Skip to main content
View source

Mistral AI

View as Markdown

A RocketRide LLM node that connects Mistral AI's chat models to a pipeline.

What it does

Connects Mistral AI models to your pipeline. Used primarily as an llm invoke connection by agents and other nodes that need an LLM. Can also be used directly via lanes.

Uses the official mistralai Python SDK (both the 1.x and 2.x import layouts are supported) and calls the chat.complete endpoint. Requests are sent with temperature: 0.0 for deterministic responses and no max_tokens cap, so the model decides output length.

Prompts are validated against the model's context window before sending. Token counts are estimated heuristically (about 1.25 tokens per word, adjusted for punctuation and long words); no tokenizer round-trip is made. The context limit comes from the selected profile's modelTotalTokens; if not configured, a built-in per-model default is used, falling back to 32,768 tokens for unknown models.

Failed API calls are retried automatically with exponential backoff (see Retries and error handling), and raw provider errors are rewritten into user-friendly messages.

When you save the node configuration, a minimal validation probe (a one-token "Hi" completion) is sent to verify the API key and model before the pipeline ever runs. Validation failures surface as warnings with the provider's error detail.

Lanes

Lane inLane outDescription
questionsanswersSend a question directly, receive a generated answer

Profiles

Default: Mistral Large 3 (mistral-large).

ProfileModelContextOutput
mistral-large (default)mistral-large-2512262,144209,715
mistral-medium-2604mistral-medium-260416,3844,096
mistral-small-2603mistral-small-2603262,144209,715
View 41 more models
ProfileModelContextOutput
custom(user-specified)32,768editable
mistral-mediummistral-medium-2508131,0724,096
mistral-smallmistral-small-2506131,0724,096
codestralcodestral-2508256,000204,800
magistral-mediummagistral-medium-250940,00040,000
magistral-smallmagistral-small-250940,9604,096
devstral-mediumdevstral-medium-2507128,000128,000
devstral-smalldevstral-small-2507128,000128,000
ministral-14bministral-14b-2512262,144209,715
ministral-8bministral-8b-2512262,144209,715
ministral-3bministral-3b-2512131,072104,857
codestral-latestcodestral-latest8,1918,191
devstral-2512devstral-2512262,144209,715
devstral-latestdevstral-latest256,000256,000
devstral-medium-latestdevstral-medium-latest256,000256,000
magistral-medium-latestmagistral-medium-latest40,00040,000
magistral-small-latestmagistral-small-latest40,00040,000
ministral-14b-latestministral-14b-latest16,3844,096
ministral-3b-latestministral-3b-latest16,3844,096
ministral-8b-latestministral-8b-latest16,3844,096
mistral-large-2411mistral-large-2411131,072128,000
mistral-large-latestmistral-large-latest32,0004,096
mistral-medium-2505mistral-medium-25058,1918,191
mistral-medium-3mistral-medium-3131,072104,857
mistral-medium-3-5mistral-medium-3-5262,144209,715
mistral-medium-c21211-r0-75mistral-medium-c21211-r0-7516,3844,096
mistral-medium-latestmistral-medium-latest131,072131,072
mistral-small-latestmistral-small-latest131,072131,072
mistral-tiny-2407mistral-tiny-240716,3844,096
mistral-tiny-latestmistral-tiny-latest16,3844,096
mistral-vibe-cli-fastmistral-vibe-cli-fast16,3844,096
mistral-vibe-cli-latestmistral-vibe-cli-latest16,3844,096
mistral-vibe-cli-with-toolsmistral-vibe-cli-with-tools16,3844,096
mistral-large-2407mistral-large-2407131,072104,857
mistral-medium-3-1mistral-medium-3.1131,072104,857
mistral-nemomistral-nemo131,07216,384
mistral-sabamistral-saba32,76826,214
mistral-small-24b-instruct-2501mistral-small-24b-instruct-250132,76816,384
mistral-small-3-1-24b-instructmistral-small-3.1-24b-instruct128,000102,400
mistral-small-3-2-24b-instructmistral-small-3.2-24b-instruct131,07216,384
mistral-medium-3-5-batchmistral-medium-3-5:batch32,76826,214

Configuration

Choose a profile to pin the Mistral model and its declared context and output limits. Most users only need to select a profile and supply an API key; choose custom to enter another Mistral model ID and context limit, and use an explicit context limit only when you need to override the built-in per-model value.

Authentication

Provide a Mistral AI API key in the apikey field (created in the Mistral AI console). The key is read at startup and never persisted by the node.

The node detects common key mix-ups at initialization and fails with a specific message:

  • Keys starting with sk- are rejected as OpenAI keys.
  • Keys starting with AI are rejected as Google AI / Gemini keys.

Notes

Retries and error handling

Transient failures (timeouts, network errors, rate limits, HTTP 5xx) are retried with exponential backoff. Retry budget scales with the model tier:

Model tierRetriesBase delay
large models32.0 s
medium / magistral models21.5 s
All other (small / edge) models21.0 s

Non-retryable errors fail immediately. Whatever the cause, the raw API error is mapped to a user-friendly message: authentication failures, rate limits, quota/billing issues, invalid input, model unavailability, server errors, content-policy violations, timeouts, and network problems each get a specific explanation instead of a stack trace.

Upstream docs


Schema

FieldTypeDescriptionDefault
mistral.profilestringModel
Mistral AI model selection
"mistral-large"
modelstringModel
Mistral AI model
modelTotalTokensnumberTokens
Maximum context length in tokens

Dependencies

  • mistralai
  • mistral-common[sentencepiece]