Models and Providers

Glue ships with a curated catalog. Selected models are always written as provider/model — for example anthropic/claude-sonnet-4-6. Credentials never live in project config; they come from env vars, ~/.glue/credentials.json, or an OS keychain layer later.

Canonical source: docs/reference/models.yaml.

shipping

Recommended coding models

Anthropic, OpenAI, Gemini, Mistral, Groq, and other hosted providers.

Model	Provider	Capabilities	Notes
anthropic/claude-sonnet-4-6★	anthropic	💬🔧👁📎{}🧠⌨	Default high-quality coding model.
anthropic/claude-opus-4-6★	anthropic	💬🔧👁📎{}🧠⌨	Use for difficult architecture, debugging, and long investigations.
anthropic/claude-haiku-4-5★	anthropic	💬🔧👁{}⌨	Good small_model candidate for titles, summaries, and quick checks.
anthropic/claude-opus-4-7★	anthropic	💬🔧👁📎{}🧠⌨	Most capable Claude model — agentic coding and long-horizon work.
openai/gpt-5.4★	openai	💬🔧👁📎{}🧠⌨	Frontier general-purpose and agentic coding model.
openai/gpt-5.4-mini★	openai	💬🔧👁{}⌨	Default small_model candidate.
gemini/gemini-pro-latest★	gemini	💬🔧👁📎{}🧠⌨	Stable alias for the current Pro-class Gemini model.
gemini/gemini-flash-latest★	gemini	💬🔧👁📎{}⌨	Fast model for summarization, extraction, and browser-heavy work.
mistral/devstral-latest★	mistral	💬🔧{}⌨	Mistral's agentic coding model. Strong tool use.
mistral/mistral-large-latest★	mistral	💬🔧👁{}⌨	Flagship multimodal general-purpose model.
mistral/mistral-medium-latest★	mistral	💬🔧👁{}	Balanced cost/quality option.
mistral/mistral-small-latest★	mistral	💬🔧👁{}🧠	Fast with reasoning toggle; good for quick tasks.
groq/gpt-oss-120b★	groq	💬🔧{}🧠⌨	Groq's flagship reasoning + coding model. 120B weights at Groq speed.
groq/gpt-oss-20b★	groq	💬🔧{}⌨	Coding-optimized, faster/cheaper than 120B.
groq/llama-3.3-70b-versatile★	groq	💬🔧{}	General-purpose alternative. No reasoning mode.
copilot/claude-sonnet-4-6★	copilot	💬🔧👁{}⌨	Uses your GitHub Copilot subscription.
copilot/gpt-4.1★	copilot	💬🔧{}⌨	Uses your GitHub Copilot subscription.
openrouter/claude-sonnet-4-6★	openrouter	💬🔧👁📎{}🧠⌨	Useful when users want one router key.
openrouter/gpt-5.4-mini★	openrouter	💬🔧👁{}⌨	Small-model fallback through a router.
openrouter/gemini-flash-latest★	openrouter	💬🔧👁📎{}🌐	Good for research and extraction workflows.

Local models

Ollama runs on localhost; capability depends on hardware.

Model	Provider	Capabilities	Notes
ollama/qwen3-coder:30b★	ollama	💬🔧{}⌨🖥	Consensus local coding agent. 30B/3.3B MoE. ~20 GB VRAM at Q4_K_M.
ollama/qwen3.6:35b★	ollama	💬🔧👁{}🧠⌨🖥	Latest Qwen generalist with agentic coding upgrades. Vision + thinking + tools. ~24 GB at Q4_K_M.
ollama/gemma4:26b★	ollama	💬🔧👁{}⌨🖥	Google's latest with native function-calling. Multimodal, 256K context. ~18 GB at Q4_K_M.
ollama/devstral-small-2:24b★	ollama	💬🔧{}⌨🖥	Mistral's agentic coding model (Dec 2025). 68% SWE-bench. ~14 GB at Q4_K_M.
ollama/qwen2.5-coder:32b★	ollama	💬🔧{}⌨🖥	Aider-verified 73.7% (GPT-4o class). Safe fallback.
ollama/qwen3:8b★	ollama	💬🔧{}🖥	Low-end floor for tool use. ~5 GB at Q4_K_M. Fits a 16 GB laptop.

OpenAI-compatible endpoints

Any endpoint that speaks the OpenAI wire format can be added with adapter: openai. That includes Groq, Ollama, vLLM, LM Studio, and OpenRouter — each listed separately in the catalog because their base URLs and auth differ, not because the wire format does.

~/.glue/models.yaml — OpenAI-compatible provider

providers:
  local-vllm:
    adapter: openai
    base_url: http://localhost:8000/v1
    auth:
      api_key: none

Minimal config

~/.glue/config.yaml — quickest path to a running agent

active_model: anthropic/claude-sonnet-4-6

Credentials come from the environment in this example (ANTHROPIC_API_KEY). To override any catalog entry or add a provider of your own, drop a models.yaml into ~/.glue/ — it merges on top of the bundled catalog.

Configuration reference →