llm11

Mistral Small 4 with Jev

Mistral Small 4 is a model from Mistral, released 2026-03-16. It costs $0.150 per million input tokens and $0.600 per million output tokens, reads up to 262K tokens of context, and writes up to 209,715 tokens in one reply. Through llm11, set model to mistralai/mistral-small-2603.

Input price
$0.150 / 1M
Output price
$0.600 / 1M
Context window
262K tokens
Max output
210K tokens
Cached input
$0.015 / 1M

Read from the provider's prompt cache

Released
2026-03-16
Accepts
text, image
Intelligence index
11.3

Artificial Analysis, via the catalogue

Read from the live catalogue and refreshed daily. At blended list price, 73% of the 332 priced models we can call cost more.

Using Mistral Small 4 with Jev

Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Mistral Small 4 does the answering when Jev sends it work, or when you name it yourself. Mistral Small 4 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.

Jev is new, so we have not published results for Mistral Small 4 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.

About JevThe System One router

What a request costs

List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.

RequestTokens in / outOneA thousand
Short chat turn500 / 200$0.00019$0.195
Question over retrieved documents4,000 / 500$0.00090$0.900
Long document summary30,000 / 1,000$0.00510$5.10

Cheaper models to try

Nearest in price and below Mistral Small 4, each within a few points of it on the intelligence index.

Cheaper alternatives to Mistral Small 4
ModelInput / 1MOutput / 1MContextIndex
OpenAI GPT-6 Luna$0.100$0.5001.05M37.3
DeepSeek DeepSeek V4 Flash 0423$0.140$0.2801.05M24.2
Qwen Qwen3.5-9B$0.100$0.150262K11.2
DeepSeek DeepSeek V4 Flash 0731$0.018$0.3201.31M34.3

Call it

Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.

python

from openai import OpenAI

client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")

res = client.chat.completions.create(
    model="mistralai/mistral-small-2603",
    messages=[{"role": "user", "content": "Hello"}],
)

More from Mistral

Other Mistral models
ModelInput / 1MOutput / 1MContext
Mistral Medium 3.5$1.50$7.50262K
Devstral 2 2512$0.400$2.00262K
Ministral 3 14B 2512$0.200$0.200262K
Ministral 3 3B 2512$0.100$0.100131K
Ministral 3 8B 2512$0.150$0.150262K
Mistral Large 3 2512$0.500$1.50262K

All 19 Mistral models

Questions

What is Mistral Small 4 with Jev?
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Mistral Small 4 does the answering when Jev sends it work, or when you name it yourself. Mistral Small 4 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
Is Mistral Small 4 a System One model?
No. Mistral Small 4 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
How much does Mistral Small 4 cost?
$0.150 per million input tokens and $0.600 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00090, so a thousand of them is about $0.900. llm11 passes provider list price through and charges 5% when you buy credits.
What is the Mistral Small 4 context window?
262,144 tokens, with up to 209,715 tokens in a single reply.
Does Mistral Small 4 support tool calling and structured output?
The catalogue lists tool calling, structured output and reasoning controls.
Can I use Mistral Small 4 through llm11?
Yes. Set model to mistralai/mistral-small-2603 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
Does Jev route to Mistral Small 4?
Routing decisions are made by Jev, TypeSafe AI's System One model. Mistral Small 4 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
What is a cheaper alternative to Mistral Small 4?
Nearest in price and below it: OpenAI GPT-6 Luna at $0.100 in and $0.500 out, DeepSeek DeepSeek V4 Flash 0423 at $0.140 in and $0.280 out and Qwen Qwen3.5-9B at $0.100 in and $0.150 out. Nearest in price and below Mistral Small 4, each within a few points of it on the intelligence index.