Models

Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks

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

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Small GPT-5 for responsive agents, coding help, and everyday automation

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

Open GPT reasoning model for self-hosted agents and controllable deployments

Open GPT reasoning model for self-hosted agents and controllable deployments

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

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

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

Cohere vision model for multilingual document analysis, OCR, and image understanding

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

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

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

Qwen coding model for software agents, repository edits, and code reasoning

Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use

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

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

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

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

AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation

Open ERNIE text MoE with 300B total and 47B active parameters

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

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

Efficient Mistral model for fast chat, extraction, and production assistants

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Fast Gemini workhorse for multimodal apps where latency and price matter

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

Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget

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

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

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

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

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

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

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

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

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

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

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

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

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

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

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