AI Gateway Inference API

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_TOKEN_KEY"],
    base_url="https://llm.telnyx.com/v1",
    max_retries=0,
)

completion = client.chat.completions.create(
    model=os.environ["AI_GATEWAY_MODEL"],
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
    max_tokens=256,
    user="application-bound-user-id",
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_GATEWAY_TOKEN_KEY,
  baseURL: "https://llm.telnyx.com/v1",
  maxRetries: 0,
});

const completion = await client.chat.completions.create({
  model: process.env.AI_GATEWAY_MODEL,
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
  max_tokens: 256,
  user: "application-bound-user-id",
});
console.log(completion.choices[0].message.content);

curl -X POST https://llm.telnyx.com/v1/chat/completions \
  -H "Authorization: Bearer $AI_GATEWAY_TOKEN_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Kimi-K3",
    "messages": [{"role": "user", "content": "Tell me about Telnyx"}],
    "max_tokens": 256,
    "user": "application-bound-user-id"
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_TOKEN_KEY"],
    base_url="https://llm.telnyx.com/v1",
    max_retries=0,
)

with client.chat.completions.create(
    model=os.environ["AI_GATEWAY_MODEL"],
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
    max_tokens=256,
    stream=True,
) as stream:
    for chunk in stream:
        if chunk.choices:
            print(chunk.choices[0].delta.content or "", end="", flush=True)

const stream = await client.chat.completions.create({
  model: process.env.AI_GATEWAY_MODEL,
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
  max_tokens: 256,
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["AI_GATEWAY_TOKEN_KEY"],
    base_url="https://llm.telnyx.com",
    max_retries=0,
)

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=256,
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
    metadata={"user_id": "application-bound-user-id"},
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.AI_GATEWAY_TOKEN_KEY,
  baseURL: "https://llm.telnyx.com",
  maxRetries: 0,
});

const message = await client.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 256,
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
  metadata: { user_id: "application-bound-user-id" },
});
console.log(message.content[0].text);

curl -X POST https://llm.telnyx.com/v1/messages \
  -H "x-api-key: $AI_GATEWAY_TOKEN_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Tell me about Telnyx"}],
    "metadata": {"user_id": "application-bound-user-id"}
  }'

with client.messages.stream(
    model="claude-sonnet-5",
    max_tokens=256,
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

const stream = client.messages.stream({
  model: "claude-sonnet-5",
  max_tokens: 256,
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
});

for await (const event of stream) {
  if (event.type === "content_block_delta" && event.delta.type === "text_delta") {
    process.stdout.write(event.delta.text);
  }
}