Apex 35B V1.0

Released
2026-10-28
Last refreshed
2026-11-18
Status
Researched today
Open sourceCommercial use: permittedRAGAgentsLong contextJSON / Tool use

Apex 35B V1.0 is a released rag, agents, and long context model with open-source and 256K context; evaluate it while provider pricing coverage matures.

Apex Intelligence releases · 1 in the last 12 monthsChangelog →
Specifications
Family
Apex
Released
2026-10-28
Context
256K
Parameters
35B (3B active)
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Apex Intelligence develops foundation models for scientific and engineering research.

Website
Pricing

No tracked provider pricing is available yet.

About

Apex 35B V1.0 is Apex Intelligence’s mixture-of-experts model for general tasks and scientific research. It is further trained from Qwen3.6-35B-A3B using proprietary data and research trajectories, with dynamic reasoning and tool use. The maker publishes BF16 weights and quantized builds under Apache 2.0. Its context window is shared by input and output.

Providers

No active provider routes are tracked for this model yet.

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.