Guide

Mistral as a Janitor AI Proxy: The Direct API, the OpenRouter Route, and the $10 of Monthly Credits on Mistral's Free Plan

Mistral as a Janitor AI proxy: the direct OpenAI-format endpoint, listed prices per message, Mistral's free plan with $10 a month in API credits, OpenRouter ids, and what no proxy changes.

HProxy Team··5 min read
HProxy.Guide

Skip the dead lists.

Our free proxy list re-checks every exit every few minutes across 100+ countries, with a live last-checked time, so you copy IPs that worked moments ago, not a stale text dump.

Open the free proxy list

Mistral is the European model provider that Janitor AI users overlook, and it is one of the easiest to connect: its API speaks the OpenAI chat-completions format natively, so it goes straight into Janitor's proxy field with no compatibility layer, no third-party relay and no :free tag to chase. Per token it is not free, but it is cheap enough that the price is worth stating up front, and its pricing page lists a free plan with a monthly allowance of API credits that, if it applies to you, covers a lot of roleplay.

This page gives the direct values, the arithmetic, the OpenRouter alternative with today's ids and prices, and the honest list of things no proxy changes. We run a proxy network of the IP-changing kind, and the last section says where that fits, which is almost nowhere on this topic.

The direct route: Mistral's own API

Mistral's API reference documents the chat endpoint at https://api.mistral.ai/v1/chat/completions, authenticated with an Authorization: Bearer header, and its own example uses the model mistral-large-latest. That is exactly the shape Janitor's proxy field expects.

FieldValue
Config NameMistral direct
Proxy URLhttps://api.mistral.ai/v1/chat/completions
API Keya key from Mistral's console (La Plateforme)
Modelmistral-large-latest, or a smaller model name from Mistral's model list

Open a chat, tap the menu, choose API Settings, then Proxy, then Add Configuration, fill those in, save, refresh, and send a test line. A network error at this point is almost always the URL missing /chat/completions, and a 401 is the key; our network error and 401 guide has the curl test that tells the two apart.

What it costs, at listed prices

Mistral's pricing page, read on 24 August 2026, listed Mistral Large at $0.50 per million input tokens and $1.50 per million output tokens, and described most models as priced per million tokens with input and output counted separately, batch processing at half price, and cached input at up to 90 percent off.

The roleplay arithmetic: a request carrying 20,000 tokens of character, memory and history costs 20,000 at $0.50 per million, which is one cent, plus a 300-token reply at $1.50 per million, a twentieth of a cent. A hundred messages an evening on Mistral Large is roughly a dollar. Compare Claude Sonnet 5 at about four cents a message on the same context, in our Claude guide, or DeepSeek's own API, which lands in the same pennies range as Mistral.

The same pricing page lists a free plan, described around Mistral's Vibe chat product, that includes $10 a month in API credits. At Mistral Large's listed input price, $10 is twenty million input tokens, or a thousand of those 20,000-token messages. We are quoting the page as it read on the day; plan contents change, and whether the credits apply to your account and your region is something to confirm on Mistral's site rather than on ours.

Cost of one 20,000-token roleplay message with a 300-token reply, at listed prices
Mistral Medium 3.5 (OpenRouter)$1.50 in, $7.50 out per million
3.2 cents
Mistral Large (Mistral pricing page)$0.50 in, $1.50 out
1.05 cents
Mistral Small 2603 (OpenRouter)$0.15 in, $0.60 out
0.32 cents
Source: Mistral pricing page and OpenRouter public models API, read 24 August 2026; arithmetic: input tokens x input price plus output tokens x output price

The OpenRouter route

If you already run other models through OpenRouter, Mistral is a model-id change. OpenRouter's public list on 24 August 2026 carried 19 Mistral ids; the useful ones for chat:

Model id on OpenRouterInput, per millionOutput, per millionContext
mistralai/mistral-large-2512$0.50$1.50262,144
mistralai/mistral-medium-3-5$1.50$7.50262,144
mistralai/mistral-small-2603$0.15$0.60262,144
mistralai/ministral-14b-2512$0.20$0.20262,144

Proxy URL https://openrouter.ai/api/v1/chat/completions, your OpenRouter key, one of those ids, and a balance, since none carry the :free tag. OpenRouter blocks requests, free models included, when a balance goes negative, per its rate-limit documentation. The general OpenRouter setup is in our OpenRouter guide.

