Kimi K3.1 Pro Highspeed API pricing

✓ Matches the official page (checked 2026-11-19 01:00 UTC) · Official pricing ↗Synced 2026-11-19 01:00 UTC · Method

Kimi K3.1 Pro Highspeed prices per 1M tokens
FieldPer 1M tokens
Input$4.00
Output$20.00
Cached input$0.20
Cache write$4.00
Cache write (1-hour TTL)$8.00

Report a wrong price

Moonshot AI (Kimi) · Context window 1,048,576 · Max input 1,048,576 · Max output 1,048,576
vision · reasoning · tool calling · structured output
Per 1K tokens: $0.004 input, $0.02 output.

Calculate my cost →

Follow this price:
Atom feed ▾
AtomJSON

Get notified in any feed reader.

Billing rules for caching, Batch and long prompts: Moonshot AI (Kimi) API cost guide.

Price in context

Kimi K3.1 Pro Highspeed ranks 5 of 5 current Moonshot AI (Kimi) models by output price, cheapest first (Kimi K2.7 Code retiring end of December 2026 is the cheapest at $4.00, Kimi K3.1 Pro Highspeed the most expensive at $20.00). Output tokens cost 5× the input price; the median across all 119 current models is 5×. Against the whole table (median $1.25 input / $4.40 output per 1M), Kimi K3.1 Pro Highspeed is pricier on both input and output.

Cached input costs 5% of the normal input price ($0.20 vs $4.00 per 1M). In the support-chatbot scenario with 60% cache hits the month comes to $1,510 instead of $1,920 without caching (21% less). Writing a prefix to the cache costs 1× the input price ($4.00), so caching pays off once a prefix is reused 2 or more times. No batch discount is published for this model.

The context window is 1,048,576 tokens, roughly 2,097 pages of English text; 12% of current models accept more. The closest model from another provider by price is Muse Wonder 1.0 ($4.00 / $20.00); the cheapest reasoning model for the chatbot scenario is MiMo V2.6 Flash at $27.18 per month against $1,510 for Kimi K3.1 Pro Highspeed.

What it costs per month

Estimated monthly cost by workload (USD)
Scenario (per month)Kimi K3.1 Pro Highspeed
Customer support chatbot
5,000 req/day · 1,200 in · 400 out · cache 60%
$1,510
RAG over documents
2,000 req/day · 8,000 in · 600 out · cache 30%
$2,093
Coding agent
1,500 req/day · 25,000 in · 2,000 out · cache 80%
$2,880
Deep reasoning
800 req/day · 3,000 in · 6,000 out · cache 20%
$3,113
Batch processing
50,000 req/day · 1,500 in · 150 out · batch
$13,500

Adjust the numbers in the calculator.

Cheaper alternatives

Lowest monthly cost for the chatbot scenario among reasoning models:

Comparisons

Other Moonshot AI (Kimi) models

Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code retiring end of December 2026, Kimi K2.6 retiring end of December 2026 · All Moonshot AI (Kimi) API prices →

Models at a similar price

Muse Wonder 1.0 ($4.00/$20.00), Claude Opus 5.5 ($4.00/$20.00), GPT-5.6 Sol ($4.00/$20.00), Gemini 4 Neon ($3.00/$15.00), Claude Opus 5 ($5.00/$25.00), Kimi K3 ($3.00/$15.00)

Price history

No price changes recorded since tracking began on 2026-10-08. See all price changes →

Other changes (1)

Listings, fields a source added or dropped, and limit changes. These are not price moves.

Recorded price changes, USD per 1M tokens
DateChangeOld /1MNew /1MWhat happened
2026-11-07Added———

Source and checks

Source and checks
Data sourceLiteLLM price list (MIT)
Official pricingplatform.kimi.ai ↗
Last synced2026-11-19 01:00 UTC
Last price changeNo price changes recorded since tracking began on 2026-10-08.
Cross-checkMatches models.dev
Official checkVerified against the official page on 2026-11-19 (automatic check)
Price regionNot confirmed by an official check
Field-by-field check against the official page
FieldThis siteOfficialStatus
Input$4.00$4.00✓ official
Output$20.00$20.00✓ official
Cached input$0.20$0.20✓ official
Cache write$4.00$4.00✓ official
Cache write (1-hour TTL)$8.00$8.00✓ official
Context window1,048,5761,048,576✓ official
Max input1,048,576—– unchecked
Max output1,048,576—– unchecked

✓ official = the official page's value is in use (other sources' values noted) · ✓ verified = other source equals the official page · ≠ mismatch = differs and is held for confirmation; both shown · … pending = the automatic check could not read the page · – unchecked = not listed on the official page or not checked yet