When was Kimi K3.1 Pro released?

Moonshot released Kimi K3.1 Pro on 23 Oct 2026. It is available through the Opper gateway.

Does Kimi K3.1 Pro support zero data retention?

Yes. Kimi K3.1 Pro is available with zero data retention on Berget, DeepInfra, Fireworks, Lyceum, Novita, TensorX through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is Kimi K3.1 Pro hosted?

Kimi K3.1 Pro runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Kimi K3.1 Pro trained on prompts and outputs?

Training behaviour varies by route. See the per-route data-handling section for each provider's training posture.

Kimi K3.1 Pro

by Moonshot

Released 99 days after Kimi K3 · All Moonshot releases

Kimi K3.1 Pro is Moonshot AI’s successor to Kimi K3. It accepts text, images and video in a 1,048,576-token context window and produces text. Moonshot positions it for coding, agent workflows, visual work and complex analysis. The API supports tool calls, strict JSON schema output and reasoning effort levels low, high and max. The model is available on Moonshot’s API; Moonshot says the weights are planned for release by November 4, 2026.

Call Kimi K3.1 Pro on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

328K

Max output

—

Input price

$3.32 /1M$0.99 cache read

Output price

$11.05 /1M

Released

23 Oct 2026

Web search

Via Opper

EU residency available on Berget, Lyceum and TensorX
US residency available on DeepInfra, Morph and Novita
Zero data retention on pay-as-you-go

Available routes

Kimi K3.1 Pro runs on 11 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Berget (Sweden), Lyceum and TensorX. See every Kimi model hosted in the EU.

Provider	Region	Training	Input	Output	Cache read
Berget	EU	No	$3.32	$11.05	$0.99
DeepInfra	US	No	$2.00	$10.00	$0.20
Fireworks	Multi	No	$2.00	$10.00	$0.20
Lyceum	EU	No	$2.00	$10.00	$0.20
Moonshot AI	Multi	Yes	$2.00	$10.00	$0.20$2.00 write
Moonshot AI	Multi	Yes	$4.00	$20.00	$0.20$4.00 write
Morph	US	No	$1.91	$12.00	$0.47
Nebius	Multi	No	$2.00	$10.00	$0.20
Novita	US	No	$2.00	$10.00	$0.20$2.00 write
Novita	US	No	$4.00	$20.00	$0.20$4.00 write
TensorX	EU	No	$3.00	$15.00	$0.75

Live routes and prices as JSON: api.opper.ai/v3/models?q=kimi-k3.1-pro

Uptime and availability

Kimi K3.1 Pro runs on 6 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 99.02% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

6 monitored providers serve Kimi K3.1 Pro.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 3 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Kimi K3.1 Pro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Berget — Sweden🇸🇪

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
Transfer mechanism: Not applicable — data stays in EU

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Transfer mechanism: SCCs

Fireworks — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Subprocessor access: Subprocessors may read content
Transfer mechanism: SCCs

Lyceum — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Subprocessor access: Subprocessors may read content
Transfer mechanism: Not applicable — data stays in EU

Moonshot AI — Multi-region

Content is retained: used for training by default. Trained on customer data by default. GLOBAL; unknown.

Zero data retention: Retained: used for training by default.
Training: Trained on customer data by default.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
Transfer mechanism: unknown

Moonshot AI — Multi-region

Content is retained: used for training by default. Trained on customer data by default. GLOBAL; unknown.

Zero data retention: Retained: used for training by default.
Training: Trained on customer data by default.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
Transfer mechanism: unknown

Morph — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. US; SCCs.

Zero data retention: With abuse monitoring, 30-day window.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Abuse monitoring: On by default, holds flagged content, a person can view samples
Transfer mechanism: SCCs

Nebius — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Abuse monitoring: No classifier
Transfer mechanism: SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Transfer mechanism: SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Transfer mechanism: SCCs

TensorX — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Transfer mechanism: Not applicable — data stays in EU

Best for

Where Kimi K3.1 Pro ranks among the models on Opper with a score for each use case.

Agents#2 of 8970.3

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →Healthcare#8 of 4551.6

Healthcare and medicalSee the Healthcare ranking →Finance#10 of 4853.3

Finance and accountingSee the Finance ranking →Coding#10 of 4742.2

FrontierCode 2.0 and Terminal-Bench 4.0See the Coding ranking →Legal#11 of 4849.2

Legal tasks and reasoningSee the Legal ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#12 of 512 LLMs

TierStrong

Output speed28 tok/s

Intelligence Index46.5

Coding

FrontierCode 2.0

26%

Terminal-Bench 4.0

67%

SciCode

61%

Agentic & knowledge work

AutomationBench

73%

GDPval

68%

GDP.pdf

31%

Briefcase (Elo)1675

Science & reasoning

Terminal-Bench Science

34%

CritPt (hard)

50%

HLE Diamond

37%

Humanity's Last Exam

53%

Long-context reasoning

86%

Knowledge

Omniscience29.9

MMMU-Pro

84%

By domain

Finance & accounting

53.3

Legal

49.2

Healthcare & medical

51.6

Engineering

50.9

Economics

49.9

Strategy & operations

57.6

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Kimi K3.1 Pro through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Kimi K3.1 Pro is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "kimi-k3.1-pro",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);