Quick Start

Go to https://www.flexinference.com/
Sign Up
You should now be in https://www.flexinference.com/dashboard
Either place your own key in place for a provider or switch it to managed here
Create a FlexInference Normal API key here
Copy and Paste any of the following

Flex Race Request (Gemini / GPT)

TypeScript

Chat Completions
Responses
Messages
generateContent

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.chat.completions.create({
  model: "gpt-5-nano",
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "00h-00m-30s",
} as any);

console.log(resp.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.responses.create({
  model: "gpt-5-nano",
  input: "Write a haiku about cheap GPUs.",
  start_within: "00h-00m-30s",
} as any);

console.log(resp.output_text);

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

const client = new Anthropic({
  baseURL: "https://api.flexinference.com",
  authToken: "flex_live_...",
});

const resp = await client.messages.create({
  model: "gemini-3.5-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "00h-00m-30s",
} as any);

console.log(resp.content[0].text);

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "flex_live_...",
  httpOptions: { baseUrl: "https://api.flexinference.com" },
});

const resp = await ai.models.generateContent({
  model: "gemini-3.5-flash",
  contents: "Write a haiku about cheap GPUs.",
  config: {
    httpOptions: { headers: { "x-start-within": "00h-00m-30s" } },
  },
});

console.log(resp.text);

Python

Chat Completions
Responses
Messages
generateContent

from openai import OpenAI
from openai.types.chat import ChatCompletion, ChatCompletionMessageParam

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

messages: list[ChatCompletionMessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: ChatCompletion = client.chat.completions.create(
    model="gpt-5-nano",
    messages=messages,
    extra_body={"start_within": "00h-00m-30s"},
)
print(resp.choices[0].message.content)

from openai import OpenAI
from openai.types.responses import Response

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

resp: Response = client.responses.create(
    model="gpt-5-nano",
    input="Write a haiku about cheap GPUs.",
    extra_body={"start_within": "00h-00m-30s"},
)
print(resp.output_text)

import anthropic
from anthropic.types import Message, MessageParam, TextBlock

client = anthropic.Anthropic(
    base_url="https://api.flexinference.com",
    auth_token="flex_live_...",
)

messages: list[MessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: Message = client.messages.create(
    model="gemini-3.5-flash",
    max_tokens=1024,
    messages=messages,
    extra_body={"start_within": "00h-00m-30s"},
)

block = resp.content[0]
if isinstance(block, TextBlock):
    print(block.text)

from google import genai
from google.genai import types

client = genai.Client(
    api_key="flex_live_...",
    http_options=types.HttpOptions(base_url="https://api.flexinference.com"),
)

resp: types.GenerateContentResponse = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Write a haiku about cheap GPUs.",
    config=types.GenerateContentConfig(
        http_options=types.HttpOptions(headers={"x-start-within": "00h-00m-30s"}),
    ),
)
print(resp.text)

Flex Race Request (Anthropic)

These need Managed Keys for Anthropic. On your own Anthropic key they return 400 flex_unsupported_for_anthropic.

TypeScript

Chat Completions
Responses
Messages
generateContent

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.chat.completions.create({
  model: "claude-opus-4-8",
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "00h-03m-00s",
} as any);

console.log(resp.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.responses.create({
  model: "claude-opus-4-8",
  input: "Write a haiku about cheap GPUs.",
  start_within: "00h-03m-00s",
} as any);

console.log(resp.output_text);

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

const client = new Anthropic({
  baseURL: "https://api.flexinference.com",
  authToken: "flex_live_...",
});

const resp = await client.messages.create({
  model: "claude-opus-4-8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "00h-03m-00s",
} as any);

console.log(resp.content[0].text);

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "flex_live_...",
  httpOptions: { baseUrl: "https://api.flexinference.com" },
});

const resp = await ai.models.generateContent({
  model: "claude-opus-4-8",
  contents: "Write a haiku about cheap GPUs.",
  config: {
    httpOptions: { headers: { "x-start-within": "00h-03m-00s" } },
  },
});

console.log(resp.text);

Python

Chat Completions
Responses
Messages
generateContent

from openai import OpenAI
from openai.types.chat import ChatCompletion, ChatCompletionMessageParam

