Skip to main content
ValarCode supports open-weight coding models, Claude tiers, and OpenAI models. Choose the supported model for each key and tool in the dashboard.

Open-weight coding models

These are the cheaper targets you route traffic to. They are regular catalog models; the Pricing page lists their rates and how ValarCode requests are billed. ValarCode routes to open-weight coding models from makers such as Z.ai (GLM), Moonshot AI (Kimi), Meta (Muse Spark) and DeepSeek. The routing picker in the dashboard lists the models available to your key and tool.

Frontier Claude tiers

These stand in for the Opus, Sonnet, Haiku, and Fable classes your harness asks for, and they are the baseline that savings are measured against. The routing picker lists the Claude models you can select.
The frontier Claude tiers are specific to ValarCode routing. They do not appear on the public Models page and are not callable as standalone models from the Responses or Chat Completions APIs. They give you a Claude baseline to compare savings against.

OpenAI models

You can select OpenAI models in the ValarCode dashboard for Claude Code, Codex, and OpenCode when enabled for your organization. The picker shows the ones available for each key and tool. Claude and OpenAI models also bill input tokens written into the prompt cache, at 1.25x the input rate (2x for a Claude write cached with the 1-hour TTL). Other models have no cache-write charge. See Cache writes. On the OpenCode tab, choose Manual and select a model for all requests from that key and tool. On the Codex tab, choose Custom under Auto-routing and pick a model for each difficulty (the same model on every row serves every request with it). Claude Code keeps its model-by-model mapping. Each picker shows the models supported by that tool. Choose US only πŸ‡ΊπŸ‡Έ under Auto-routing to use models from US vendors for the selected key and tool.

How each harness is served

ValarCode meets each tool on its own API: Authenticate with a coding key or, when enabled for your organization, an SSO sign-in. Requests are forwarded to the resolved target model, and the response is rewritten so the model your harness sees is the one it asked for. That keeps the harness working across restarts, whatever target actually served the request. Whatever the target, Valar serves it on throughput-optimized inference tuned for agentic workloads. That highly efficient serving is what makes the open-weight models a practical everyday default rather than something you reach for only on cheap background work.

Next steps

Model routing

Point each alias at one of these models per cohort.

Analytics & savings

See the served-model mix and per-model savings.