What no proxy changes

Limits and credits. Through Mistral directly, the rate limit and the credit balance belong to your Mistral account and follow your key; through OpenRouter, they belong to your OpenRouter account. A second key on the same account shares the limit, and a different IP address is not an input, a rule we lay out for every backend in Janitor AI error 429.

Content. What Mistral's models will write is decided by Mistral's terms and the model's training, not by the URL. Refusals come from the provider.

The route's honesty. Both routes above are your own key with an official endpoint. A "free Mistral proxy" from a Discord post is somebody else's key with somebody else reading the chat; Chub's documentation describes such proxies as created by unauthorized third parties who gain access to your data and IP address. With Mistral costing a cent a message, there is nothing to gain from borrowing one.

Where the network kind of proxy fits

Mistral's API is broadly available, and we found no country list restricting it, so the network-proxy case here is narrower than for Claude or Gemini: a school or office network that filters api.mistral.ai or janitorai.com, or Janitor's own regional rules (it blocked UK addresses from 24 July 2025 until age verification replaced the block on 15 June 2026). For that, a static residential or ISP address in a served country, kept for the session, from $0.44 per GB on a usage meter, is the tool. For the price, the credits, the limits and the refusals, it changes nothing, and the honest recommendation on this page is a Mistral key, the direct URL, and a cent a message.

Sources

Frequently asked questions

What is the Mistral proxy URL for Janitor AI?
https://api.mistral.ai/v1/chat/completions, with a Mistral API key and a model name such as mistral-large-latest. Mistral's API reference documents that endpoint with a Bearer key, and it speaks the OpenAI chat-completions format directly, so no compatibility layer or third-party relay is involved. The OpenRouter route works too: https://openrouter.ai/api/v1/chat/completions with an id such as mistralai/mistral-large-2512.
Is Mistral free to use on Janitor AI?
Not free per token, but close: Mistral's pricing page listed Mistral Large at $0.50 per million input tokens and $1.50 per million output tokens when we read it on 24 August 2026, which makes a 20,000-token roleplay message about one cent. The same page lists a free plan that includes $10 a month in API credits alongside its Vibe chat product; at Mistral Large's price that is twenty million input tokens a month. Check the plan's current terms on Mistral's site before relying on it, because plan contents change.
Which Mistral model should I use for Janitor AI?
mistral-large-latest is the general-purpose model in Mistral's own API example and the cheapest way to get the biggest one. On OpenRouter the current ids include mistralai/mistral-large-2512 ($0.50 and $1.50 per million), mistralai/mistral-small-2603 ($0.15 and $0.60) and mistralai/mistral-medium-3-5 ($1.50 and $7.50). Small is the budget choice for fast back-and-forth; Large for longer scenes. Ids rotate with releases, so copy the current one from the provider's page.
Why do I get a 429 with Mistral on Janitor AI?
You hit your Mistral account's rate limit or ran out of credits, both of which are tied to your key and account. Wait, slow down, or add credit. A different IP address does nothing, and a second key on the same account shares the same limit. If you use the OpenRouter route, OpenRouter's own balance and limits apply instead.
Will Mistral write uncensored roleplay?
Mistral's models are widely used for roleplay and its terms and usage policies decide what they will produce; refusals, where they happen, come from the model and its provider, not from the URL. A proxy of either kind, a model endpoint or a network proxy, does not change a provider's content policy. Read Mistral's terms before choosing it for a particular kind of scene.
Do I need a network proxy for Mistral on Janitor AI?
Only if api.mistral.ai or janitorai.com will not answer from your network or your country. Mistral is a French company and its API is broadly available, but school and office networks filter API hosts, and Janitor itself blocked UK addresses between July 2025 and June 2026. For that case a static residential address in a served country is the tool; for cost, limits and refusals it changes nothing.

Get proxies that are alive right now

Our free list re-checks every exit every few minutes and shows a last-checked time, so you copy IPs that worked moments ago, not a stale text dump. When the location has to survive a real check, the paid network holds up.

129M+ proxy checks run · 100+ countries · HTTP / HTTPS / SOCKS · re-checked every few minutes · no signup