Magistral Small 2509
Magistral Small is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.
- Input / output price
- $0.50 / $1.50 per 1M
- Context
- 128K tokens
- Released
- Sep 17, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/magistral-small-1.2 | $0.50/M | $1.50/M |
Pricing
USD per 1M tokens on Concentrate, after gateway discounts.
- Input
- $0.50 per 1M
- Output
- $1.50 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better15tokens/sacross providers
Response latency
Lower is better1.3sacross providers
Benchmarks
7 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBench (v5)huggingface.co | 70.9% | huggingface.co | Sep 17, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA Diamondhuggingface.co | 70.1% | huggingface.co | Sep 17, 2025 |
| GPQA DiamondEpoch AI | 47.6% | Epoch AI | Oct 13, 2026 |
| Chess PuzzlesEpoch AI | 3% | Epoch AI | Oct 13, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME24 (pass@1)huggingface.co | 86.1% | huggingface.co | Sep 17, 2025 |
| AIME25 (pass@1)huggingface.co | 77.3% | huggingface.co | Sep 17, 2025 |
| OTIS Mock AIME 2024-2025Epoch AI | 28.1% | Epoch AI | Oct 13, 2026 |
Apps
Use Magistral Small 2509 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Magistral Small 2509 FAQ
Short answers, built from the data on this page.
Magistral Small 2509 is a model from Mistral, released on Sep 17, 2025. Magistral Small is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.
On the Respan gateway, Magistral Small 2509 costs $0.50 per 1M input tokens and $1.50 per 1M output tokens on Concentrate, after gateway discounts.
Magistral Small 2509 is served by Concentrate.
Magistral Small 2509 accepts up to 128K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "magistral-small-2509". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Magistral Small 2509 has 7 published benchmark scores, including LiveCodeBench (v5) 70.9%, GPQA Diamond 70.1%, and AIME24 (pass@1) 86.1%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.