What is Small 3 API?
Small 3 is available through AIMLAPI.
Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 32,768 tokens / Max output: 16,384 tokens
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
Small 3 API Pricing
- Input: $0.065 / 1M tokens
- Output: $0.104 / 1M tokens
Where to Use Small 3
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Code Sample
[embed]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Fast-response conversational agents are a documented fit for this model, especially where quick, accurate replies and near real-time interaction matter.
Low-latency function calling is another stated use case, including automated or agentic workflows that need rapid tool execution.
Subject matter experts via fine-tuning are explicitly called out as a use case, with the model intended to be specialized for domains like legal advice, medical diagnostics, and technical support.
Local inference is also documented as a use case, particularly for hobbyists and organizations handling sensitive or proprietary information.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "mistralai/mistral-small-24b-instruct-2501", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "mistralai/mistral-small-24b-instruct-2501", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"mistralai/mistral-small-24b-instruct-2501","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU-Pro | 66.3% | Multi-discipline knowledge + reasoning (harder MMLU) | Source | July 13, 2026 |
| Intelligence | 6.7 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Math | 4.3 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Small 3 This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Small 3 has a 32,768 tokens context window and can return up to 16,384 tokens.
Small 3 takes image, text as input and returns text.
Use mistralai/mistral-small-24b-instruct-2501 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Small 3 is priced at input $0.06877 / 1M tokens, output $0.110032 / 1M tokens.
Yes, Small 3 can stream responses as they are generated.
Yes, Small 3 accepts image input alongside text.
Small 3 was built by Mistral AI.
Yes, Small 3 supports function calling as well as parallel tool calls.
