Models/Moonshot AI/Kimi K3

Moonshot AI

Kimi K3

moonshot/kimi-k3

Live on DIT

Get API Key

$3 input / $15 output per 1M tokens; $0.30 per 1M cached input tokens.

ModalitiesText + Image + Video → Text

DIT in / out$2.4 / $9per 1M tokens

Context1.05Mreviewed context window

Max output1.05Mtokens per response

ReleasedJul 16, 2026OPENAI compatible

Capabilities

Reasoning

Tool calling

Structured outputs

Reviewed Oct 17, 2026Moonshot AI model documentation ↗models.dev catalog ↗DIT live model catalog ↗

Overview

Recommended use cases and a precise technical profile, generated from the same reviewed model record used throughout this page.

Technical profileReviewed model metadata

Model ID	kimi-k3	Provider	Moonshot AI
Protocol	OPENAI compatible	DIT availability	2 active routes
Input	Text, Image, Video	Output	Text
Context window	1,048,576 tokens	Maximum output	1,048,576 tokens
Released	Jul 16, 2026	Knowledge cutoff	—

Reasoning controls

Official identifiers and selectable reasoning effort

Aliases

No alias published

Reasoning effort

No default published

Supported API endpointsOfficial model API surface

Endpoint	Path	Status
Chat Completions	`/v1/chat/completions`	Supported

Providers

Compare DIT market routing with the official upstream reference across price, speed, and availability. Supplier identities remain private.

Market coverage2 active routes

Selection strategyPrice + health + automatic failover

Runtime window30 days

Provider	Input /M	Output /M	Cache read /M	Latency	Throughput	Uptime
DIT Market 40% off Aggregated supply · 2 active routes	$3$2.4	~~$15~~$9	—	2913 msP50 TTFT	64.1 tpsP50 output	54.13%30-day success
MMoonshot AI official Reference Direct upstream · reviewed list price	$3	$15	—	—Awaiting data	—Awaiting data	—No status source

Prices are USD per 1M tokens. DIT performance and uptime appear only after 50 eligible requests; supplier identities and customer traffic remain private.

Pricing

Compare DIT market rates directly with reviewed official prices so savings remain visible and auditable.

Current price comparison

Effective DIT rate compared with the reviewed official list price.

Effective

USD / 1M tokens

Up to 40% lower

Direct rate comparison · reviewed standard prices per 1M tokens

Price composition

DIT effective rate mix

$11.4combined rate

InputOutput

Relative rate composition, not estimated invoice share

Price comparisonReviewed source ↗

Usage	Official	DIT market	Saving	Billing basis
Input tokens	$3	$2.4	~40%	Per 1M tokens
Output tokens	$15	$9	~40%	Per 1M tokens
Cached input	—	—	—	Per 1M cached tokens

Performance

Latency, throughput, activity, and request success use privacy-safe DIT runtime aggregates only when the eligibility threshold is met.

Throughput

64.1 tok/s

P50 across eligible DIT traffic

Latency

2913 ms TTFT

Lower is better

Runtime sample

109

30-day privacy-safe window

All locations

P50 / P95

30-day eligible DIT traffic · privacy-safe aggregates

Latency distribution

Time to first token and end-to-end

Lower is better · aggregated eligible requests only

Traffic activity

Privacy-safe normalized request index

Relative shape only; customer traffic totals remain private

Request success

Eligible DIT request completion rate

54.13%

System probes and user fallback traffic excluded

DIT runtime distribution30-day eligible traffic

Metric	P50	P95	Reading
Time to first byte	2913 ms	71888 ms	Lower is better
End-to-end latency	22753 ms	—	Lower is better
Output throughput	64.1 tps	—	Higher is better

Uptime

A concise service-health view with scope and source stated next to the number.

54.13%30-day eligible request success

~110 eligible requestsSystem probes and user fallback traffic excluded

Quick Start

A copy-ready request for the compatible DIT endpoint using this model's reviewed identifier.

cURLOPENAI compatible

curl https://api.dit.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [{"role":"user","content":"Explain dynamic model routing."}]
  }'

Sources

Field-level provenance keeps pricing, limits, capabilities, and benchmarks independently reviewable.

Reviewed sources3 references · reviewed Oct 17, 2026

Source	Type	Covers	Checked
Moonshot AI model documentation ↗	Official	Context, Modalities, Capabilities	Oct 17, 2026
models.dev catalog ↗	models.dev	Context, Modalities, Pricing	Oct 17, 2026
DIT live model catalog ↗	DIT catalog	DIT availability, Pricing	Oct 17, 2026

Official sources take priority. Third-party metadata is retained only when its field and review date are shown.

Models like Kimi K3

Reviewed models ranked by capability overlap, protocol compatibility, and context similarity.

Qwen3.8 MaxAlibaba Cloud

1MContextOfficial: $2 / $6

GLM 5.3 FlashZ.ai

1.05MContextOfficial: $0.15 / $0.5

GPT-5.6 SolOpenAI

1.05MContextOfficial: $4 / $20

Frequently asked questions

Answers use the same reviewed facts and pricing fields presented in the tables above.

What is Kimi K3?+

$3 input / $15 output per 1M tokens; $0.30 per 1M cached input tokens.

How much does Kimi K3 cost?+

The reviewed official rate is $3 per 1M input tokens and $15 per 1M output tokens. DIT pricing is shown only when a live DIT route exists.

What is the context length of Kimi K3?+

Kimi K3 supports a reviewed context window of 1,048,576 tokens and up to 1,048,576 output tokens.

What capabilities does Kimi K3 support?+

Reviewed capabilities include Reasoning, Tool calling, Structured outputs. Consult the linked official documentation for endpoint-specific limits.

What inputs and outputs does Kimi K3 support?+

Reviewed input modalities: Text, Image, Video. Reviewed output modalities: Text.

Which API endpoints and reasoning levels does Kimi K3 support?+

Kimi K3 is documented for Chat Completions.

Is Kimi K3 available on DIT?+

Kimi K3 currently has 2 active routes. DIT selects eligible supply by price and health, with automatic failover when another route is available.

When was Kimi K3 released?+

Kimi K3 was released on Jul 16, 2026.