Mistral Small 4
Access Mistral Small 4 through one API key. Europe's leading AI model at a great price.
Mistral's efficient general-purpose model. Fast, affordable, and strong at code, reasoning, and multilingual tasks.
No credit card required. Takes 30 seconds.
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Try it live
Send a message and see Mistral Small 4 respond in real time.
Maximum tokens in the response.
Real-time tokens
Context Window
262K tokens
Max Output
8K tokens
Input Price
$0.21 / 1M tokens
Output Price
$0.84 / 1M tokens
Strengths
Mistral's efficient general-purpose model, optimized for low latency and high throughput, with a 262,144-token context window and up to 8,192 output tokens.
Solid coverage across European and other languages despite its small size, reflecting Mistral's multilingual focus.
Capable code generation and basic debugging for routine programming tasks, punching above its weight for an ultra-low-cost model.
At $0.21 / $0.84 per 1M tokens it is one of the cheapest capable models available, built for very high-volume, cost-sensitive workloads.
Quick start
Copy this snippet and start making calls with Mistral Small 4.
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "mistralai/mistral-small-2603",
"messages": [
{
"role": "user",
"content": "Explain API gateways in 2 sentences."
}
],
"maxTokens": 256
}),
});
const { data } = await res.json();
console.log(data.message.content);Why use Mistral Small 4 through YepAPI?
Mistral Small 4 API — pricing, context window & access
Mistral Small 4 is Mistral's efficient general-purpose model — fast, affordable, and capable at code, reasoning, and multilingual tasks. It pairs a 262,144-token context window with up to 8,192 output tokens at an ultra-low price.
Through YepAPI you reach Mistral Small 4 over an OpenAI-compatible endpoint with one key that also covers Mistral Medium 3.5, Devstral 2, Claude, Gemini, Grok, Qwen, and Perplexity Sonar, plus SEO, SERP, and web-scraping endpoints.
What is Mistral Small 4?
Mistral Small 4 is the efficient, low-cost model in Mistral's lineup, designed for speed and volume. It handles general reasoning, code, and multilingual tasks well for its size, and is tuned to keep latency and price low. It carries a 262,144-token context window — large for a small model — and returns up to 8,192 output tokens. As Europe's leading lab's affordable model, it suits high-throughput applications where most requests are routine and cost-per-call is the priority.
Build with Mistral Small 4 via YepAPI
Set the model to mistral-small-2603 on YepAPI's OpenAI-compatible /v1/ai/chat endpoint; standard OpenAI SDK code needs only a base-URL and model-name change. Run Small 4 as a cheap default and escalate harder requests to Mistral Medium 3.5 or Claude with a one-string swap. The same key reaches Devstral 2 for coding and Sonar for web-grounded answers, so tiering needs no extra wiring.
Mistral Small 4 API pricing — $0.21 / $0.84 per 1M tokens
Mistral Small 4 costs $0.21 per 1M input tokens and $0.84 per 1M output tokens on YepAPI — among the lowest rates for any capable model. That makes it ideal for very high-volume work where you make millions of calls and need each one to be nearly free. The 256K-token window means it stays useful even on long inputs. Billing is per token with no minimums.
Mistral Small 4 for high-volume routine tasks
Small 4 is the model for scale-and-save workloads: classification, tagging, extraction, short-form generation, routing, and simple multilingual chat at massive volume. It won't match a flagship on hard reasoning, but for the large share of requests that are routine, its near-free pricing and decent quality make it the obvious workhorse — leaving Medium or a flagship to handle only the difficult cases.
Try Mistral Small 4 free
Sign up for $5 in free YepAPI credit, no card required. At Small 4's ultra-low rates, $5 buys an enormous number of tokens — more than enough to stress-test it across your high-volume workloads before paying.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
Mistral's efficient general-purpose model. Fast, affordable, and strong at code, reasoning, and multilingual tasks.
Input tokens cost $0.21 per 1M tokens and output tokens cost $0.84 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.
Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.
Mistral Small 4 supports a 262K token context window with up to 8K output tokens per request.
Ready to use Mistral Small 4?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
Mistral Medium 3.5
MistralAccess Mistral Medium 3.5 through one API key. Mistral's balanced mid-tier model.
Devstral 2
MistralAccess Devstral 2 through one API key. Mistral's coding-specialized model for developers.
Mistral Small Creative
MistralAccess Mistral Small Creative through one API key. Creative writing at the lowest price.