@cf/mistral/mistral-7b-instruct-v0.1
@cf/mistral/mistral-7b-instruct-v0.1 by Mistral AI: 1 offer. From €0.099 per 1M input tokens. No offer with EU processing is listed.
Calculate costs for this modelOffers and price history
Profile
| Profile | |
|---|---|
| Developer | Mistral AI |
| Type | Language models |
| Origin | FR |
| Input types | text |
| Context (tokens) | 8,192 |
| Max. output (tokens) | – |
| Reasoning | – |
| Parameters (bn) | 7.24 |
| Open weights | ✓ yes |
| Licence | Apache-2.0 |
| Released | – |
Offers with processing in the EU (0)
No offers in this group.
Offers outside the EU (1)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| Cloudflare Workers AI | US | standard | €0.099 | €0.17 | developers.cloudflare.com | 22 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 7 Nov 2026.
Calculate costs for this model
What does @cf/mistral/mistral-7b-instruct-v0.1 cost per month? Example: 2,000,000 input and 500,000 output tokens from €0.28 – all offers, EU and non-EU.
Without JavaScript you see the example calculation. With JavaScript the table uses your volumes.
| Provider | EU processing | Input, € per 1M tokens | Output, € per 1M tokens | Cost per month, € |
|---|---|---|---|---|
| Cloudflare Workers AI | – no | €0.099 | €0.17 | €0.28 |
Source: providers' pricing pages, read and checked by searchit. As of 7 Nov 2026.
Cost = input tokens ÷ 1M × input price + output tokens ÷ 1M × output price. List prices without discounts, cache prices and taxes.
How many tokens is my text? Open the token counter
AI Act
Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act
Self-hosting
| Self-hosting | |
|---|---|
| GPU memory | from 8 GB (4-bit, derived) |
| Card | RTX PRO 4000 |
| Licence | Apache-2.0 |
| Model files | huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 |
The GPU memory is derived from the parameter count (parameters × 0.55 GB + 4 GB) and is a lower bound: long contexts and many concurrent requests need more.
All models of the tier 24 GB – one RTX PRO 4000
Benchmarks
No benchmarks recorded for this model yet.