Supported LLM Models

Large language models available on WaveSpeedAI.

Available Models

Note: Visit wavespeed.ai/llm for the latest pricing and model availability. Select a model in the Playground to see its context length, input price, and output price.

Model Categories

Fast & Affordable

For quick responses and cost efficiency:

• bytedance-seed/seed-1.6-flash — Fast inference, large context
• google/gemini-3-flash-preview — Google’s fast model

High Performance

For complex tasks requiring advanced reasoning:

• openai/gpt-5.2-pro — OpenAI’s professional model
• bytedance-seed/seed-1.6 — Full Seed model

Creative & Specialized

For creative writing and specialized tasks:

• mistralai/mistral-small-creative — Creative writing focus
• minimax/minimax-m2.1 — Minimax’s latest model

Code & Technical

For coding and technical tasks:

• z-ai/glm-4.7 — Strong technical capabilities
• nvidia/nemotron-3-nano-30b-a3b — NVIDIA’s efficient model

Choosing a Model

Model Properties

When you select a model in the Playground, you’ll see:

Using Different Models

Select a different model from the dropdown in the LLM Playground. Each model has different capabilities, context lengths, and pricing.

Click View Code in the Playground to get the API code for your selected model and configuration.

Model Updates

We regularly add new models. Check the LLM Playground for the latest availability.

Related Pages

• LLM Service Overview
• LLM Quick Start