MistralFree

Mistral Small 4

Mistral's hybrid model unifying instruct, reasoning, and coding in a single efficient model.

Model ID

mistralai/mistral-small-2603
Context window
256K
tokens
Max output
66K
tokens
Pricing
Free
$0 per token, for input and output.

Quickstart

Call Mistral Small 4 in one request.

Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.

SDK guides
main.py
import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["XKIRO_API_KEY"],    base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create(    model="",    messages=[        {"role": "user", "content": "Explain HTTP caching in two sentences."},    ],) print(res.choices[0].message.content)
Response · Example

✓ 200 OK

"model": "mistralai/mistral-small-2603"

HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.

14 input · 42 output tokens · $0 on this free model

Create an API key in the dashboard and export it as XKIRO_API_KEY.

Pricing

What Mistral Small 4 costs.

Free to call on every account, within the daily free-model allowance. No credit card.

Free

$0 per token, for input and output.

Billed fairly

  • A request that fails before any output is generated is never billed
  • An identical blocking request retried within two minutes replays the first result — no double charge
  • If a stream breaks off or you cancel it, you pay only up to that point

Specifications

Limits and capabilities.

Context window
256,000 tokens
Max output
65,536 tokens
Input
Text · Image
Output
Text
Provider
Mistral
Model ID
mistralai/mistral-small-2603
Good for
Coding · Long context

Capabilities

  • Tool useSupported
  • VisionSupported
  • Video inputNot supported
  • ReasoningSupported

Reasoning effort

  1. none
  2. high

Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.

Reasoning guide

Supported parameters

  • max_tokens
  • temperature
  • top_p
  • stop
  • frequency_penalty
  • presence_penalty
  • seed
  • stream
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning

Compare

Similar models.

Closest in price and context window — same provider first, then alternatives from other providers.

Browse all 69 models
Mistral Small 4 compared with similar models, prices per 1M tokens
ModelInput / 1MOutput / 1M
Mistral Small 4This modelVision · Reasoning · Tool use256KFree—
CodestralTool use256KFree—
Devstral 2Tool use256KFree—
Ministral 3 14BVision · Tool use256KFree—
North Mini CodeReasoning · Tool use256KFree—
SenseNova 6.8 Flash-LiteVision · Reasoning · Tool use262KFree—
Command ATool use288KFree—
modelmistralai/mistral-small-2603

Start building with Mistral Small 4.

Mistral Small 4 is free to call. Create a key and start in minutes, no credit card.

No credit card · No auto-renewal · 26 free models, free forever