Try for free
DocsModels and pins

Models and pins

Every agent runs DeepSeek V4.1 Flash today, at medium reasoning. Each pin moves only when the benchmark finds a better buy.

Today’s pins

Each agent's model
AgentModelRetry modelCost per review
Code Reviewdeepseek/deepseek-v4.1-flashmedium reasoningmeta/muse-spark-1.3medium reasoning$0.102
Security Reviewdeepseek/deepseek-v4.1-flashmedium reasoningz-ai/glm-5.3-flashlow reasoning$0.063
AI Architecturedeepseek/deepseek-v4.1-flashmedium reasoningz-ai/glm-5.3medium reasoning$0.050
Log & Errorsdeepseek/deepseek-v4.1-flashmedium reasoninggoogle/gemini-3.8-flashmedium reasoning$0.039
Docs Reviewdeepseek/deepseek-v4.1-flashmedium reasoninggoogle/gemini-3.8-flashmedium reasoningNot measured yet
API Performancedeepseek/deepseek-v4.1-flashmedium reasoningmeta/muse-spark-1.3medium reasoning$0.043
SOC 2 Reviewdeepseek/deepseek-v4.1-flashmedium reasoningz-ai/glm-5.3-flashlow reasoning$0.038
CI/CD Performancedeepseek/deepseek-v4.1-flashmedium reasoningdeepseek/deepseek-v4-pro-0813medium reasoning$0.0095

Model ids are OpenRouter’s. When a lane’s first attempt fails, the second can run on its retry model. Cost per review is what the pin averaged on IonWarpBench.

Around the agents

Models around the agents
JobModel
The planner, which writes the walkthrough and the repository facts every agent readsopenai/gpt-6-luna-prolow reasoning
The checker, which re-reads every findingdeepseek/deepseek-v4.1-flashmedium reasoning
Ask IonWarp, the chat in the appdeepseek/deepseek-v4.1-flashmedium reasoning

How a pin is chosen

IonWarpBench runs each agent’s tasks on candidate models: positive cases with a known defect and negative cases with none. A judge grades every finding, and the bench records what each run cost and how long it took. A model becomes an agent’s pin when it costs least per task while staying above the quality bar.

The results are public: the benchmark, and how we measure.

A different model for your workspace

A workspace or a single project can run another model on any agent, such as a larger one for Code Review. A project’s choice wins over the workspace’s, and the workspace’s over IonWarp’s pin. The model’s cost comes out of your monthly budget.

To set one, write to team@ionwarp.com or use the link on the agent’s page in the app.

ionwarp.review.model_pins
{
  "code-review": { "model": "meta/muse-spark-1.3", "reasoning_effort": "medium" }
}

Keys are the agents’ reviewer ids: code-review, security-review, ai-architecture, log-coverage, docs-freshness, performance-review, soc2-review, cicd-performance.

Where models run

Every call goes through OpenRouter, only to providers that don’t keep or train on what they receive. Security has the details.