Magistral Medium

Mistral · mistral family · Official Docs

Magistral Medium 1.2 is Mistral's answer to the reasoning model trend — a dedicated chain-of-thought model with explicit [THINK]/[/THINK] tokens that make reasoning traces inspectable and debuggable. This transparency is a significant advantage for Refrase's prompt optimization workflow: users can see exactly how the model reasons and tune prompts to guide that reasoning. The 131K max output tokens is generous for reasoning-heavy tasks. The key limitation is the proprietary nature — unlike Mistral Large 3, this model cannot be self-hosted, locking users into Mistral's API. The 40K optimal context threshold is notably lower than the 128K advertised maximum, so Refrase should flag this discrepancy in recommendations. At $2/$5 per million tokens, it sits in the premium tier — best reserved for high-value reasoning tasks where the thinking trace visibility justifies the cost premium over alternatives.

Rank

Quality Score

2000ms

Avg Response

+9%

Adaptation Gain

Specifications

128K

Context Window

131K

Max Output

$2 / $5

Per 1M tokens (in/out)

Mistral API (La Plateforme) 'Premier' tier pricing. Not open-weight — proprietary model. Magistral Small 1.2 is available as a cheaper open-weight alternative at $0.50 input / $1.50 output. (source: Mistral Docs, Models overview page)

Key Capabilities

✓Frontier-class reasoning model with dedicated [THINK] and [/THINK] tokens for chain-of-thought traces (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')
✓Multimodal: visual encoder for image analysis and understanding (source: Mistral Docs, Magistral Medium 1.2 page)
✓Native function calling, structured outputs, and agent conversations with built-in tools (source: Mistral Docs, Magistral Medium 1.2 page)
✓Document AI: OCR with structured annotations, bounding box extraction, and document Q&A (source: Mistral Docs, Magistral Medium 1.2 page)
✓Audio transcription with timestamps (source: Mistral Docs, Magistral Medium 1.2 page)
✓Fill-in-the-Middle (FIM) for code generation and predicted outputs (source: Mistral Docs, Magistral Medium 1.2 page)
✓25+ language support including French, German, Arabic, Japanese, and Chinese (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')

Known Limitations

⚠Proprietary model — weights not publicly available, no self-hosting option (unlike Mistral Large 3 and Magistral Small) (source: Mistral Docs, Models overview page)
⚠Context window optimal performance under 40K tokens despite 128K maximum — quality may degrade at longer contexts (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')
⚠Exact parameter count and architecture undisclosed — limited transparency compared to open-weight alternatives (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')
⚠Premium pricing ($2/1M input, $5/1M output) — 4x the cost of Mistral Large 3 input and 3.3x output, reflecting reasoning compute overhead (source: Mistral Docs, Models overview page)

Prompt Patterns

Preferred Instruction Format

Standard chat format with system/user/assistant roles. Reasoning traces enclosed in [THINK] and [/THINK] tokens for developer inspection. API model name: magistral-medium-2509 or magistral-medium-latest.

Recommended Practices

Use temperature=0.7, top_p=0.95, max_tokens=131072 as recommended sampling parameters (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')
Leverage [THINK]/[/THINK] tokens to inspect reasoning traces for debugging and quality assurance (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')
Use for reasoning-intensive tasks where chain-of-thought quality matters more than raw speed (source: Mistral Docs, Models overview page)
Apply the same Mistral prompt engineering best practices: explicit role definition, hierarchical structure, Markdown/XML formatting (source: Mistral Docs, Prompting Capabilities)
Keep context under 40K tokens for optimal reasoning quality (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')

Anti-Patterns to Avoid

Do not use for simple tasks where reasoning overhead is unnecessary — Mistral Large 3 or smaller models are more cost-effective (source: Mistral Docs, Models overview page)
Avoid same anti-patterns as Mistral Large 3: vague quantifiers, ambiguous descriptors, contradictory rules, numeric scales (source: Mistral Docs, Prompting Capabilities)
Do not exceed 40K tokens of context if reasoning quality is critical — performance is optimal below this threshold (source: apidog.com, 'Magistral Small 1.2 and Magistral Medium 1.2 are here')

Sources

What Refrase Does

Here is exactly how Refrase optimizes prompts for Magistral Medium, rule by rule:

Step-by-step for analysis

Refrase rewrites analysis prompts to include explicit step-by-step instructions, since Mistral Large lacks a built-in thinking mode and benefits from methodical guidance.

JSON reinforcement

Refrase adds explicit JSON schema hints and formatting rules so the model produces valid, parseable JSON output without extra markdown or commentary.

Reasoning hints

Refrase adds chain-of-thought prompting cues that guide the model to reason step-by-step before answering, improving accuracy on complex tasks.

Before / After

See how Refrase transforms a generic prompt for Magistral Medium.

Original

Extract the key information from this document. Be accurate.

Adapted for Magistral Medium

Extract the key information from this document.
Approach this step-by-step:
1. Identify the document type and structure
2. Extract each key field
3. Verify completeness against the original
Think through the extraction systematically before producing your final answer.
Return valid JSON only. No markdown fences, no commentary outside the JSON object.

Try It

Your prompt134 chars

Optimized for magistral

Click "Refrase It" or select a model to see the optimized prompt.