Models

Long-lived GPT workhorse for coding, instruction following, and production apps

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Affordable GPT-4.1 lane for fast coding help and structured extraction

Mistral vision-language model for image understanding and multimodal chat

Flagship Nemotron model for high-throughput reasoning and complex agents

Nemotron model for efficient reasoning, coding, and specialized AI agents

Open Llama with long-context vision for efficient multimodal agents

Open multimodal Llama for strong reasoning with efficient everyday serving

Dense open Qwen model for self-hosted chat, reasoning, and coding

Large open Qwen MoE for multilingual reasoning, coding, and tool use

Smaller Qwen coder for efficient local agents and repo-level fixes

Open Qwen coding heavyweight for repository reasoning and agentic engineering

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

O-series reasoning model for hard analysis, math, coding, and planning

Mistral reasoning model for transparent analysis, math, and complex decisions

Efficient multimodal model for instruction following, coding, reasoning, and function calling

Cohere command model for multilingual enterprise agents, tools, and chat

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Open multimodal Gemma instruction model for efficient text generation and image understanding

Qwen reasoning model for deliberate problem solving, math, and coding

Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving

Compact open multilingual vision model for OCR and visual question answering

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

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

Balanced Claude model for coding, analysis, agent workflows, and cost control

MiniMax text-to-image generation model with reference-image support

Sonar search model for autonomous research and citation-backed long-form reports

ALLaM-2-7b instruction tuned model by SDAIA

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

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Qwen omni model for text, vision, audio, and multimodal agent tasks

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

Smaller o-series reasoner for economical coding, math, and planning tasks

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

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

Low-latency Gemini model for high-volume multimodal and agent workloads

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

O-series reasoning model for hard analysis, math, coding, and planning

Efficient model for low-latency assistance, extraction, and routine automation

Efficient model for low-latency assistance, extraction, and routine automation

Flagship model for demanding analysis, coding, and production agent workflows

Cohere retrieval model for long-context chat and enterprise RAG workflows

GPT model for general reasoning, writing, coding, and tool-assisted tasks

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

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

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

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

Efficient Qwen model for fast chat, extraction, and high-volume workloads

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