Maple

LEARN / MODELS

Choose the model. Understand the tradeoffs.

Compare capabilities, privacy, and access across the models available through Maple.

Explore models How Maple protects your work

Catalog reviewed

MODEL CATALOG

Explore by family

These names and IDs come from Maple’s public model catalog. Published guides explain each version in depth.

Compare model pricing

GLM

Compare the flagship and Flash releases separately. Their capabilities and deployment requirements differ; benchmark results for one do not describe the other.

  • GLM 5.3glm-5-3
  • GLM-5.3 Flashglm-5-3-flash
  • GLM 5.2glm-5-2

Kimi

Check the exact version and input types before choosing a Kimi model for a workflow.

  • Kimi K3kimi-k3
  • Kimi K2.6kimi-k2-6

DeepSeek

A separate model family with its own usage and evaluation tradeoffs.

  • DeepSeek V4.1 Flashdeepseek-v4-1-flash

GPT-OSS

The Safeguard variant is listed for API use only; it is not a Research model-picker option.

  • OpenAI GPT-OSS 120Bgpt-oss-120b
  • OpenAI GPT-OSS Safeguard 120Bgpt-oss-safeguard-120bAPI only

Gemma

An open-weight model family in Maple’s public catalog.

  • Gemma 4 31Bgemma4-31b

Llama

Meta’s open-weight model family in Maple’s public catalog.

  • Llama 3.3 70Bllama3-3-70b

CHOOSE YOUR ACCESS PATH

The model is only part of the decision.

Where it runs affects setup, cost, data handling, and the claims you can verify.

01

Run it locally

Keep model execution on a machine you control. Check the exact weights, license, memory requirement, context setting, and performance of the version you plan to run.

See a production serving recipe
02

Use a hosted API

Let a provider run the model. Compare its pricing, retention terms, logging, and available model version before sending sensitive material.

03

Use Maple

Use a hosted model through Maple’s client encryption and protected inference architecture. Review what the service can verify and what account or usage metadata remains.

How Maple works