Models
Every request is routed through the gateway, which picks a model from the free pool or the premium catalog — and falls back across candidates when one fails.
Auto (default)
With no model selected, the gateway resolves the plan's default model — every tier defaults to nvidia/nemotron-3-ultra-550b-a55b:free. The router then builds a candidate chain: requested model → openrouter/free load balancer → the rest of the free pool, skipping models whose circuit breaker is open.
Override
Use the model dropdown in the Brody AI window to pin a specific model — premium models are available on Pro and above. An empty override ("") means auto. Your chosen model and key are forwarded to the gateway so the selection is honored server-side.
Tip: if a model keeps failing, the router falls through the pool automatically — a pinned model never blocks your session.
Tool-call pinning
Native function calling requires a tool-capable model. When a request includes tools and the resolved model is a prose-only one (free load balancers, Nemotron, reasoning models), the router silently swaps to cohere/north-mini-code:free — the live-verified tool-caller — so the 76-tool agent always works, even on the free tier.
Free pool
Curated from the OpenRouter catalog — $0 at the provider. Overridable at gateway boot viaOPENROUTER_FREE_MODEL_POOL_CSV.
| Model | Note |
|---|---|
| openai/gpt-4o-mini | Cheapest paid-tier quality/price leader; leads the fallback pool. |
| meta-llama/llama-3.3-70b-instruct | Strong reasoning at low cost. |
| openrouter/free | Official OpenRouter auto free-load balancer. |
| nvidia/nemotron-3-ultra-550b-a55b:free | Default plan model for every tier (550B). |
| cohere/north-mini-code:free | Optimized for C# / Unity code generation — emits real tool calls. |
| google/gemma-4-31b-it:free | Vision + tools capable. |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Reasoning engine. |
| nvidia/nemotron-nano-12b-v2-vl:free | Vision and multimodal. |
| deepseek/deepseek-r1:free | DeepSeek R1 reasoning. |
| qwen/qwen-2.5-coder-32b-instruct:free | Coder-specialized. |
| mistralai/pixtral-12b:free | Multimodal / vision. |
| google/gemini-2.0-flash-exp:free | Gemini 2.0 Flash experimental. |
| meta-llama/llama-3.1-405b-instruct:free | Largest Llama on the free pool. |
| inclusionai/ling-3.0-flash:free | Fast flash model. |
| poolside/laguna-s-2.1:free | Code-oriented poolside model. |
Premium models
Available on paid plans — provider cost per 1M tokens is on the pricing page.
| Model | Note |
|---|---|
| anthropic/claude-3.5-sonnet | Frontier coding model, direct Anthropic fallback supported. |
| anthropic/claude-3-5-haiku | Fast, cheap Claude. |
| openai/gpt-4o | Frontier OpenAI model. |
| openai/gpt-4o-mini | Cheap and fast. |
| google/gemini-3.5-flash | Paid safety net for tool calls. |
| google/gemini-3.6-flash | Latest Gemini flash. |
| google/gemini-2.0-flash-001 | Gemini 2.0 Flash. |
| google/gemini-pro | Gemini Pro. |
| deepseek/deepseek-chat | Cheap chat model. |
| deepseek/deepseek-r1 | DeepSeek R1 reasoning (paid). |
Vision
Screenshot analysis (the analyze_screenshot tool and the /api/v1/vision/analyze endpoint) uses a dedicated vision pool, tried in order:
- google/gemma-4-31b-it:free — vision + tools, free
- cohere/north-mini-code:free — proven tool-caller
- nvidia/nemotron-nano-12b-v2-vl:free
- google/gemini-3.5-flash
- openai/gpt-4o-mini
- mistralai/pixtral-12b:free
Bring your own key (BYOK)
OpenAI
GPT models with your key.
Claude (Anthropic)
Claude 3.5 Sonnet / 3.5 Haiku with your key.
Gemini (Google)
Gemini models with your key.
DeepSeek
DeepSeek chat / R1 models.
Ollama
Local models on http://localhost:11434.
OpenRouter
One key, hundreds of models.
Groq
Fast inference provider.
Custom
Any OpenAI-compatible endpoint.
Keys are stored in editor preferences and forwarded per request, so your selected provider and model are honored end-to-end. With BYOK you pay the provider directly at their published rates.