All Azure Models
GPT-4o (Azure)
Enterprise-grade OpenAI models deployed via Azure AI Foundry with global scale.
GPT-4 Turbo (Azure)
Fast and scalable GPT-4 model running on Azure AI Foundry.
GPT-4o Mini (Azure)
Compact, cost-effective multimodal GPT-4o variant on Azure AI Foundry.
o1 (Azure)
O-series reasoning model on Azure for hard analysis, math, coding, and planning.
o3-mini (Azure)
Fast O-series reasoning model on Azure for coding and planning.
o4-mini (Azure)
Fast o-series model for compact reasoning, coding, and tool use.
GPT-5 (Azure)
GPT-5 model for general reasoning, writing, coding, and tool-assisted tasks via Azure Foundry.
GPT-5 Pro (Azure)
Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning via Azure Foundry.
GPT-5 Mini (Azure)
Compact GPT-5 model for low-latency assistance and high-volume workloads.
GPT-5.1 (Azure)
Speech generation model for controllable voice, narration, and audio delivery via Azure Foundry.
GPT-5.1 Codex (Azure)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5.1 Codex Max (Azure)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5.1 Codex Mini (Azure)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5.2 (Azure)
GPT model for general reasoning, writing, coding, and tool-assisted tasks.
GPT-5.2 Codex (Azure)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5.3 Codex (Azure)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5.4 (Azure)
Agent-ready GPT for coding and computer-use workflows at a lower cost.
GPT-5.4 Mini (Azure)
Strong small GPT for coding subagents, quick tool use, and high-volume work.
GPT-5.4 Nano (Azure)
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation.
GPT-5.5 (Azure)
Default frontier GPT for coding, computer use, research, and knowledge work via Azure Foundry.
GPT-5.6 Luna (Azure)
Cost-efficient GPT-5.6 model for fast, high-volume workloads via Azure Foundry.
GPT-5.6 Sol (Azure)
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows.
GPT-5.6 Terra (Azure)
Balanced GPT-5.6 model for capable, cost-efficient everyday work.
Claude Opus 5 (Azure)
Strongest Claude Opus model for coding, agents, and professional work via Azure Foundry.
Claude Sonnet 5 (Azure)
Everyday Claude agent model for coding, planning, browsing, and general work.
Claude Mythos 5 (Azure)
Restricted Claude model for advanced cybersecurity and biology research workflows.
Kimi K2.6 (Azure)
Kimi multimodal agent model for visual understanding, coding, and planning.
Kimi K2.7 Code (Azure)
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking.
Devstral 2 (Azure)
Mistral coding agent model for repository tasks and software engineering workflows.
DeepSeek-V4-Pro (Azure)
Open MoE flagship with million-token context for coding and long agent runs.
DeepSeek-V4-Flash (Azure)
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work.
Phi-4 (Azure)
Open-weight instruction model for adaptable chat and self-hosted production workloads.
Phi-4-mini (Azure)
Efficient model for low-latency assistance, extraction, and routine automation.
Phi-4-reasoning (Azure)
Reasoning model for deliberate analysis, multi-step problem solving, and tool use.
Phi-4 Reasoning Plus
Reasoning model for deliberate analysis, multi-step problem solving, and tool use via Azure AI Foundry.
Phi-4-multimodal (Azure)
Multimodal model for analyzing text, images, documents, and rich media.
DeepSeek V3.2 Speciale
DeepSeek chat model optimized for instruction following, coding, and analysis via Azure AI Foundry.
Gemma 4 26B A4B IT (Azure CF)
Open Gemma instruction model for efficient chat and self-hosted deployments via Cloudflare Workers AI.
Deepseek R1 Distill Qwen 32B (Azure CF)
R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving.
Claude Fable 5 (Azure Gateway)
Claude model for creative writing, analysis, and controlled agent workflows via AI Gateway.
GPT-5.6 (Azure Gateway)
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows.
Llama 4 Scout 17B 16E (Azure Gateway)
Open Llama with long-context vision for efficient multimodal agents.
Glm 5.2 (Azure Gateway)
Open flagship GLM for long-horizon coding agents and million-token context work.
GPT-5.3 Codex Spark (Azure Gateway)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
Nemotron 3 Super 120B (Azure Gateway)
Nemotron middle tier for collaborative agents and high-volume reasoning workloads.
o4-mini (Azure Gateway)
Fast o-series model for compact reasoning, coding, and tool use.
Claude Opus 5 (Azure Gateway)
Strongest Claude Opus model for coding, agents, and professional work.
DeepSeek V4 Pro 0813 (Workers AI)
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes.
DeepSeek V4 Flash 0731 (Workers AI)
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding.
Llama 4 Scout 17B (Workers AI)
Open Llama with long-context vision for efficient multimodal agents.
Llama 3.3 70B FP8 (Workers AI)
Popular open Llama workhorse for multilingual chat, coding, and self-hosting.
Kimi K2.7 Code (Workers AI)
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking.
GPT OSS 120B (Workers AI)
Open GPT reasoning model for self-hosted agents and controllable deployments.
Qwen3 30B FP8 (Workers AI)
Qwen instruction model for multilingual chat, reasoning, and tool use.
GLM 5.2 (Workers AI)
Open flagship GLM for long-horizon coding agents and million-token context work.
Nemotron 3 Super 120B (Workers AI)
Nemotron middle tier for collaborative agents and high-volume reasoning workloads.
Gemma 4 26B Instruct (Workers AI)
Open Gemma instruction model for efficient chat and self-hosted deployments.
