> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-docs-revamp.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Venice API
Die API für privaten, uneingeschränkten Zugang zu Intelligenz.
OpenAI-kompatibel: Chat, Bild, Audio und Video hinter einem API-Schlüssel.
```bash curl theme={"dark"}
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org-glm-5-1",
"messages": [{"role": "user", "content": "Build without permission."}]
}'
```
```ts TypeScript theme={"dark"}
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.VENICE_API_KEY,
baseURL: "https://api.venice.ai/api/v1",
});
const res = await client.chat.completions.create({
model: "zai-org-glm-5-1",
messages: [{ role: "user", content: "Build without permission." }],
});
```
```python Python theme={"dark"}
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["VENICE_API_KEY"],
base_url="https://api.venice.ai/api/v1",
)
res = client.chat.completions.create(
model="zai-org-glm-5-1",
messages=[{"role": "user", "content": "Build without permission."}],
)
```
Endpoints
Eine API für jede Modalität
Chat, Bild, Audio, Video und Embeddings hinter einem API-Schlüssel.
Plus Embeddings, File Inputs, MCP-Tools und Wallet-Zahlungen. Alle Endpoints ansehen →
Agents
Gemacht für KI-Agenten
Private Inferenz, MCP-Tools und wallet-finanzierte Workflows für Messaging-, Coding- und On-Chain-Agenten.
Den AI-Agents-Hub erkunden →
Modelle
Beliebte Modelle
Einige der meistgenutzten Modelle auf Venice. Verwenden Sie die ID als Ihren `model`-Parameter.
250+ Modelle
Text, Bild, Audio und Video
Katalog durchsuchen →
Tools
Integrierte Tools für Chat-Modelle
Schalten Sie Web-Search ein, hängen Sie Dateien an oder fragen Sie eine Blockchain mit `venice_parameters` oder einem Venice-eigenen Endpoint ab.
Fügen Sie jedem Textmodell über `enable_web_search` Echtzeit-Web-Search mit Zitaten hinzu.
```bash Curl theme={"dark"}
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org-glm-5-1",
"messages": [{"role": "user", "content": "What are the latest developments in AI?"}],
"venice_parameters": {
"enable_web_search": "auto"
}
}'
```
```ts TypeScript theme={"dark"}
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.VENICE_API_KEY!,
baseURL: "https://api.venice.ai/api/v1",
});
const completion = await client.chat.completions.create({
model: "zai-org-glm-5-1",
messages: [{ role: "user", content: "What are the latest developments in AI?" }],
// @ts-expect-error - Venice-specific parameter
venice_parameters: {
enable_web_search: "auto",
},
});
console.log(completion.choices[0].message.content);
```
```python Python theme={"dark"}
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["VENICE_API_KEY"],
base_url="https://api.venice.ai/api/v1",
)
response = client.chat.completions.create(
model="zai-org-glm-5-1",
messages=[{"role": "user", "content": "What are the latest developments in AI?"}],
extra_body={
"venice_parameters": {
"enable_web_search": "auto",
}
},
)
print(response.choices[0].message.content)
```
```bash Model Suffix theme={"dark"}
# Alternative: Parameter direkt an die Modell-ID anhängen
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org-glm-5-1:enable_web_search=on&enable_web_citations=true",
"messages": [{"role": "user", "content": "What are the latest developments in AI?"}]
}'
```
Setzen Sie `enable_web_scraping: true`, und das Modell ruft alle URLs in der Benutzernachricht ab und liest sie, bevor es antwortet.
```bash Curl theme={"dark"}
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai-gpt-55",
"messages": [
{"role": "user", "content": "Summarize this post in five bullets: https://venice.ai/blog/how-to-use-venice-api"}
],
"venice_parameters": {
"enable_web_scraping": true
}
}'
```
```ts TypeScript theme={"dark"}
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.VENICE_API_KEY!,
baseURL: "https://api.venice.ai/api/v1",
});
const response = await client.chat.completions.create({
model: "openai-gpt-55",
messages: [
{
role: "user",
content:
"Summarize this post in five bullets: https://venice.ai/blog/how-to-use-venice-api",
},
],
// @ts-expect-error - Venice-specific parameter
venice_parameters: {
enable_web_scraping: true,
},
});
console.log(response.choices[0].message.content);
```
```python Python theme={"dark"}
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["VENICE_API_KEY"],
base_url="https://api.venice.ai/api/v1",
)
response = client.chat.completions.create(
model="openai-gpt-55",
messages=[
{
"role": "user",
"content": "Summarize this post in five bullets: https://venice.ai/blog/how-to-use-venice-api",
}
],
extra_body={
"venice_parameters": {
"enable_web_scraping": True,
}
},
)
print(response.choices[0].message.content)
```
Hängen Sie PDFs, Office-Dokumente, Code- und Textdateien (bis zu 25 MB) direkt an eine Chat-Anfrage an. Die vollständige Formatliste finden Sie im [File-Inputs-Leitfaden](/guides/features/file-inputs).
