Skip to content

Model catalog

Frontier-class open models, priced at list, routed for cost.

Every model speaks the OpenAI API and is billed per token at the rate below. Prefer stratacode/auto unless you have a reason to pin a specific model — it routes each request to the cheapest model that can handle it and bills you at that model’s rate.

Catalog

ModelInput / 1MOutput / 1MCached / 1MContextTools
stratacode/autoroutedroutedrouted
stratacode/glm-5.2$1.40$4.40$0.26200K
stratacode/glm-4.5-air$0.20$1.10$0.03128K
stratacode/deepseek-v4-flash$0.14$0.28$0.0031M
stratacode/qwen3.5-plus$0.40$2.40256K
stratacode/free$0$0128K

This is the static launch catalog. Once the gateway exposes its /v1/models endpoint, this page reads live prices and lane health from it directly.

Sourcing & availability

GLM models are served through US-based inference hosts (DeepInfra primary, with failover) rather than a single origin — this is the standard, compliance-aware way to serve GLM and keeps a lane up if any one host degrades. Each host must pass our quality bench before it enters rotation, so a cheaper host never means quietly worse output.

We do not list models whose supply or compliance status is unsettled. Kimi is not in the catalog. See trust & sourcing for the full policy.

Get started Set up your tool