Moonshot AI?

Moonshot AI charges $4 per 1M input tokens and $20 per 1M output tokens for Kimi K3.1 Pro Highspeed.

How many providers offer Kimi K3.1 Pro Highspeed?

14 providers list Kimi K3.1 Pro Highspeed on Sovyron; 13 of them sell it at a metered per-token price.

Is Kimi K3.1 Pro Highspeed free?

2 providers list a free-tier offer: Kimi For Coding (kimi.ai), Kimi For Coding (kimi.com). Free tiers usually have rate limits.

Is Kimi K3.1 Pro Highspeed included in a subscription plan?

Yes. 4 flat-rate plans include it; the cheapest is Moonshot AI Kimi Code Moderato at $19/month.

What is the context window of Kimi K3.1 Pro Highspeed?

Kimi K3.1 Pro Highspeed 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

—