VerifiedChat

Kimi-K3

by 0G Foundation

Moonshot AI Kimi K3; multimodal input (text, image, video), text output. 1M context, deep thinking always on. Function calling and implicit prompt caching supported.

openaiTool CallingModalities

Context

1,000,000 tokens

Max Output

131K

131,072 tokens

Input

per 1M tokens

Output

$15

per 1M tokens

Provider

3 endpoints across 3 providers

Tencent (CN)TEE (dstack)TeeTLS

Input / 1M

$3 ·15.54000G/M

Output / 1M

$15 ·77.72000G/M

Cache Read / 1M

$0.3 ·1.55400G/M

Tencent (CN)TEE (dstack)TeeTLS

Input / 1M

$3 ·15.55000G/M

Output / 1M

$15 ·77.76000G/M

Cache Read / 1M

$0.3 ·1.55500G/M

anonymous1Non-verifiable

Input / 1M

$3 ·15.40000G/M

Output / 1M

$15 ·77.03000G/M

Cache Read / 1M

$0.3 ·1.54000G/M

API

POSThttps://router-api.0g.ai/v1/chat/completions

curl "https://router-api.0g.ai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

Create API key

Additional Features

TEE Verification

Request on-chain signature verification with verify_tee. The response includes a tee_verified field in the trace.

{
  "model": "kimi-k3",
  "messages": [{"role": "user", "content": "Hello!"}],
  "verify_tee": true
}

Provider Routing

Control which provider handles your request using the X-0G-Provider-* request headers.

X-0G-Provider-Address pins a provider; X-0G-Provider-Identity pins which of its upstreams to route through — both values come from the address and provider_identity fields of GET /v1/providers. Together they address one specific upstream of one provider. Send neither and the router picks by price and health, exactly as before.

curl "https://router-api.0g.ai/v1/chat/completions" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -H "X-0G-Provider-Address: <PROVIDER_ADDRESS>" \
  -H "X-0G-Provider-Identity: <UPSTREAM>" \
  -H "X-0G-Provider-Sort: latency" \
  -H "X-0G-Provider-Allow-Fallbacks: true" \
  -d '{
    "model": "kimi-k3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Try in Playground