Model Router

Iterate quickly with seamless access to the most popular models

With Model Router, you can access the most popular models with a single endpoint and bill. Experiment with new models and scale your app without worrying about the underlying infrastructure.

Setup

Getting started with Model Router is simple. Generate an API key and drop it into your favorite framework.

Generate API key

API keys for Model Router are generated within your workspace. Generate a key by logging into the console and navigating to Model router → API keys.

Connect via framework

Model Router integrates easily into the most popular frameworks.

OpenAI SDK

Model Router is a drop-in replacement for OpenAI’s API.

Python

import openai

# Configure with your Hypermode Workspace API key and Hypermode Model Router base url
client = openai.OpenAI(
    api_key="<YOUR_HYP_WKS_KEY>",
    base_url="https://models.hypermode.host/v1",
)

# Set up the request
response = client.chat.completions.create(
    model="meta-llama/llama-4-scout-17b-16e-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Modus?"},
    ],
    max_tokens=150,
    temperature=0.7,
)

# Print the response
print(response.choices[0].message.content)

Model Router is a drop-in replacement for OpenAI’s API.

Python

import openai

# Configure with your Hypermode Workspace API key and Hypermode Model Router base url
client = openai.OpenAI(
    api_key="<YOUR_HYP_WKS_KEY>",
    base_url="https://models.hypermode.host/v1",
)

# Set up the request
response = client.chat.completions.create(
    model="meta-llama/llama-4-scout-17b-16e-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Modus?"},
    ],
    max_tokens=150,
    temperature=0.7,
)

# Print the response
print(response.choices[0].message.content)

import { createOpenAI } from "@ai-sdk/openai"
import { generateText } from "ai"

// Configure with your Hypermode Workspace API key and Hypermode Model Router base url
const hypermode = createOpenAI({
  name: "hypermode",
  apiKey: "<YOUR_HYP_WKS_KEY>",
  baseURL: "https://models.hypermode.host/v1",
})

async function generateHoliday() {
  try {
    const { text, usage, providerMetadata } = await generateText({
      model: hypermode("o3-mini"),
      prompt: "Invent a new holiday and describe its traditions.",
      providerOptions: { hypermode: { reasoningEffort: "low" } },
    })

    // Print the response
    console.log(text)
    return { text, usage, providerMetadata }
  } catch (error) {
    console.error("Error generating text:", error)
    throw error
  }
}

// Call the function
generateHoliday()

To use the Model Router in a Modus app, in your app manifest create a connection to the Model Router and add a model that references that connection.

modus.json

{
    ...
  "models": {
    "meta-llama-llama-4-scout-17b-16e-instruct": {
      "sourceModel": "meta-llama/llama-4-scout-17b-16e-instruct",
      "connection": "model-router",
      "path": "v1/chat/completions"
    },
  },
  "connections": {
    "model-router": {
      "type": "http",
      "baseUrl": "https://models.hypermode.host/",
      "headers": {
        "Authorization": "Bearer {{YOUR_HYP_WKS_KEY}}"
      }
    }
  },
  ...
}

Connect directly via API

You can also access the API directly.

Generation

curl

curl -X POST \
  https://models.hypermode.host/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_HYP_WKS_KEY" \
  -d '{
    "model": "meta-llama/llama-4-scout-17b-16e-instruct",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Dgraph?"}
    ],
    "max_tokens": 150,
    "temperature": 0.7
  }'

curl

curl -X POST \
  https://models.hypermode.host/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_HYP_WKS_KEY" \
  -d '{
    "model": "meta-llama/llama-4-scout-17b-16e-instruct",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Dgraph?"}
    ],
    "max_tokens": 150,
    "temperature": 0.7
  }'

curl

# Note: verify that your model supports the dimensions parameter
# this is the case for OpenAI 'text-embedding-3' and later models.

curl -X POST \
  https://models.hypermode.host/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_HYP_WKS_KEY" \
  -d '{
    "model": "text-embedding-3-large",
    "dimensions": 256,
    "input": [
        "Hypermode is an AI development platform that provides hosting and management capabilities for agents and knowledge graphs",
        "Modus is an open source, serverless framework for building functions and APIs, powered by WebAssembly."
    ],
    "encoding_format": "float"
  }'

Available models

Hypermode provides a variety of the most popular open source and commercial models.

