Mistral Small 3.1 24B Instruct

We couldn't load the overview just now. Please try again in a little while.

Cloudflare Workers AI@cf/mistralai/mistral-small-3.1-24b-instructmistral-small

Open provider page Provider docs

Quick Info

Provider: Cloudflare Workers AI
Model key: @cf/mistralai/mistral-small-3.1-24b-instruct
Release date: Mar 17, 2025
Last updated: Mar 17, 2025
Knowledge cutoff: 2024-06
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.351
Output token cost: $0.555

Limits

Output tokens: 128,000 tokens
Context window: 128,000 tokens

Transparent token rates

Compare Mistral Small 3.1 24B Instruct pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Mistral Small 3.1 24B Instruct

Cloudflare Workers AI

Coverage

The Ollama library page documents MHKetbi's community repack of Mistral-Small3.1-24B-Instruct-2503, which the supplied excerpt identifies as the same underlying Mistral Small 3.1 24B Instruct checkpoint referenced by the Cloudflare Workers AI model `@cf/mistralai/mistral-small-3.1-24b-instruct`. Per the page, this is a For local deployment on Ollama, the repack ships the default `Mistral-Small3.1-24B-Instruct-2503:latest` at 47GB alongside seven quantization variants (q2_K_L at 9.5GB, q3_K_L at 12GB, q4_K_L at 15GB, q5_K_L at 17GB, q6_K_L at 20GB, and q8_0 at 25GB), all preserving the 128K context window and text-only modality as pac