Models

Open multilingual vision model for OCR, visual reasoning, and image question answering

Compact open multilingual vision model for OCR and visual question answering

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

Open DeepSeek MoE chat model for coding, math, and general reasoning

Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Open coding-focused Qwen model for code generation, repair, and repository reasoning

Tiny open Qwen code model for lightweight completion and on-device coding

Mistral's larger vision model for document-heavy image understanding and chat

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Open multilingual model optimized for generation across 23 languages

Efficient open Mistral edge model for on-device chat and function calling

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Open multimodal Llama model for image understanding, captioning, and visual QA

Small open Llama base model for lightweight text generation and self-hosting

Compact open Llama base model for lightweight and on-device use

Mistral vision-language model for image understanding and multimodal chat

Qwen vision-language model for visual reasoning, documents, and agent tasks

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

Compact Nemotron model for efficient reasoning and deployable AI agents

Llama 3.1-based safety classifier for moderating prompts and model responses

Open Llama instruction model for multilingual chat, reasoning, and coding

Compact open Llama model for lightweight chat, drafting, and self-hosting

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Open Mistral code model for fill-in-the-middle and 80+ programming languages

Mistral code model for completions, refactors, and developer IDE workflows

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...