ASSISTANTS

BLOCKS

BUNDLES

Models

Models are blocks that let you specify Large Language Models (LLMs) and other deep learning models to be used in different affordances like Chat, Autocomplete, Edit, @Codebase, and @Docs

Learn more

Explore Models

The following models are curated by the Continue team and are ready to be added as building blocks to your custom AI code assistants

Claude 4 Sonnet

Anthropic's latest high-performance model

OpenAI GPT-4.1

Llama 4 Maverick Instruct (17Bx128E)

Gemini 2.5 Pro Beta

Claude 4 Opus

Anthropic's most intelligent model

Codestral

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Morph Fast Apply v2

Fast AI Code Edits. Accurate + Reliable

Grok 2

xAI's previous frontier language model with state-of-the-art reasoning capabilities

Claude 3.7 Sonnet

Anthropic's previous most intelligent model with toggleable extended thinking

voyage-code-3

Voyage's next-generation embedding model optimized for code retrieval

OpenAI GPT-4o

OpenAI's versatile, high-intelligence flagship model

Relace Instant Apply

Instantly merge code snippets from an LLM into your existing codebase

Llama 4 Scout Instruct (17Bx16E)

Gemini 2.0 Flash

Gemini's newest multimodal model, with next generation features and improved capabilities

Voyage AI rerank-2

Voyage's generalist reranker optimized for quality with multilingual support

Claude 3.5 Haiku

Claude 3.5 Haiku efficiently processes and categorizes information, making it effective for rapid data extraction and automated labeling tasks.

Mercury Coder Small

o3-mini

OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini

voyage-code-2

Voyage's previous generation of code embeddings

qwen2.5-coder 1.5b

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Morph Rerank v2

OpenAI GPT-4o Mini

OpenAI's fast, affordable small model for focused tasks

o1

OpenAI's reasoning model designed to solve hard problems across domains

Mistral Embed

State-of-the-art semantic for extracting representation of text extracts

nomic-embed-text latest

A high-performing open embedding model with a large token context window

deepseek-r1 8b

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

hermes-2-pro-llama-3-8b

Hermes-2-Pro-Llama-3-8B fine-tunes Llama-3-8B with the enhanced OpenHermes 2.5 dataset. This 8B model specializes in function calling and structured JSON outputs while maintaining strong general capabilities.

qwen2.5-coder-32b-instruct

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Mistral Large

Top-tier reasoning model for high-complexity tasks with the lastest version released November 2024.

Morph Embedding v2

Best in class embeddings built for code

Qwen 2.5 Coder 32b

qwen2.5-coder 1.5b

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

deepseek-r1 8b

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

DeepSeek R1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

midnight-rose-70b

Midnight-Rose-70B merges multiple models for advanced creative writing and storytelling. This 70B parameter model builds on Rogue Rose and Aurora Nights, optimizing for detailed narrative generation and character interactions.

deepseek-r1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

CodeGate Anthropic

OpenAI text-embedding-3-large

OpenAI's larger embedding model that creates embeddings with up to 3072 dimensions