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

messages: list[ChatCompletionMessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: ChatCompletion = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=messages,
    extra_body={"start_within": "00h-03m-00s"},
)
print(resp.choices[0].message.content)

from openai import OpenAI
from openai.types.responses import Response

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

resp: Response = client.responses.create(
    model="claude-opus-4-8",
    input="Write a haiku about cheap GPUs.",
    extra_body={"start_within": "00h-03m-00s"},
)
print(resp.output_text)

import anthropic
from anthropic.types import Message, MessageParam, TextBlock

client = anthropic.Anthropic(
    base_url="https://api.flexinference.com",
    auth_token="flex_live_...",
)

messages: list[MessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: Message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=messages,
    extra_body={"start_within": "00h-03m-00s"},
)

block = resp.content[0]
if isinstance(block, TextBlock):
    print(block.text)

from google import genai
from google.genai import types

client = genai.Client(
    api_key="flex_live_...",
    http_options=types.HttpOptions(base_url="https://api.flexinference.com"),
)

resp: types.GenerateContentResponse = client.models.generate_content(
    model="claude-opus-4-8",
    contents="Write a haiku about cheap GPUs.",
    config=types.GenerateContentConfig(
        http_options=types.HttpOptions(headers={"x-start-within": "00h-03m-00s"}),
    ),
)
print(resp.text)

Default Request

TypeScript

Chat Completions
Responses
Messages
generateContent

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.chat.completions.create({
  model: "gpt-5-nano",
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "default",
} as any);

console.log(resp.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...",
});

const resp = await client.responses.create({
  model: "gpt-5-nano",
  input: "Write a haiku about cheap GPUs.",
  start_within: "default",
} as any);

console.log(resp.output_text);

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

const client = new Anthropic({
  baseURL: "https://api.flexinference.com",
  authToken: "flex_live_...",
});

const resp = await client.messages.create({
  model: "claude-opus-4-8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a haiku about cheap GPUs." }],
  start_within: "default",
} as any);

console.log(resp.content[0].text);

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "flex_live_...",
  httpOptions: { baseUrl: "https://api.flexinference.com" },
});

const resp = await ai.models.generateContent({
  model: "gemini-3.5-flash",
  contents: "Write a haiku about cheap GPUs.",
  config: {
    httpOptions: { headers: { "x-start-within": "default" } },
  },
});

console.log(resp.text);

Python

Chat Completions
Responses
Messages
generateContent

from openai import OpenAI
from openai.types.chat import ChatCompletion, ChatCompletionMessageParam

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

messages: list[ChatCompletionMessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: ChatCompletion = client.chat.completions.create(
    model="gpt-5-nano",
    messages=messages,
    extra_body={"start_within": "default"},
)
print(resp.choices[0].message.content)

from openai import OpenAI
from openai.types.responses import Response

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",
)

resp: Response = client.responses.create(
    model="gpt-5-nano",
    input="Write a haiku about cheap GPUs.",
    extra_body={"start_within": "default"},
)
print(resp.output_text)

import anthropic
from anthropic.types import Message, MessageParam, TextBlock

client = anthropic.Anthropic(
    base_url="https://api.flexinference.com",
    auth_token="flex_live_...",
)

messages: list[MessageParam] = [
    {"role": "user", "content": "Write a haiku about cheap GPUs."}
]

resp: Message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=messages,
    extra_body={"start_within": "default"},
)

block = resp.content[0]
if isinstance(block, TextBlock):
    print(block.text)

from google import genai
from google.genai import types

client = genai.Client(
    api_key="flex_live_...",
    http_options=types.HttpOptions(base_url="https://api.flexinference.com"),
)

resp: types.GenerateContentResponse = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Write a haiku about cheap GPUs.",
    config=types.GenerateContentConfig(
        http_options=types.HttpOptions(headers={"x-start-within": "default"}),
    ),
)
print(resp.text)

Get started

Concepts

Additional Features

Using the API

Agent Keys + Integrations

Flex Race Request (Gemini / GPT)

TypeScript

Python

Flex Race Request (Anthropic)

TypeScript

Python

Default Request

TypeScript

Python

​Flex Race Request (Gemini / GPT)

​TypeScript

​Python

​Flex Race Request (Anthropic)

​TypeScript

​Python

​Default Request

​TypeScript

​Python

Flex Race Request (Gemini / GPT)

TypeScript

Python

Flex Race Request (Anthropic)

TypeScript

Python

Default Request

TypeScript

Python