Models

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

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

Hosted Qwen coder for software agents, repo edits, and long-context code

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Google's proven reasoning model for coding, math, and multimodal analysis

Fast Gemini workhorse for multimodal apps where latency and price matter

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

High-effort o3 tier for difficult technical reasoning and careful answers

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Fast o-series model for compact reasoning, coding, and tool use

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

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

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

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

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

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

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

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 efficient text generation and image understanding

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

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

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

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

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

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

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

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

Cohere's RAG workhorse for long-context enterprise search and tool use

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

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

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

Small omni GPT for cheap multimodal assistance and production-scale traffic

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

Research model for long-horizon investigation, synthesis, and analytical reports

Research model for long-horizon investigation, synthesis, and analytical reports

Omni-era GPT for multimodal chat, practical coding, and general assistants

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

Qwen instruction model for multilingual chat, reasoning, and tool use

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

Deeper Sonar search model with broader retrieval and stronger synthesis

Web-grounded Sonar for multi-step research questions that need cited reasoning

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

Compact GPT model for low-latency assistance and high-volume workloads

Compact GPT model for low-latency assistance and high-volume workloads