Magistral Small 2509 API: Amazon Bedrock (US)'s chat / LLM model, one key away
Magistral Small 2509 via the ApexApi gateway
Mistral's reasoning model, the 24B Magistral Small 1.2 (2509). It thinks through the problem before answering, with a 128K window, vision and tool calling, at the same per-token price as Mistral Large 3. Pick it over Ministral when the task needs multi-step reasoning rather than a fast completion. Call it through ApexApi's unified, OpenAI-compatible API with one `ak-` key, alongside every other model in the catalog. It supports a 131,072-token context window, tool / function calling, image (vision) input, and streaming responses. Pricing is $0.60 input and $1.80 output per 1M tokens, billed pay-per-use from your credit balance with no subscription.
Magistral Small 2509 is served through ApexApi's unified, OpenAI-compatible API. One key, one format, with smart routing and automatic failover. Provider: Amazon Bedrock (US).
Why Magistral Small 2509
131,072-token context
Reason over long documents, codebases, and multi-turn history in a single request.
Tool & function calling
Structured outputs and tool orchestration for agentic and automation workloads.
Vision input
Send images alongside text for document, UI, and visual-understanding tasks.
Specifications
- Modality
- chat
- Context window
- 131.1K tokens
- Max output
- 41.0K tokens
- Streaming
- Yes
- Tool / function calling
- Yes
- Vision input
- Yes
Magistral Small 2509 pricing
- A million tokens in and a million out costs $2.40 here, all-in.
- That makes it the 24th cheapest of the 77 chat models we serve, ranked on output price.
- For lighter work, Ministral 3 3B 2512 from the same maker costs 15.0× less — one string apart on the same key.
Getting started with Magistral Small 2509
OpenAI-compatible. Point your client at ApexApi, swap your key, and call it. No new SDK to learn.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apexapi.dev/v1",
api_key="<YOUR_APEXAPI_KEY>",
)
response = client.chat.completions.create(
model="mistralai/magistral-small-2509",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Magistral Small 2509 use cases
What teams build with Magistral Small 2509 on ApexApi.
Agents & automation
Tool-using agents that orchestrate multi-step workflows and call APIs.
Coding assistants
Code generation, refactoring, reviews, and multi-file reasoning.
RAG & knowledge apps
Summarization and long-document Q&A grounded in your own data.
Magistral Small 2509 vs other models
How it compares, and on ApexApi you can switch between any of them with a single string change, same key, same endpoint.
Magistral Small 2509 vs Claude Opus 4.7
Compare Magistral Small 2509 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Claude Opus 4.7 API →Magistral Small 2509 vs GPT-5.5
Compare Magistral Small 2509 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about GPT-5.5 API →Magistral Small 2509 vs Gemini 3.1 Pro Preview
Compare Magistral Small 2509 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Gemini 3.1 Pro Preview API →Magistral Small 2509 API: FAQ
How do I call Magistral Small 2509 through ApexApi?
Create an ApexApi key, point your client at https://api.apexapi.dev/v1, and POST to /v1/chat/completions with the model set to `mistralai/magistral-small-2509`. The API is OpenAI-compatible, so an existing OpenAI SDK works once you change the base URL and key.
How much does Magistral Small 2509 cost on ApexApi?
$0.60 per million input tokens and $1.80 per million output tokens, all-in with no separate platform fee. You buy credits and pay per call, with no subscription or minimum.
What is the context window for Magistral Small 2509?
131,072 tokens. It can return up to 40,960 tokens in a single response.
Does Magistral Small 2509 support tool calling and image input?
Magistral Small 2509 supports tool / function calling, image (vision) input, and streaming responses.
What should I use instead of Magistral Small 2509?
From the same maker, Codestral 2508 costs less for lighter work. Switching is one string: it runs on the same endpoint and the same key, so there is nothing to re-integrate.
Ready to build with Magistral Small 2509?
One API key. Every major AI model. Pay only for what you use.
Get your API key, free to start