LLM Reference

Apodex 1 Models by Apodex

ApodexApache 2.0Open source
4 models2026Up to 262k ctx

Details

ResearcherApodex
LicenseApache 2.0(OSI)
Commercial useCommercial use allowed
Models4
Released2026
Max context262k

Capabilities

Function CallingAll models
Tool UseAll models

About

Apodex's first generation of open-weight agentic models for deep research. All variants are fine-tuned from Qwen3.5 base models using three-stage post-training (SFT, agentic DPO, RL on long agentic rollouts). Designed for verification-centric reasoning with native function calling.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

4 in view

Use when the workload needs deep research, agentic, 262k context, and 36B parameters.

2026-06deep research, agentic262k context36B parameters

Use when the workload needs deep research, agentic, 262k context, and 5B parameters.

2026-06deep research, agentic262k context5B parameters

Use when the workload needs deep research, agentic, 262k context, and 2B parameters.

2026-06deep research, agentic262k context2B parameters

Use when the workload needs deep research, agentic, 262k context, and 900M parameters.

2026-06deep research, agentic262k context900M parameters

Release Timeline

1 release group
2026-06
4 current
Apodex 1.0 0.8B SFT
deep research, agentic262k context900M parameters
Current
Apodex 1.0 2B SFT
deep research, agentic262k context2B parameters
Current
Apodex 1.0 4B SFT
deep research, agentic262k context5B parameters
Current
Apodex 1.0 Mini
deep research, agentic262k context36B parameters
Current

Specifications(4 models)

Apodex 1 model specifications comparison
ModelReleasedContextParametersFn CallingTool Use
Apodex 1.0 Mini2026-06262k36BYesYes
Apodex 1.0 4B SFT2026-06262k5BYesYes
Apodex 1.0 2B SFT2026-06262k2BYesYes
Apodex 1.0 0.8B SFT2026-06262k900MYesYes

Frequently Asked Questions

What is Apodex 1 used for?
Apodex 1 is used for deep research, agentic, agent workflows and tool use, and agent workflows. The family description and listed model capabilities point to those workloads as the best fit.
How does Apodex 1 compare to Claude 3?
Apodex 1 by Apodex is strongest where you need deep research, agentic, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. Apodex 1 has 4 listed variants and reaches up to 262k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
Which Apodex 1 model should I use?
If price is the main constraint, use the pricing table first because Apodex 1 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Apodex 1.0 Mini with 262k context and tool use and function calling.