AI Agent StoreCallstack · Specialized hosted model
Callstack Apex
A model trained for React Native and React engineering, with Next.js use described by the provider. The native pinned version is October 1; Gateway availability is a separate October 8 offer. Comparable independent coding results are pending.
Released 2026-10-01 · First reviewed 2026-10-09 · Checked 2026-10-15.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact pinned native model ID: apex-20261001. The native contract lists text input and a 262,144-token context. Use apex-20261001 for a stable snapshot; apex is a moving alias. Gateway separately lists callstack/apex with text/image input, tools and 131,072 maximum output; those are hosted-route declarations, not verified native capabilities.
Thinking settings listed by AI Gateway: none, low, medium, xhigh. These controls apply to this AI Gateway service. We have not confirmed how they match the model maker’s settings, which is the default, or how they perform in comparable independent tests. Verify the exact Gateway catalog entry ↗
The provider identifies a licensed Qwen base without publishing an exact base checkpoint. Weights are not publicly distributed. Hosted and commercial self-hosting access are separate choices; no Qwen benchmark is transferred.
The native maximum output and effort default remain unverified. Native text-only documentation differs from Gateway’s image-input declaration; test the route you will use before relying on screenshots.
The Gateway catalog quotes $0.50 input, $0.20 cache reads and $3 output per million, checked October 10. The linked native pricing page returns 404; these are not verified direct-provider list prices. Your bill can also include tools, retries and charged thinking tokens. Check the offer used by your application.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