We’re constantly evaluating model usage in determining new models to add to our catalog. Interested in using a model not listed here? Let us know at [e-mail].

Generation

Large language models provide text generation and reasoning capabilities.

Provider	Model	Slug
Anthropic	Claude 3.7 Sonnet (latest)	claude-3-7-sonnet-latest
Anthropic	Claude 3.7 Sonnet	claude-3-7-sonnet-20250219
Anthropic	Claude 3.5 Sonnet (latest)	claude-3-5-sonnet-latest
Anthropic	Claude 3.5 Sonnet	claude-3-5-sonnet-20241022
Anthropic	Claude 3.5 Sonnet	claude-3-5-sonnet-20240620
Anthropic	Claude 3.5 Haiku (latest)	claude-3-5-haiku-latest
Anthropic	Claude 3.5 Haiku	claude-3-5-haiku-20241022
Anthropic	Claude 3 Opus (latest)	claude-3-opus-latest
Anthropic	Claude 3 Opus	claude-3-opus-20240229
Anthropic	Claude 3 Sonnet	claude-3-sonnet-20240229
Anthropic	Claude 3 Haiku	claude-3-haiku-20240307
DeepSeek	DeepSeek-R1-Distill-Llama	deepseek-ai/deepseek-r1-distill-llama-8b
Google	Gemini 2.5 Pro	gemini-2.5-pro-exp-03-25
Google	Gemini 2.5 Pro Preview	gemini-2.5-pro-preview-05-06
Google	Gemini 2.5 Flash Preview	gemini-2.5-flash-preview-04-17
Google	Gemini 2.0 Flash Lite	gemini-2.0-flash-lite
Google	Gemini 2.0 Flash Image Generation	gemini-2.0-flash-exp-image-generation
Google	Gemini 2.0 Flash Live	gemini-2.0-flash-live-001
Google	Gemini 2.0 Flash (latest)	gemini-2.0-flash
Google	Gemini 2.0 Flash	gemini-2.0-flash-001
Google	Gemini 1.5 Pro (latest)	gemini-1.5-pro-latest
Google	Gemini 1.5 Pro	gemini-1.5-pro
Google	Gemini 1.5 Pro	gemini-1.5-pro-002
Google	Gemini 1.5 Pro	gemini-1.5-pro-001
Google	Gemini 1.5 Flash (latest)	gemini-1.5-flash-latest
Google	Gemini 1.5 Flash	gemini-1.5-flash
Google	Gemini 1.5 Flash	gemini-1.5-flash-002
Google	Gemini 1.5 Flash	gemini-1.5-flash-001
Google	Gemini 1.5 Flash 8B (latest)	gemini-1.5-flash-8b-latest
Google	Gemini 1.5 Flash 8B	gemini-1.5-flash-8b
Google	Gemini 1.5 Flash 8B	gemini-1.5-flash-8b-exp-0924
Google	Gemini 1.5 Flash 8B	gemini-1.5-flash-8b-exp-0827
Google	Gemini 1.5 Flash 8B	gemini-1.5-flash-8b-001
Meta	Llama 4 Scout	meta-llama/llama-4-scout-17b-16e-instruct
Meta	Llama 3.2	meta-llama/llama-3.2-3b-instruct
OpenAI	O3 (latest)	o3
OpenAI	O3	o3-2025-04-16
OpenAI	O4 Mini (latest)	o4-mini
OpenAI	O4 Mini	o4-mini-2025-04-16
OpenAI	GPT 4.5 Preview (latest)	gpt-4.5-preview
OpenAI	GPT 4.5 Preview	gpt-4.5-preview-2025-02-27
OpenAI	O3 Mini (latest)	o3-mini
OpenAI	O3 Mini	o3-mini-2025-01-31
OpenAI	O1 (latest)	o1
OpenAI	O1	o1-2024-12-17
OpenAI	O1 Preview (latest)	o1-preview
OpenAI	O1 Preview	o1-preview-2024-09-12
OpenAI	O1 Mini (latest)	o1-mini
OpenAI	O1 Mini	o1-mini-2024-09-12
OpenAI	GPT 4.1 (latest)	gpt-4.1
