Supported AI Models¶

TranslateBot Django supports 100+ AI models through LiteLLM. This page covers the most popular options.

OpenAI¶

OpenAI models provide excellent translation quality and are the default choice.

settings.py

import os

TRANSLATEBOT_API_KEY = os.getenv("OPENAI_API_KEY")
TRANSLATEBOT_MODEL = "gpt-4o-mini"  # Default, recommended

Available Models¶

Model	Quality	Speed	Cost
`gpt-4o-mini`	Good	Fast	Low
`gpt-4o`	Excellent	Medium	Medium
`gpt-4-turbo`	Excellent	Medium	Medium

Recommendation

Start with gpt-4o-mini for most projects. It offers the best balance of quality, speed, and cost.

Anthropic Claude¶

Claude models excel at nuanced translations and context understanding.

settings.py

import os

TRANSLATEBOT_API_KEY = os.getenv("ANTHROPIC_API_KEY")
TRANSLATEBOT_MODEL = "claude-sonnet-4-5-20250929"

Available Models¶

Model	Quality	Speed	Cost
`claude-sonnet-4-5-20250929`	Excellent	Medium	Medium
`claude-opus-4-5-20251101`	Best	Slow	High
`claude-3-5-sonnet-20240620`	Excellent	Medium	Medium
`claude-3-haiku-20240307`	Good	Fast	Low

Recommendation

claude-sonnet-4-5-20250929 offers the best quality-to-cost ratio for most translation tasks.

Google Gemini¶

Google's Gemini models offer competitive translation quality, especially for Asian languages.

settings.py

import os

TRANSLATEBOT_API_KEY = os.getenv("GEMINI_API_KEY")
TRANSLATEBOT_MODEL = "gemini/gemini-2.5-flash"

Available Models¶

Model	Quality	Speed	Cost
`gemini/gemini-2.5-flash`	Good	Fast	Low
`gemini/gemini-3-flash-preview`	Excellent	Fast	Low

Azure OpenAI¶

Use Azure-hosted OpenAI models for enterprise deployments.

settings.py

import os

TRANSLATEBOT_API_KEY = os.getenv("AZURE_API_KEY")
TRANSLATEBOT_MODEL = "azure/gpt-4o-mini"

# Additional Azure configuration
os.environ["AZURE_API_BASE"] = "https://your-resource.openai.azure.com/"
os.environ["AZURE_API_VERSION"] = "2024-02-15-preview"

Other Providers¶

LiteLLM supports many additional providers:

AWS Bedrock: bedrock/anthropic.claude-3-sonnet
Cohere: command-r-plus
Mistral: mistral/mistral-large-latest
Ollama (local): ollama/llama3

See the LiteLLM Providers Documentation for the complete list.

Choosing a Model¶

By Use Case¶

Use Case	Recommended Model
General translation	`gpt-4o-mini`
High-quality production	`gpt-4o` or `claude-sonnet-4-5-20250929`
Budget-conscious	`gpt-4o-mini` or `claude-3-haiku-20240307`
Asian languages	`gpt-4o` or `claude-sonnet-4-5-20250929`
European languages	Any model works well

By Priority¶

Priority	Recommended Model
Quality	`claude-opus-4-5-20251101` or `gpt-4o`
Speed	`gpt-4o-mini` or `claude-3-haiku-20240307`
Cost	`gpt-4o-mini`
Balance	`claude-sonnet-4-5-20250929`

Cost Estimates¶

Approximate costs per million tokens (input):

Model	Cost
`gpt-4o-mini`	~$0.15
`claude-3-haiku`	~$0.80
`gpt-4o`	~$2.50
`claude-sonnet-4-5`	~$3.00
`claude-opus-4-5`	~$15.00

Typical Project Cost

A small-to-medium Django app with ~500 translatable strings (~10,000 words) typically costs under $0.01 per language with gpt-4o-mini.

Testing Different Models¶

Try different models without code changes:

# Test with GPT-4o
export TRANSLATEBOT_MODEL="gpt-4o"
python manage.py translate --target-lang nl --dry-run

# Test with Claude
export TRANSLATEBOT_MODEL="claude-sonnet-4-5-20250929"
export TRANSLATEBOT_API_KEY="your-anthropic-key"
python manage.py translate --target-lang nl --dry-run