Choose a Model

Pick the right model for your task, budget, and latency requirements from 220 options across 18 providers.

Model Naming

All models use the provider/model format:

anthropic/claude-sonnet-4-6
openai/gpt-4.1
google/gemini-2.5-pro
deepseek/deepseek-chat

Bare model names (e.g., gpt-4.1) are accepted as aliases and resolve to the default provider.

By Use Case

General Chat and Assistants

ModelStrengthSpeedCost
anthropic/claude-sonnet-4-6Best overall balanceFastMedium
openai/gpt-4.1Strong general purposeFastMedium
google/gemini-2.5-proLong context (1M tokens)MediumMedium
deepseek/deepseek-chatCost-effectiveFastLow

Complex Reasoning

ModelStrengthSpeedCost
anthropic/claude-opus-4-6Deep analysis, researchSlowHigh
openai/o3Math, logic, scienceSlowHigh
openai/o4-miniReasoning at lower costMediumMedium
google/gemini-2.5-proLong-context reasoningMediumMedium

Fast and Cheap

ModelStrengthSpeedCost
anthropic/claude-haiku-4-5Fastest ClaudeVery fastLow
openai/gpt-4.1-nanoCheapest OpenAIVery fastVery low
google/gemini-2.5-flashFast with thinkingVery fastLow
deepseek/deepseek-chatHigh quality for priceFastLow

Coding

ModelStrengthSpeedCost
anthropic/claude-sonnet-4-6Best for code generationFastMedium
openai/gpt-5-codexOptimized for codeMediumMedium
alibaba/qwen3-coder-nextStrong coding in Chinese+EnglishFastLow
deepseek/deepseek-chatCompetitive codingFastLow

Chinese Language

ModelStrengthSpeedCost
alibaba/qwen-3.6-plusBest Chinese understandingFastLow
zhipu/glm-5.1Strong Chinese reasoningFastLow
deepseek/deepseek-chatBilingual excellenceFastLow
moonshot/kimi-k2.5Chinese conversationFastLow

Image Generation

ModelEndpointStrength
google/imagen-4.0/v1/images/generationsPhotorealistic
azure/mai-image-2/v1/images/generationsCreative styles
alibaba/wan-2.7/v1/images/generationsArtistic generation

Embeddings

ModelDimensionsUse Case
openai/text-embedding-3-large3072Highest accuracy
openai/text-embedding-3-small1536Good balance
google/gemini-embedding-0013072Long text
cohere/embed-v41024Multilingual

Auto Routing

Set model to auto and Chuizi.AI selects the best model based on your request characteristics — input length, language, task type, and budget:

example.py
python
response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
)

Cost Comparison

All pricing is upstream cost x 1.05. Check current prices at chuizi.ai/models — the models page shows input/output price per million tokens for every model.

As a rough guide:

TierInput (per 1M tokens)Models
Budget< $0.50GPT-4.1-nano, Gemini Flash, Haiku
Mid-range$0.50 - $5Sonnet, GPT-4.1, DeepSeek
Premium> $5Opus, o3, Gemini Pro

Full Model List

Browse all available models with live pricing, context window sizes, and capability tags at chuizi.ai/models.

Next Steps

Choose a Model — Chuizi AI Docs | Chuizi AI