Mistral Tiny
Mistral Tiny is a previous cheap Mistral snapshot powered by leftover Mistral-7B-v0.2 copy, not the live catalog lead.
Compare Mistral 7B Instruct if you wanted the leftover 7B twin already rewritten as previous, Mistral Small if you wanted leftover Small v24.09, and Mistral Nemo if you wanted the leftover 12B NVIDIA snapshot.
Key Features
- Previous Tiny snapshot: older copy said it is currently powered by Mistral-7B-v0.2. Confirm the live models page before you hard-code Tiny.
- Not the 2026 Mistral lead: Live catalog leads with Medium 3.5 / Small 4 / Large 3.
- Website is models, not a company slug: There is no
/items/ai-ecosystem/mistralpage.
Use Cases
- People with a Mistral Tiny bookmark who need the catalog corrected.
- People who were about to keep 7B-v0.2 as the current cheap Mistral default.
Limitation: We did not call a Tiny API. Absence from the live pricing nav is not a shutdown certificate.
Pricing
First-party pages on 2026-08-18.
| Piece | Price | Notes |
|---|---|---|
| Mistral Tiny | Previous snapshot | Confirm mistral.ai/models. |
| Live Mistral catalog | Confirm Medium 3.5 / Small 4 / Large 3 | Those names lead the public pages. |
| Dollar row | Confirm live Mistral API pricing | Confirm the live official page. |
If a leftover blog still calls Tiny the current cheap Mistral default, treat the live models page as the correction.
Getting Started
- Open mistral.ai/models before you hard-code Tiny.
- Confirm Small 4 / Medium 3.5 / Large 3 if you wanted the live path.
- Confirm Mistral 7B Instruct if you wanted the leftover 7B twin.
- Do not paste "currently powered by 7B-v0.2" into a 2026 deck.
Frequently Asked Questions
Is Tiny still the cheap Mistral default?
Not on the live catalog on the public page. Medium 3.5 / Small 4 lead.
Same as 7B Instruct?
No. Both are leftover snapshots. Tiny's older copy pointed at 7B-v0.2 fine-tuning.
Same as Small 4?
No. Small 4 is a current live catalog row.
Alternatives
- Mistral Small: Leftover Small v24.09 already rewritten as previous.
- Mistral 7B Instruct: Leftover 7B twin.
- GPT-5.6 Sol: Live OpenAI frontier if you wandered here for a current model.
Tips
- Call Tiny a previous snapshot, not the current cheap Mistral default.
- Point new Mistral work at Medium 3.5 / Small 4 / Large 3.
- Confirm live docs before you invent a Tiny dollar row.
Conclusion
Mistral Tiny is a previous cheap snapshot, not the 2026 Mistral default. Start at mistral.ai/models, then decide whether Small 4 or Medium 3.5 already covers the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights

Grok Bot and Hermes Bot: one person finally gets a think tank and a secretariat
Grok Bot now ships with Cursor Pro+. Hermes Bot runs on a VPS. They are not smarter chat boxes. The think tank advises, the secretariat executes, and you still make the call.
Hook OpenCode Go into Codex on Windows. Do Not Open a Second Toolkit.
A ChatGPT-signed Codex desktop app still shows mostly GPT in the picker. On Windows, enable only OpenCode Go and the Grok, GLM, Kimi, DeepSeek, and MiniMax models you already pay for appear in the same selector. Keys stay local. Native GPT stays put.
What Locks Codex Is the Picker, Not the Models
You already pay for OpenCode Go, Grok, and Z.ai, but the Codex picker still shows mostly GPT. The community project codex-router does not teach another install ritual. It puts subscriptions you already bought back into the selector, keeps keys on the machine, and leaves native GPT alone.