LLM
The connection to an LLM is based on an
- A URL endpoint, as shown below
- An API token the customer must enter when creating the configuration.
For example, to obtain your key from ChatGPT, please refer to the following page:
| LLM | API Endpoint URL | Model Examples |
|---|---|---|
| ChatGPT (OpenAI) | https://api.openai.com/v1/chat/completions |
gpt-5.5, gpt-5.4-mini, o3 |
| Claude (Anthropic) | https://api.anthropic.com/v1/messages |
claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5 |
| DeepSeek | https://api.deepseek.com/v1/chat/completions |
deepseek-v4-pro, deepseek-v4-flash, deepseek-r1 |
| Fireworks | https://api.fireworks.ai/inference/v1/chat/completions |
accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3 |
| Gemini (Google) | https://generativelanguage.googleapis.com/v1beta/models/ |
gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite |
| Groq | https://api.groq.com/openai/v1/chat/completions |
llama-3.3-70b-versatile, gpt-oss-120b |
| Mistral | https://api.mistral.ai/v1/chat/completions |
mistral-large-3, mistral-small-4, codestral |
| OpenRouter | https://openrouter.ai/api/v1/chat/completions |
openai/gpt-5.5, anthropic/claude-sonnet-4-6, google/gemini-3.1-pro |
| Perplexity | https://api.perplexity.ai/chat/completions |
sonar-pro, sonar |
| Together AI | https://api.together.xyz/v1/chat/completions |
meta-llama/Llama-3.3-70B-Instruct-Turbo, deepseek-ai/DeepSeek-V4-Pro |
| xAI Grok | https://api.x.ai/v1/chat/completions |
grok-4, grok-4-fast, grok-3-mini |
Below is a view of the Edit page:
Token Count
When viewing the LLM connection, the number of tokens used up to that point will be displayed.
When an LLM is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page.
Prompting
For best results with an LLM, prompting is recommended. Localyzer allows for three levels of prompting:
See: Prompting
Context Prompting
If the LLM connection is configured with an InContext server, then when a context has been associated with a string (See String Manager / Context), the context will be passed to ChatGPT to provide the necessary information to better translate that string.
Make sure the LLM model takes advantage of the InContext image. Not all models do.