Grok 4.20 (Reasoning) (Azure)
Grok model for agentic tool use, reasoning, coding, and live assistance.
Grok 4.20 (Non-Reasoning) (Azure)
Grok model for agentic tool use, coding, and live assistance (faster, no reasoning).
GPT-4.1 Nano (Azure)
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks.
Claude Haiku 4.5 (Azure)
Fast Claude model for responsive assistance, classification, and lightweight agents.
Claude Sonnet 4.6 (Azure)
Claude workhorse for coding agents, careful analysis, and production cost control.
Claude Opus 4.8 (Azure)
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents.
Mistral Small 3.1 (Azure)
Efficient Mistral model for fast chat, extraction, and production assistants.
Llama 4 Scout 17B (Azure)
Open multimodal Llama model for long-context analysis and efficient agents.
Kimi K2.5 (Azure)
Kimi multimodal agent model for visual understanding, coding, and planning.
GPT-Image-2 (Azure)
Image model for prompt-driven generation, editing, and visual design workflows.
GPT-4.1 (ACS)
Long-lived GPT workhorse for coding, instruction following, and production apps.
GPT-4.1 mini (ACS)
Affordable GPT-4.1 lane for fast coding help and structured extraction.
GPT-5 Codex (ACS)
Coding-optimized GPT model for repository edits, reviews, and agentic software work.
GPT-5 Nano (ACS)
Compact GPT model for low-latency assistance and high-volume workloads.
GPT-5.4 Pro (ACS)
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks.
o3 (ACS)
Deliberate o-series reasoner for hard math, coding, and multi-step analysis.
Phi-4-mini-reasoning (ACS)
Efficient Microsoft model for low-latency assistance, extraction, and routine automation.
Mistral Medium 3 (ACS)
Mistral model for multilingual chat, reasoning, and tool-assisted workflows.
Codestral 25.01 (ACS)
Mistral coding model for code completion, generation, and developer workflows.
Llama 4 Maverick 17B FP8 (ACS)
Open multimodal Llama model for strong reasoning and fast responses.
MAI Code 1.1 Flash
Microsoft AI coding model with native vision support, optimized for fast and efficient software development.
MAI Code 1 Flash Picker
Microsoft AI routing model for Copilot that automatically balances speed and reasoning.
GPT-5.5 (Copilot)
Default frontier GPT for coding, computer use, research, and knowledge work via GitHub Copilot.
GPT-5.6 Luna (Copilot)
Cost-efficient GPT-5.6 model for fast, high-volume workloads via GitHub Copilot.
GPT-5.6 Sol (Copilot)
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows.
Claude Opus 5 (Copilot)
Strongest Claude Opus model for coding, agents, and professional work via GitHub Copilot.
Claude Sonnet 5 (Copilot)
Everyday Claude agent model for coding, planning, browsing, and general work.
Gemini 3.7 Flash (Copilot)
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning.
Kimi K3 (Copilot)
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work.
Grok 4.6 (Copilot)
xAI frontier model for long-running agents, coding, knowledge work, and visual projects.
Gemini 3.1 Pro Preview (Vertex)
Reasoning-first Gemini preview for agentic coding and complex problem solving.
Gemini 3.5 Flash (Vertex)
Fast Gemini model balancing multimodal reasoning, tool use, and cost.
Gemini 3.7 Flash (Vertex)
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning.
Claude Opus 5 (Vertex)
Strongest Claude Opus model for coding, agents, and professional work.
Claude Sonnet 5 (Vertex)
Everyday Claude agent model for coding, planning, browsing, and general work.
DeepSeek V3.2 (Vertex MaaS)
DeepSeek chat model for instruction following, coding, and analysis.
Llama 4 Maverick 17B (Vertex MaaS)
Open multimodal Llama model for strong reasoning and fast responses.
Kimi K2 Thinking (Vertex MaaS)
Kimi reasoning model for long-horizon research, planning, and tool use.
GPT OSS 120B (Vertex MaaS)
Open-weight GPT model for self-hosted reasoning and instruction-following workloads.
GLM-5 (Vertex MaaS)
Flagship GLM model for hybrid reasoning, coding, and agentic engineering.
Nova 2 Lite (Bedrock)
Multimodal reasoning model for visual analysis, planning, and tool use on AWS Bedrock.
Nova Pro (Bedrock)
Flagship model for demanding analysis, coding, and production agent workflows on AWS Bedrock.
Claude Opus 5 (Bedrock)
Strongest Claude Opus model for coding, agents, and professional work on AWS Bedrock.
Claude Sonnet 5 (Bedrock)
Everyday Claude agent model for coding, planning, browsing, and general work on AWS Bedrock.
Claude Fable 5 (Bedrock)
Claude model for creative writing, analysis, and controlled agent workflows on AWS Bedrock.
DeepSeek-R1 (Bedrock)
DeepSeek reasoning model for multi-step analysis, math, coding, and tools on AWS Bedrock.
DeepSeek-V3.1 (Bedrock)
DeepSeek chat model for instruction following, coding, and analysis on AWS Bedrock.
Gemma 3 27B Instruct (Bedrock)
Open Gemma instruction model for efficient chat and self-hosted deployments on AWS Bedrock.
Llama 4 Maverick 17B (Bedrock)
Open multimodal Llama model for strong reasoning and fast responses on AWS Bedrock.
Llama 4 Scout 17B (Bedrock)
Open multimodal Llama model for long-context analysis and efficient agents on AWS Bedrock.
