Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.
How Magistral Small 1.2 performs*
Intelligence - general reasoning and knowledge
11
Coding - code generation and problem-solving
15
What Magistral Small 1.2 costs to run
| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention |
| --- | ---: | ---: | --- |
| Amazon Bedrock | $0.5000 | $1.50 | Yes |
| Mistral | $0.5000 | $1.50 | No |
Test Magistral Small 1.2
with Gateway’s Simulator
See a prompt's output, token spend, latency, and more with Magistral Small 1.2.
Route requests to Magistral Small 1.2 in minutes
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1$ pip install merge-gateway-sdkSend a request
Python
1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6 model="openai/gpt-5.2",
7 input=[
8 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10 ],
11)
12
13print(response.output[0].content[0].text)Try a diffrent model
Swap the model string to route to a different provider. No other code changes needed.
Anthropic
1response = client.responses.create(
2 model="anthropic/claude-sonnet-4-20250514",
3 input=[
4 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)Point to Gateway
Python
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/openai",
6)Send a request
Use the standard chat.completions.create method. No provider prefix needed on the model name.
Python
1response = client.chat.completions.create(
2 model="gpt-5.2",
3 messages=[
4 {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)
8
9print(response.choices[0].message.content)Install packages
1npm install merge-gateway-ai-sdk-provider aiCreate the provider
TypeScript
1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4 apiKey: "YOUR_API_KEY",
5});Send a request
Use generateText to send a request. Model names use the provider/model format.
TypeScript
1import { generateText } from "ai";
2
3const { text } = await generateText({
4 model: gateway("openai/gpt-4o"),
5 prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:
TypeScript
1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4 apiKey: "YOUR_API_KEY",
5 baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchangedInstall the Merge Gateway SDK
Anthropic SDK
1from anthropic import Anthropic
2
3client = Anthropic(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9 model="claude-sonnet-4-20250514",
10 max_tokens=1024,
11 messages=[
12 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13 ],
14)
15
16print(message.content[0].text)Explore other models available in Merge Gateway
Magistral Small 1.2 FAQ
If you have more questions about Magistral Small 1.2, we've covered a few more below. The details here reflect what was known in July, 2026 and are subject to change.
Heading
What other models does Mistral AI offer?
Mistral AI ships a reasoning line alongside general-purpose, coding, and small edge models. Here are some other models Mistral AI supports:
- Magistral Medium 1.2: the larger reasoning model in the same line, for the most demanding chain-of-thought work
- Mistral Large: the high-end general-purpose model for demanding reasoning and generation
- Mistral Medium 3.5: the mid-tier general model, balancing quality and cost with multimodal input
- Mistral Small: a compact, open-weight general model for high-volume, cost-sensitive tasks
- Codestral: the coding-specialized model for code generation and completion
How does Magistral Small 1.2 differ from Mistral AI's other models?
Magistral Small 1.2 is the compact model in Mistral's reasoning line, tuned to think step by step rather than answer in one pass.
- Reasoning focus: applies explicit chain-of-thought for multi-step, analytical, and multilingual problems, unlike the general-purpose Mistral models
- Size and licensing: a small, open-weight model you can self-host and fine-tune, which the larger hosted-first models don't offer
- Multimodal input: the 1.2 line accepts image input alongside text, broadening it beyond text-only reasoning
- Position vs Magistral Medium 1.2: lower cost and smaller, trading some peak reasoning quality for efficiency
Reach for Magistral Small 1.2 when you want transparent, step-by-step reasoning on a small, self-hostable model rather than a general chat model.
What models should I consider using alongside Magistral Small 1.2?
No single model is optimal for every task. Here are models worth pairing with Magistral Small 1.2 depending on what your product needs:
- Magistral Medium 1.2 as the escalation path within the reasoning line when the small tier's ceiling isn't enough
- Claude Opus 4.8 for the hardest reasoning or coding problems that need frontier quality
- DeepSeek V4 Pro as another strong reasoning model to benchmark against on your problems
- Mistral Small for the routine, non-reasoning steps where chain-of-thought is unnecessary overhead
- Gemini 3.1 Pro for long-context reasoning over large documents
What are the challenges of using Magistral Small 1.2 in my product?
Like any production LLM, Magistral Small 1.2 comes with tradeoffs worth planning for:
- Reasoning verbosity: it generates thinking tokens before the final answer, which raises latency and token counts for simple requests
- Quality ceiling: as a small model, it trails larger reasoning models on the hardest problems, so plan an escalation path
- Task fit: reasoning mode is overkill for classification or short extraction, so route those to a general model
- Self-host operations: running the open weights yourself means owning deployment, scaling, and upkeep
- Provider dependency: relying only on Mistral is fragile during outages or model retirements
Why should I use Merge Gateway to route LLM requests with Magistral Small 1.2 and every other model?
Magistral Small 1.2 through Merge Gateway comes with the control layer around the model, not just the model:
- One API, every provider: Access Magistral Small 1.2 and every other major LLM behind one endpoint and key, changing models by editing a string instead of your code
- Intelligent routing and automatic failover: Merge reroutes around Mistral outages automatically, and a small-to-larger reasoning ladder is easy to express as a policy that can cut spend 40 to 60%
- Cost governance: Keep reasoning traffic on budget with project caps, and attribute every request by model, project, and tag in one dashboard
- Build Your Own Router: Weight your own evals so the router keeps routine tasks off the reasoning model and escalates only when needed, explaining each pick
- Security and compliance controls: Enforce DLP, prompt injection protection, and per-project region rules before any request reaches Mistral
How can I start routing requests to Magistral Small 1.2 via Merge Gateway?
Getting Magistral Small 1.2 running through Merge Gateway takes a few minutes:
1. Create an account and get your API key from the dashboard.
2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.
3. Make your first request using the provider/model format. For Magistral Small 1.2, the model string is mistral/magistral-small-2509 (confirm the exact slug in the dashboard). Swap the model string to route to any other provider without changing anything else.
4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming Magistral Small 1.2 as primary with one fallback.
Full setup instructions and SDK references are in the Merge Gateway docs.
Try Magistral Small 1.2 through Merge Gateway
Route, observe, and control AI requests across providers from one API.
