Discover

Which model is best for what?

The right model for the right job. Recommendations by use case, plus every model on the platform with its context length and price.

By use case

Pick a model by your task

Coding & Software

Writing code, debugging, refactoring and tests. Needs strong logic and long code context.

Claude GPT-4o DeepSeek-Coder Qwen-Coder

Reasoning & Analysis

Multi-step problem solving, math, decisions and strategy. Deep-reasoning models.

o1 / o3 DeepSeek-R1 Claude Gemini

Writing & Content

Blogs, marketing copy, emails and reports. Fluent, consistent and on-brand.

Claude GPT-4o Gemini

Vision

Reading images, screenshots, documents and tables. Multimodal models.

GPT-4o Gemini Claude

Long Context

Hundreds of pages, large codebases and long chats. Million-token context.

Gemini 1.5/2.5 Claude GPT-4.1

Fast & Cheap

High volume, low latency and cost. Classification, summaries, simple tasks.

GPT-4o-mini Gemini Flash Llama Mistral

Multilingual & Turkish

Strong Turkish and 100+ languages, translation and localization.

GPT-4o Gemini Claude Qwen

Agents & Tool Use

Function calling, tool use and multi-step automation. Reliable tool-calling.

Claude GPT-4o Gemini

Summarization & RAG

Grounded, cited answers from documents, summarization and knowledge-base Q&A.

Claude GPT-4o-mini Gemini

Creative & Ideas

Brainstorming, scripts, naming and campaign ideas. Creative variety.

Claude GPT-4o Gemini

All models

Model catalog (20)

Anthropic (20)

claude-fable-5.1:batch[1m] — —

claude-fable-5.1[1m] — —

deepseek/deepseek-v4.1-flash[1m] — —

google/gemini-3.8-flash:batch[1m] — —

google/gemini-3.8-flash[1m] — —

ibm-granite/granite-4.2-8b — —

inception/mercury-2.5 — —

inclusionai/ling-3.0-flash-fin — —

inclusionai/ling-3.0-flash-sante:free — —

inclusionai/ling-3.0-flash-vl:free — —

meta/muse-spark-1.3-contributor[1m] — —

meta/muse-spark-1.3[1m] — —

nex-agi/nex-n2.5-mini:free — —

nex-agi/nex-n2.5-pro:free — —

openai/gpt-6-astra-pro:batch[1m] — —

openai/gpt-6-astra-pro[1m] — —

openai/gpt-6-astra:batch[1m] — —

openai/gpt-6-astra[1m] — —

qwen/qwen3.8-max-0902 — —

tencent/hy4-preview[1m] — —