Pular para o conteúdo principal

Moonshot AIAdded Jul 16, 2026PrivateOpen weights

Kimi K3

Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.

kimi-k3POST https://api.venice.ai/api/v1/chat/completions
Input / output
$3.75 / $18.75
per 1M tokens
Context
1M
128K max output
Reasoning
none, low, high, max
default max
Cached input
$0.375
90% off input
Modalities
Text, image
out: text

Pricing

USD per 1M tokens
Input
$3.75
Cached input
$0.375
Output incl. reasoning
$18.75
Similar modelsInputOutputOutput price, relative
Kimi K3$3.75$18.75
GPT-5.6 Sol$4.00$20.00
GPT-5.6 Sol Pro$4.00$20.00
Claude Opus 5.5$4.00$20.00
Claude Opus 5$5.00$25.00

Prompt caching is automatic; see Prompt caching.

Specs

Model ID
kimi-k3
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
131,072 tokens
Reasoning effort
reasoning_effort: none | low | high | max · default max · guide
Served precision
Not disclosed
Added
Jul 16, 2026
Weights
Open

Capabilities

Modalities
Text
Input and output
Image
Input only · up to 10
Audio
Not supported
Video
Not supported
Features
Streaming (SSE)
Supported
Function calling
Supported
Structured output (json_schema)
Supported
Reasoning effort
none, low, high, max
Prompt caching
Supported
Web search
venice_parameters
X search
Not supported
Log probabilities
Not supported
Fine-tuning
Not supported
Image generation
Not supported
POST/api/v1/chat/completionsRecommended
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "max"
}'

Privacy

Tier 1
Anonymized

Included

Tier 2 · this model
Private

Zero data retention, enforced by contract. Prompts and outputs aren’t stored.

Tier 3
TEE
Tier 4
End-to-end encrypted

Variants

VariantModel IDPrivacyContextMax outputInput / outputEffortAdded
kimi-k3Private1M128K$3.75 / $18.75none, low, high, maxJul 2026
kimi-k3-fast-apiPrivate1M128K$4.50 / $22.50none, low, high, maxAug 2026
e2ee-kimi-k3-pE2EE1M128K$3.75 / $18.75none, maxSep 2026