Get Started

Choosing a model

The catalog is deliberately curated: five production models spanning reasoning, coding, chat, and vision, all behind the same OpenAI-compatible endpoint.

Larger models give you more capability on complex tasks; smaller ones respond faster and cost less per token. Capability is never one-to-one across model families, so treat these recommendations as starting points and spot-check candidates on your own prompts, the playground makes side-by-side comparisons quick.

Recommendations by use case

Use caseStart withAlso consider
Agentic coding & complex reasoningGLM-5.2DeepSeek V4 Pro
Low-latency agents & high-volume pipelinesDeepSeek V4 FlashGLM-5.3 Flash
General chat & assistantsGLM-5.2DeepSeek V4 Pro
Vision & image understandingGemma 4 31B InstructGLM-5.3 Flash
Long documents & whole-codebase contextDeepSeek V4 Pro (1M-token context)GLM-5.2 (also 1M)
Low-cost, short-context tasksGemma 4 31B InstructDeepSeek V4 Flash

Supported models

Pass the model ID as the model parameter in your requests. Context and max output are shown as rounded thousands; the exact values are at GET /models.

ModelContextMax outputInputFeatures
Gemma 4 31B Instructgoogle/gemma-4-31b-it256k256kText, ImageTools, JSON mode
GLM-5.2zai-org/GLM-5.21M1MTextTools, JSON mode, Reasoning
GLM-5.3 Flashzai-org/GLM-5.3-Flash1M1MText, ImageTools, JSON mode, Reasoning
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro1M1MTextTools, JSON mode, Reasoning
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-0731256k256kTextTools, JSON mode, Reasoning

In one line each:

ModelBest for
Gemma 4 31B InstructVision and image understanding at a small-model price point
GLM-5.2General chat and long-context assistants with strong tool use and visible reasoning
GLM-5.3 FlashFast multimodal chat and high-volume agents with visible reasoning
DeepSeek V4 ProAgentic coding, hard reasoning, and whole-codebase context
DeepSeek V4 FlashFast, cost-efficient reasoning for high-volume agents and pipelines

Pricing is per token and varies by model. Live rates for your organization, including discounted cached-input pricing, are always on the dashboard's Models page.

List models via the API

The live catalog is also served by the standard OpenAI models endpoint. Each entry's id is the value you pass as model, alongside per-model context length, modalities, and supported parameters:

curl https://inference.pearlresearch.ai/v1/models \
  -H "Authorization: Bearer $PEARL_API_KEY"

Migrating from closed models

Moving from a closed-model provider? Because the endpoint is OpenAI-compatible, migrating is usually a base-URL and model-name change. As a starting point:

If you useStart with
Frontier coding & agent models (GPT-5-class, Claude Opus-class)DeepSeek V4 Pro
Mid-tier general models (GPT-4o-class, Claude Sonnet-class)GLM-5.2
Fast, low-cost models (mini/Haiku-class)DeepSeek V4 Flash
Fast multimodal models (GPT-4o-mini-class)GLM-5.3 Flash
Multimodal models used for image understandingGemma 4 31B Instruct
Choosing a model, Pearl Inference Docs