moonshotaiNot yet certifiedReleased 10/23/2026

Kimi K3.1 Pro

Kimi K3.1 Pro is a frontier model from Moonshot AI for complex reasoning, coding, and agentic workflows, with support for vision, tool use, structured outputs, and long-context tasks.

View API reference ↓
Input / output priceFrom$0.24 / $7.00per 1M
24h uptime99.86%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "moonshotai/kimi-k3.1-pro",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
alibaba1.05M1.05M1.7 s40 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
Baseten1M262K1.0 s206 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
boundless1.05M1.05M0.5 s124 tps$1.70$8.50Read $0.20Write —6 featuresNoNoGlobalListed
DeepInfra1.05M1.05M0.5 s58 tps$1.90$9.50Read $0.19Write —6 featuresNoYesGlobalListed
digitalocean1.05M132K0.5 s285 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
Fireworks1.05M1.05M0.8 s64 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
inference-net1.05M1.05M0.4 s188 tps$2.00$10.00Read $0.20Write —6 featuresNoNoGlobalListed
modal1.05M1.05M0.4 s136 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
moonshotai1.05M1.05M3.0 s27 tps$2.00$10.00Read $0.20Write $2.006 featuresYesYesGlobalListed
morph1.05M1.05M0.5 s107 tps$1.68$12.00Read $0.26Write —6 featuresYesYesGlobalListed
nebius1.05M1.05M0.6 s149 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
parasail1.05M1.05M0.4 s188 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
pareto1.05M1.05M0.6 s32 tps$1.40$7.00Read $0.14Write —6 featuresNoYesGlobalListed
relace1.05M1.05M1.2 s62 tps$0.24$8.40Read $0.20Write —6 featuresYesYesGlobalListed
runware1.05M1.05M0.8 s95 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
Together AI1.05M1.05M0.4 s69 tps$2.00$10.00Read $0.20Write —6 featuresYesYesGlobalListed
wafer1.05M1.05M0.3 s108 tps$1.80$9.00Read $0.18Write —6 featuresYesYesUSListed

Uptime

24 hours

Request success rate per provider.

alibaba100.00%
Baseten99.99%
boundless100.00%
DeepInfra100.00%
digitalocean100.00%
Fireworks100.00%
inference-net99.73%
modal100.00%
moonshotai100.00%
morph99.62%
nebius100.00%
parasail100.00%
pareto100.00%
relace99.88%
runware99.74%
Together AI98.61%
wafer100.00%

Throughput

last hour

P50 output tokens per second.

digitalocean285 tps
Baseten206 tps
inference-net188 tps
parasail188 tps
nebius149 tps
modal136 tps
boundless124 tps
wafer108 tps
morph107 tps
runware95 tps
Together AI69 tps
Fireworks64 tps
relace62 tps
DeepInfra58 tps
alibaba40 tps
pareto32 tps
moonshotai27 tps

Latency

last hour

P50 time to first token.

wafer0.3 s
inference-net0.4 s
modal0.4 s
parasail0.4 s
Together AI0.4 s
morph0.5 s
boundless0.5 s
DeepInfra0.5 s
digitalocean0.5 s
pareto0.6 s
nebius0.6 s
runware0.8 s
Fireworks0.8 s
Baseten1.0 s
relace1.2 s
alibaba1.7 s
moonshotai3.0 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "moonshotai/kimi-k3.1-pro",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. moonshotai/kimi-k3.1-pro. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Kimi K3.1 Pro supports up to 262,144 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by moonshotai

ModelContextInputOutputCacheRelease
moonshotai/kimi-k3.1-pro-highspeed1.05M$4.00$20.00Read $0.20Write $5.0010/23/2026
moonshotai/kimi-k3-fast1M$6.00$22.50Read $0.60Write —07/27/2026
moonshotai/kimi-k31M$3.00$15.00Read $0.30Write —07/16/2026
moonshotai/kimi-k2.7-code-highspeed262K$1.90$8.00Read $0.38Write —06/15/2026
moonshotai/kimi-k2.7-code256K$0.95$4.00Read $0.19Write —06/12/2026
moonshotai/kimi-k2.6262K$0.95$4.00Read $0.16Write —04/20/2026
moonshotai/kimi-k2.5256K$0.60$3.00Read —Write —01/26/2026
moonshotai/kimi-k2131K$0.57$2.30Read —Write —07/11/2025