weightsapi.INFERENCEConsole
Navigation
MODEL REFERENCE

Mistral Small 4

An official Mistral model combining text and image input, tool calling and configurable reasoning, with a published 262,144-token window.

No KYC

No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.

No added content filters

WeightsAPI adds no content filter at the gateway. A model’s own training can still lead it to refuse a request.

INPUT / 1M$0.15
OUTPUT / 1M$0.60
SERVICE CONTEXT*128K
MEASURED SPEEDnot measured

API model IDmistralai/Mistral-Small-4-119B-2603

Published context262,144 tokens

QuantizationNot verified

LicenseApache 2.0

Best for#

Assistants that combine text, images and tool workflows, including document extraction and coding. The publisher supports instruction and reasoning modes in one checkpoint. Model card.

Choose another model when#

You need audio input or image generation. This checkpoint takes text and images and produces text. Compare a specialist model for workloads that do not need vision. Published modalities.

Deployment details#

Mistral publishes a 262,144-token serving window. The configuration contains a larger positional ceiling with YaRN; it does not establish a validated million-token service. Mistral-specific processing and parsers are required. Confirm WeightsAPI’s serving quantization and deployment support before use.

Shared inference is billed at the input and output prices shown on this page, in USD per million tokens. The same rates apply throughout WeightsAPI’s service context window; no cache or batch discount applies to this standard rate. Confirm the deployed context before using the listed 131,072-token service ceiling. See pricing and service status before use.

License and provenance#

Use the official Apache-2.0 checkpoint mistralai/Mistral-Small-4-119B-2603. Its NVFP4 variant and Eagle head are separate downloads. Publisher repository.

Call this model#

Set model to mistralai/Mistral-Small-4-119B-2603 in a request prepared from the quickstart. Confirm image, tool and reasoning support on the actual WeightsAPI deployment before relying on those features.

Sign-in, one confirmed top-up of at least USD 100 and enough available credit are required for AI access. Published prices do not activate a model: check service status for deployment availability.

Request example

curl https://weightsapi.com/v1/chat/completions \
  -H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistralai/Mistral-Small-4-119B-2603",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true
}'