Available Models

The Morpheus Inference Marketplace provides access to a variety of open-source AI models. Models are hosted by providers in the decentralized marketplace, and availability may vary based on provider activity.

Pricing: The Morpheus Inference API is currently FREE during the Open Beta program. Billing infrastructure will be implemented soon, with free inference available until 1/31/26.

Large Language Models (LLMs)

Flagship Models

These are the most capable models available for complex tasks.

Model	Context Window	Capabilities	Best For
`qwen3-coder-480b-a35b-instruct`	256K	Code, Function Calling	Code generation, programming
`qwen3-coder-480b-a35b-instruct:web`	256K	Code, Function Calling, Web	Code with web search
`hermes-3-llama-3.1-405b`	128K	Web Search	General purpose, instruction following
`hermes-3-llama-3.1-405b:web`	128K	Web Search	General purpose with web
`gpt-oss-120b`	128K	Function Calling	GPT-style responses
`gpt-oss-120b:web`	128K	Function Calling, Web	GPT-style with web search

Reasoning Models

Models optimized for step-by-step thinking and complex problem solving.

Model	Context Window	Capabilities	Best For
`kimi-k2-thinking`	256K	Code, Function Calling, Reasoning	Deep reasoning, math, logic, coding
`kimi-k2-thinking:web`	256K	Code, Function Calling, Reasoning, Web	Deep reasoning with web search
`glm-4.7-thinking`	198K	Function Calling, Reasoning	Extended thinking, analysis
`glm-4.7-thinking:web`	198K	Function Calling, Reasoning, Web	Extended thinking with web
`qwen3-235b`	128K	Function Calling	Complex reasoning, long documents
`qwen3-235b:web`	128K	Function Calling, Web	Complex reasoning with web

Mid-Size Models

Balanced performance and speed for most use cases.

Model	Context Window	Capabilities	Best For
`llama-3.3-70b`	128K	Function Calling	General purpose, reliable
`llama-3.3-70b:web`	128K	Function Calling, Web	General purpose with web
`qwen3-next-80b`	256K	Function Calling	Next-gen reasoning, long context
`qwen3-next-80b:web`	256K	Function Calling, Web	Next-gen with web search
`mistral-31-24b`	128K	Function Calling, Vision	Fast, efficient, image analysis
`mistral-31-24b:web`	128K	Function Calling, Vision, Web	Fast with web search
`glm-4.6`	198K	Function Calling, Reasoning	General purpose, long context
`glm-4.6:web`	198K	Function Calling, Reasoning, Web	General purpose with web
`glm-4.7`	198K	Function Calling, Reasoning	Improved GLM, largest context
`glm-4.7:web`	198K	Function Calling, Reasoning, Web	Improved GLM with web
`venice-uncensored`	32K	—	Uncensored, creative, roleplay
`venice-uncensored:web`	32K	Web	Uncensored with web search
`hermes-4-14b`	128K	—	Efficient instruction following

Fast Models

Optimized for speed and low latency.

Model	Context Window	Capabilities	Best For
`llama-3.2-3b`	128K	Function Calling	Fastest responses, simple tasks
`llama-3.2-3b:web`	128K	Function Calling, Web	Fast with web search
`qwen3-4b`	32K	Function Calling, Reasoning	Lightweight, mobile, low-latency
`qwen3-4b:web`	32K	Function Calling, Reasoning, Web	Lightweight with web

Embeddings Models

For vector embeddings and semantic search.

Model	Best For
`text-embedding-bge-m3`	Text embeddings, RAG, semantic search

Audio Models

Text-to-Speech

Model	Best For
`tts-kokoro`	Natural-sounding voice synthesis

Speech-to-Text

Model	Best For
`whisper-v3-large-turbo`	Transcription, audio processing

Model Capabilities

Function Calling

Models with function calling can invoke tools and APIs. Use the tools parameter in your chat completion request to define available functions.Supported models: Most models except venice-uncensored and hermes-3-llama-3.1-405b

Reasoning

Reasoning models support extended thinking and step-by-step problem solving. They’re optimized for complex math, logic, and analytical tasks.Supported models: kimi-k2-thinking, glm-4.7-thinking, glm-4.6, glm-4.7, qwen3-4b

Vision

Vision-capable models can analyze images passed in the messages array.Supported models: mistral-31-24b

Web Search

Models with the :web suffix can search the internet for current information.Supported models: All models have a :web variant

Code Optimization

Models specifically optimized for code generation and programming tasks.Supported models: qwen3-coder-480b-a35b-instruct, kimi-k2-thinking

Model Naming Convention

Models with the :web suffix have web search capabilities enabled, allowing them to access current information from the internet.

Suffix	Meaning
(none)	Base model without web access
`:web`	Model with web search capabilities

Using Models

Specify the model ID in your API requests:

curl
Python
JavaScript

curl https://api.mor.org/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.mor.org/api/v1"
)

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.mor.org/api/v1",
});

const response = await client.chat.completions.create({
  model: "llama-3.3-70b",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

List Active Models

Query the API to see currently available models:

curl https://api.mor.org/api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Model availability depends on active providers in the Morpheus Inference Marketplace. The API automatically routes your request to the highest-rated provider for your selected model.

Model Selection Guide

Best for coding

qwen3-coder-480b-a35b-instruct - Top choice for code generation (256K context)
kimi-k2-thinking - Best for complex algorithmic problems with reasoning
llama-3.3-70b - Good balance of speed and quality

Best for long documents

qwen3-next-80b - 256K context window
qwen3-coder-480b-a35b-instruct - 256K context window
glm-4.7 - 198K context, excellent at document analysis
kimi-k2-thinking - 256K context with reasoning

Best for speed

qwen3-4b - Fastest, 32K context
llama-3.2-3b - Very fast, 128K context
mistral-31-24b - Good speed with vision support

Best for reasoning

kimi-k2-thinking - Deep reasoning chains, 256K context
glm-4.7-thinking - Extended thinking mode, 198K context
qwen3-235b - Complex analysis, 128K context

Best for uncensored/creative

venice-uncensored - Minimal content restrictions, roleplay

Next Steps

Quickstart

Get started making your first API call.

Chat Completions

Full API reference for chat completions.

Embeddings

Create embeddings for semantic search.

Text-to-Speech

Generate speech from text.

Getting Started

Models

Guides

SDKs

AI Coding Tools

Agent Frameworks

Workflow Automation

Chat UIs

Available Models

Available Models

Large Language Models (LLMs)

Flagship Models

Reasoning Models

Mid-Size Models

Fast Models

Embeddings Models

Audio Models

Text-to-Speech

Speech-to-Text

Model Capabilities

Model Naming Convention

Using Models

List Active Models

Model Selection Guide

Next Steps

Quickstart

Chat Completions

Embeddings

Text-to-Speech

Getting Started

Models

Guides

SDKs

AI Coding Tools

Agent Frameworks

Workflow Automation

Chat UIs

​Available Models

​Large Language Models (LLMs)

​Flagship Models

​Reasoning Models

​Mid-Size Models

​Fast Models

​Embeddings Models

​Audio Models

​Text-to-Speech

​Speech-to-Text

​Model Capabilities

​Model Naming Convention

​Using Models

​List Active Models

​Model Selection Guide

​Next Steps

Quickstart

Chat Completions

Embeddings

Text-to-Speech

Available Models

Large Language Models (LLMs)

Flagship Models

Reasoning Models

Mid-Size Models

Fast Models

Embeddings Models

Audio Models

Text-to-Speech

Speech-to-Text

Model Capabilities

Model Naming Convention

Using Models

List Active Models

Model Selection Guide

Next Steps