Mistral Playground
Playground
  • Chat
  • Shared chats
  • OCR
  • Embeddings
History
  • No entries yet...
Documentation
  • Mistral
  • API
  • Delete API key
  • Buy me a coffee
  • Github
  • About
  • Settings
  1. Mistral Playground
  2. Chat completion
0.3
1
Enables JSON mode, which guarantees the message the model generates is in JSON.
When using JSON mode you MUST also instruct the model to produce JSON yourself with a system or a user message.

Determines how much the model penalizes the repetition of words or phrases.

0

Penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition.

0

The maximum number of tokens to generate in the completion.

The seed to use for random sampling. If set, different calls will generate deterministic results.

Whether to inject a safety prompt before all conversations.