Kimi K3

MoonshotAIReleased Jul 16, 2026

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

Input, per 1M tokens: $3.60$3.31 for holders
Output, per 1M tokens: $18.00$16.56 for holders
Context: 1M tokens
Tokens this week: None yet

Price

Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.

Charge	Agents	Holders	Per
Inputper 1M tokens	$3.60	$3.31	per 1M tokens
Outputper 1M tokens	$18.00	$16.56	per 1M tokens
Cached inputper 1M tokens	$0.36	$0.33	per 1M tokens

Price history

What an agent paid per million tokens, by day.

Unchanged since Sep 29, 2026: $3.60 in and $18.00 out per million tokens.

Usage through bInference

Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.

Last 7 days: 0
Last 30 days: 0
All time: 0

InputOutputReasoning

Where it runs

The hosts serving this model now, and how often each answered over the last day.

Use it

Two settings: our address and your agent’s key. The model is set in each call.

import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://binference.io/api/v1",Address  apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({  model: "moonshotai/kimi-k3",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address  -H "Authorization: Bearer $BINF_API_KEY" \Key  -H "Content-Type: application/json" \  -d '{    "model": "moonshotai/kimi-k3",    "messages": [{ "role": "user", "content": "Hello" }],    "max_tokens": 1024  }'

Questions

More from MoonshotAI

Kimi K2.7 CodeMoonshotAI262K$0.79 in · $3.96 out$0.72 in · $3.64 out Kimi K2.6MoonshotAI262K$0.78 in · $4.09 out$0.72 in · $3.76 out Kimi K2.5MoonshotAI262K$0.54 in · $2.70 out$0.50 in · $2.48 out Kimi K2 ThinkingMoonshotAI262K$0.72 in · $3.00 out$0.66 in · $2.76 out

Agents

Holders

Inputper 1M tokens

$3.60

$3.31

per 1M tokens

Outputper 1M tokens

$18.00

$16.56

per 1M tokens

Cached inputper 1M tokens

$0.36

$0.33

per 1M tokens

Host	Answered, last day	Context
InferenceNetFp4fp4, having trouble	99.6%	1M
RelaceFp4fp4, answering	97.6%	1M
Sail ResearchFp4fp4, answering	99.8%	1M
Wafer, answering	99.8%	1M
Makora, answering	99%	1M
MorphFp8fp8, answering	99.3%	1M
Phala, answering	99.5%	1M
DigitalOcean, answering	87.5%	1M
WaferUS, answering	99.8%	1M
DeepInfraBf16bf16, answering	98.7%	1M
DecartMxfp4mxfp4, having trouble	78.4%	1M
AkashMLFp4fp4, answering	99.7%	1M
ChutesMxfp4mxfp4, answering	98.2%	1M
ParasailFp4fp4, answering	99%	1M
ModalMxfp4mxfp4, answering	99.5%	1M
Together, having trouble	99%	1M
Fireworks, answering	99.9%	1M
BaseTenFp8fp8, answering	97.8%	1M
Moonshot AIMxfp4mxfp4, answering	99.8%	1M
FireworksUS, answering	99.5%	1M
Alibaba, answering	93.7%	1M
FireworksFast, answering	99.5%	1M

Host

Answered, last day

Context

InferenceNetFp4fp4

99.6%

RelaceFp4fp4

97.6%

Sail ResearchFp4fp4

99.8%

Wafer

99.8%

Makora

99%

MorphFp8fp8

99.3%

Phala

99.5%

DigitalOcean

87.5%

WaferUS

99.8%

DeepInfraBf16bf16

98.7%

DecartMxfp4mxfp4

78.4%

AkashMLFp4fp4

99.7%

ChutesMxfp4mxfp4

98.2%

ParasailFp4fp4

99%

ModalMxfp4mxfp4

99.5%

Together

99%

Fireworks

99.9%

BaseTenFp8fp8

97.8%

Moonshot AIMxfp4mxfp4

99.8%

FireworksUS

99.5%

Alibaba

93.7%

FireworksFast

99.5%

import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://binference.io/api/v1",Address apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({ model: "moonshotai/kimi-k3", messages: [{ role: "user", content: "Summarize today's trades" }], max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address -H "Authorization: Bearer $BINF_API_KEY" \Key -H "Content-Type: application/json" \ -d '{ "model": "moonshotai/kimi-k3", "messages": [{ "role": "user", "content": "Hello" }], "max_tokens": 1024 }'

Kimi K3

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

More from MoonshotAI

Similar models

Kimi K3

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

More from MoonshotAI

Similar models

Where it runs

Kimi K3

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

How much does Kimi K3 cost?

How does my agent use Kimi K3?

How much can Kimi K3 read at once?

What can Kimi K3 do?

Are my prompts stored?

More from MoonshotAI

Similar models

Kimi K3

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

How much does Kimi K3 cost?

How does my agent use Kimi K3?

How much can Kimi K3 read at once?

What can Kimi K3 do?

Are my prompts stored?

More from MoonshotAI

Similar models

Where it runs