OpenAI	GPT 4.1	gpt-4.1-2025-04-14
OpenAI	GPT 4.1 Mini (latest)	gpt-4.1-mini
OpenAI	GPT 4.1 Mini	gpt-4.1-mini-2025-04-14
OpenAI	GPT 4.1 Nano (latest)	gpt-4.1-nano
OpenAI	GPT 4.1 Nano	gpt-4.1-nano-2025-04-14
OpenAI	GPT-4o Mini Search Preview (latest)	gpt-4o-mini-search-preview
OpenAI	GPT-4o Mini Search Preview	gpt-4o-mini-search-preview-2025-03-11
OpenAI	GPT 4o (latest)	gpt-4o
OpenAI	GPT 4o	gpt-4o-2024-11-20
OpenAI	GPT 4o	gpt-4o-2024-08-06
OpenAI	GPT 4o	gpt-4o-2024-05-13
OpenAI	GPT 4o Mini (latest)	gpt-4o-mini
OpenAI	GPT 4o Mini	gpt-4o-mini-2024-07-18
OpenAI	GPT 4o Audio Preview (latest)	gpt-4o-audio-preview
OpenAI	GPT 4o Audio Preview	gpt-4o-audio-preview-2024-12-17
OpenAI	GPT 4o Audio Preview	gpt-4o-audio-preview-2024-10-01
OpenAI	GPT 4o Search Preview (latest)	gpt-4o-search-preview
OpenAI	GPT 4o Search Preview	gpt-4o-search-preview-2025-03-11
OpenAI	GPT 4o Search Preview	gpt-4o-search-preview-2025-03-11
OpenAI	ChatGPT 4o	chatgpt-4o-latest
OpenAI	GPT 4 (latest)	gpt-4
OpenAI	GPT 4	gpt-4-0613
OpenAI	GPT 4 Turbo	gpt-4-turbo-2024-04-09
OpenAI	GPT 4 Turbo Preview	gpt-4-turbo-preview
OpenAI	GPT 4 Preview (latest)	gpt-4-1106-preview
OpenAI	GPT 4 Preview	gpt-4-0125-preview
OpenAI	GPT 3.5 Turbo (latest)	gpt-3.5-turbo
OpenAI	GPT 3.5 Turbo	gpt-3.5-turbo-1106
OpenAI	GPT 3.5 Turbo	gpt-3.5-turbo-0125
Mistral	Mistral Large (coming soon)	mistral-large-latest
Mistral	Pixtral Large (coming soon)	pixtral-large-latest
Mistral	Mistral Medium (coming soon)	mistral-medium-latest
Mistral	Mistral Moderation (coming soon)	mistral-moderation-latest
Mistral	Ministral 3B (coming soon)	ministral-3b-latest
Mistral	Ministral 8B (coming soon)	ministral-8b-latest
Mistral	Open Mistral Nemo (coming soon)	open-mistral-nemo
Mistral	Mistral Small (coming soon)	mistral-small-latest
Mistral	Mistral Saba (coming soon)	mistral-saba-latest
Mistral	Codestral (coming soon)	codestral-latest
xAI	Grok 3 Beta (coming soon)	grok-3-beta
xAI	Grok 3 Fast Beta (coming soon)	grok-3-fast-beta
xAI	Grok 3 Mini Beta (coming soon)	grok-3-mini-beta
xAI	Grok 3 Mini Fast Beta (coming soon)	grok-3-mini-fast-beta

Embedding

Embedding models provide vector representations of text for similarity matching and other applications.

Provider	Model	Slug
Nomic AI	Embed Text V1.5	nomic-ai/nomic-embed-text-v1.5
OpenAI	Embedding 3 Large	text-embedding-3-large
OpenAI	Embedding 3 Small	text-embedding-3-small
OpenAI	ADA Embedding	text-embedding-ada-002
Hugging Face	MiniLM-L6-v2 (coming soon)	sentence-transformers/all-MiniLM-L6-v2

Logging

By default, all model invocations are logged for future display in the console. If you’d like to opt out of model logging, please contact us.