Mistral Shieldstral 1.0
Shieldstral 1.0 is the live compact multimodal moderation row on the Mistral catalog, not leftover chat / VLM pages. Rechecked 2026-08-18: docs.mistral.ai/models still lists Shieldstral 1.0 as a compact multimodal moderation model, and docs.mistral.ai/capabilities/guardrailing still names Shieldstral 2.0 as a later 400M / 1B Apache-2.0 pair. Do not invent a Shieldstral 1.0 dollar row. Recheck first-party pricing before you quote one.
Compare leftover Pixtral 12B if you wanted the leftover 2024 VLM, leftover Mistral Small if you wanted leftover chat, and Mistral OCR 4.1 if you wanted the live OCR row already added.
Key Features
- Live compact moderation row: First-party catalog still names Shieldstral 1.0.
- Later 2.0 docs exist: Guardrailing docs also name Shieldstral 2.0. Recheck that page before you collapse the family.
- Not leftover Pixtral / Small: Those leftover pages stay previous snapshots.
- No invented dollar row: Recheck mistral.ai/pricing before you quote a token price.
Use Cases
- People who need the current Mistral moderation row after leftover chat / VLM pages were rewritten.
- People comparing Shieldstral 1.0 vs later Shieldstral 2.0 docs.
- People who were about to invent a Shieldstral 1.0 dollar table.
Limitation: We did not invent a 2026 Shieldstral 1.0 dollar row.
Pricing
First-party pages on 2026-08-18.
| Piece | Price | Notes |
|---|---|---|
| Shieldstral 1.0 | Recheck first-party pricing | Listed on docs.mistral.ai/models. No invented dollar row. |
| Later docs | Shieldstral 2.0 | Named on the guardrailing page. |
If a leftover blog still treats leftover Pixtral as the current Mistral safety model, treat this page as the correction.
Getting Started
- Open docs.mistral.ai/models and confirm Shieldstral 1.0.
- Recheck the guardrailing page for later Shieldstral 2.0 docs.
- Recheck leftover Pixtral 12B only as a leftover VLM.
- Do not invent a Shieldstral 1.0 token table.
Frequently Asked Questions
Same as Pixtral 12B?
No. Pixtral 12B is a leftover 2024 VLM.
Same as OCR 4.1?
No. Mistral OCR 4.1 is the live OCR row.
Did we invent a price?
No. Recheck first-party pricing before you quote one.
Alternatives
- Mistral OCR 4.1: Live latest OCR row.
- Pixtral 12B: Leftover 2024 VLM.
- omni-moderation-latest: Leftover OpenAI moderation twin if you wandered here for a current safety API.
Tips
- Call Shieldstral 1.0 the live compact moderation row, not leftover Pixtral.
- Recheck Shieldstral 2.0 docs before you collapse the family.
- Do not invent a Shieldstral 1.0 dollar row.
Conclusion
Shieldstral 1.0 is the live compact multimodal moderation row on the Mistral catalog. Start at docs.mistral.ai/models, then decide whether later Shieldstral 2.0 docs already cover the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
Mistral Voxtral Mini Transcribe 2
docs.mistral.ai/models
Mistral Voxtral Mini Transcribe 2: live Premier transcription row, v 26.02. Rechecked 2026-08-18. Older 25.07 is deprecated. No invented dollar row.
Mistral Voxtral Mini Transcribe Realtime
docs.mistral.ai/models
Mistral Voxtral Mini Transcribe Realtime: live realtime transcription sibling. Rechecked 2026-08-18. Not leftover Transcribe 25.07. No invented dollar row.
Mistral Voxtral TTS
docs.mistral.ai/models
Mistral Voxtral TTS: live catalog TTS row, v 26.03, CC BY-NC 4.0. Rechecked 2026-08-18. No invented dollar row.
Related Insights
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.
Seven AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.