Mistral Small 4

Chat model from Mistral. One API key reaches all 2 providers, with automatic failover.

Input / 1M$0.16

Output / 1M$0.63

Context262K

Providers 2 providers, one key

No card required. Start with 1 million free tokens.

Overview

About Mistral Small 4

Mistral Small 4 is a chat model published by Mistral, with a 262,144-token context window. Through TrustedRouter it runs on 2 providers, with options in the EU, from $0.16 per million input tokens. One provider offers zero data retention.

Model ID: mistralai/mistral-small-2603
Publisher: Mistral
Modes: chat
Billing: Credits or your own provider key
More data: Mistral Small 4 Providers Mistral Small 4 Pricing

Quickstart

Set it up with your agent

Paste this into Claude Code, Cursor or any coding agent.

Use Mistral Small 4 through TrustedRouter in this project.

1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
   https://api.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Set the model to mistralai/mistral-small-2603.
4. Run the tests, then show me the diff before committing.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
response = client.chat.completions.create(
    model="mistralai/mistral-small-2603",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)

curl https://api.trustedrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-small-2603",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Your agent will need an API key.

2 providers

Providers

Your key goes to the cheapest healthy provider and fails over on its own. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.

Mistral Small 4 providers and prices per 1M tokens
Provider	Input	Cached	Output	Cost per 1M in + out
Mistral Cheapest	$0.158	$0.0158	$0.633	$0.79
Retention Verification: no verified privacy claim. TrustedRouter's managed Mistral account has model-training use disabled, so new input and output sent through TR-funded routes is opted out of model training. This is not zero data retention: Mistral's published policy says ordinary API input and output may be retained for 30 rolling days unless ZDR is separately activated. Customer BYOK accounts keep their own Mistral privacy settings. Provider policy source Location Operator country: FR Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence Weight format Unknown Price and speed Input $0.15825/1M · Cached input $0.015825/1M · Output $0.633/1M TTFT: 1.00 s Speed: insufficient data Last sample: 2026-11-12T14:16:01.000Z Mistral provider page
Regolo Zero retention	$0.589	—	$2.48	$3.06
Retention Zero data retention. Regolo states that inference prompts and outputs are processed in memory and discarded, with no reuse for training. This is a provider policy, not verified confidential compute or provider-side E2EE. Provider policy source Location Operator country: IT Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence Weight format Unknown Price and speed Input $0.589323/1M · Cached input Not published · Output $2.475157/1M TTFT: insufficient data Speed: insufficient data Last sample: 2026-11-12T15:54:30.000Z Regolo provider page

Append :nitro to the model ID, or send "provider": {"sort": "throughput"}, to route to the fastest provider instead.

FAQ

Questions

What model ID should I use for Mistral Small 4?

Use mistralai/mistral-small-2603 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Do you log my prompts or outputs?

No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.

Which providers serve Mistral Small 4?

TrustedRouter currently lists Regolo, and Mistral for Mistral Small 4. Provider availability and routing eligibility can change as catalog and health data update.

How much does Mistral Small 4 cost through TrustedRouter?

The current lowest Credits input price is $0.15825/1M and the lowest Credits output price is $0.633/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Mistral Small 4?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.

Compare

Mistral Small 4 vs other models

vs Qwen3.8 27B All comparisons

Start building with Mistral Small 4.

No card required. Start with 1 million free tokens.