```bash Curl theme={"dark"}
# Eine lokale Datei als base64-Data-URL kodieren und dann inline senden
FILE_B64=$(base64 q3-report.pdf | tr -d '\n')
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"openai-gpt-55\",
\"messages\": [
{
\"role\": \"user\",
\"content\": [
{\"type\": \"text\", \"text\": \"Summarize this report in five bullets and list the main risks.\"},
{\"type\": \"file\", \"file\": {\"filename\": \"q3-report.pdf\", \"file_data\": \"data:application/pdf;base64,${FILE_B64}\"}}
]
}
]
}"
```
```ts TypeScript theme={"dark"}
import OpenAI from "openai";
import { readFile } from "node:fs/promises";
const client = new OpenAI({
apiKey: process.env.VENICE_API_KEY!,
baseURL: "https://api.venice.ai/api/v1",
});
const pdf = await readFile("q3-report.pdf");
const fileData = `data:application/pdf;base64,${pdf.toString("base64")}`;
const response = await client.chat.completions.create({
model: "openai-gpt-55",
messages: [
{
role: "user",
content: [
{ type: "text", text: "Summarize this report in five bullets and list the main risks." },
// @ts-expect-error - Venice file input block
{ type: "file", file: { filename: "q3-report.pdf", file_data: fileData } },
],
},
],
});
console.log(response.choices[0].message.content);
```
```python Python theme={"dark"}
import base64
import os
from pathlib import Path
from openai import OpenAI
client = OpenAI(
api_key=os.environ["VENICE_API_KEY"],
base_url="https://api.venice.ai/api/v1",
)
path = Path("q3-report.pdf")
file_data = "data:application/pdf;base64," + base64.b64encode(path.read_bytes()).decode("utf-8")
response = client.chat.completions.create(
model="openai-gpt-55",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Summarize this report in five bullets and list the main risks."},
{"type": "file", "file": {"filename": "q3-report.pdf", "file_data": file_data}},
],
}
],
)
print(response.choices[0].message.content)
```
Proxyen Sie JSON-RPC-2.0-Aufrufe über 11 unterstützte Chains mit Ihrem Venice-Schlüssel oder einer x402-Wallet. Siehe die [Crypto-RPC-Referenz](/api-reference/endpoint/crypto/rpc) für Chains, Methoden und Credit-Stufen.
```bash Curl theme={"dark"}
curl https://api.venice.ai/api/v1/crypto/rpc/ethereum-mainnet \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "eth_blockNumber",
"params": [],
"id": 1
}'
```
```ts TypeScript theme={"dark"}
const response = await fetch(
"https://api.venice.ai/api/v1/crypto/rpc/base-mainnet",
{
method: "POST",
headers: {
Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify([
{ jsonrpc: "2.0", method: "eth_chainId", params: [], id: 1 },
{ jsonrpc: "2.0", method: "eth_blockNumber", params: [], id: 2 },
]),
}
);
const results = await response.json();
console.log(results);
```
```python Python theme={"dark"}
import os
import requests
response = requests.post(
"https://api.venice.ai/api/v1/crypto/rpc/ethereum-mainnet",
headers={
"Authorization": f"Bearer {os.environ['VENICE_API_KEY']}",
"Content-Type": "application/json",
},
json={
"jsonrpc": "2.0",
"method": "eth_getBalance",
"params": ["0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045", "latest"],
"id": 1,
},
)
print(response.json())
```
Preise
Aufladen, staken oder pro Anfrage bezahlen
Laden Sie ein Konto mit Credits auf, staken Sie DIEM für ein tägliches Kontingent oder überspringen Sie das Konto ganz mit USDC auf Base.
Credits
USD oder Krypto
Pay-as-you-go in USD oder Krypto. Credits verfallen nie und funktionieren über jeden Endpoint.
Credits kaufen
DIEM
Tägliches Kontingent
Staken Sie DIEM oder VVV einmal und verdienen Sie täglich ein festes Inferenz-Kontingent, ohne Gebühren pro Aufruf.
Mehr über DIEM erfahren
x402
USDC auf Base
Pro Anfrage aus jeder Base-Wallet in USDC bezahlen. Kein Konto oder API-Schlüssel, gebaut für Agenten.
x402-Leitfaden lesen
Fragen oder Feedback? Treffen Sie uns auf [Discord](https://discord.gg/askvenice).