Skip to main content
Moonshot AISep 8, 2026

Kimi K3 E2EE

e2ee-kimi-k3-pOpen weights

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows.

  • Prompts are decrypted only inside an attested TEE on the GPU.
  • Calls need the E2EE handshake. Without it, requests reach Venice as plaintext and run TEE-only. How to call an E2EE model
$3.75/$18.75
per 1M in / out
1M
context window
128K
max output
Also available without end-to-end encryption$3.75 / $18.75 per 1M
How it comparesamong 143 text models
Pricecheaper than 15%$7.50
First token—
Output speed—
Context windowlarger than 43%1M

Further right is better. Hover a dot for its model.

Capabilities

What the model takes in, returns and supports through the API.

InTextImage
OutText

Not supportedvideo input, audio input, X search and log probabilities

Performance

Measured on Venice API traffic over the last 24 hours.

Time to first token—
Output speed—
Uptime—

How it’s measured

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$3.75per 1M tokens
Cached input$0.37590% off input
Output$18.75per 1M tokens

Estimate a workload

$0.0169per request
$169for 10,000 requests

Blended price against similar models

Kimi K3 E2EE$7.50

Per 1M tokens at three input tokens for each output token.

Specs

Model ID
e2ee-kimi-k3-p
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
131,072 tokens
Reasoning
none · max · default max
Precision
Not disclosed
Privacy
E2EE
Added
Sep 8, 2026

Compare

ModelInputOutputContextMax outputFirst tokenSpeed
Kimi K3 E2EE$3.75$18.751M128K——
Claude Opus 5.5$4.00$20.001M128K——
GPT-5.6 Sol$4.00$20.001M128K——
GPT-5.6 Sol Pro$4.00$20.001M128K——
Muse Wonder$5.00$25.001M128K——

Other versions

  1. Kimi K2.6 E2EESep 2026
  2. Kimi K3 E2EESep 2026

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "e2ee-kimi-k3-p",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "max"
}'
Base URL https://api.venice.ai/api/v1

These samples send the prompt as plaintext, so the request runs TEE-only. For end-to-end encryption, send encrypted messages with the E2EE headers, as the TEE and E2EE guide shows.

Parameters

ParameterValuesNotes
modele2ee-kimi-k3-pRequired
messagestext · image_urlContent parts the model reads
max_completion_tokensUp to 131,072Counts reasoning tokens
reasoning_effortnone | maxDefault max
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations