Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.
What Ministral 3 3B costs to run
Test Ministral 3 3B
with Gateway’s Simulator
See a prompt's output, token spend, latency, and more with Ministral 3 3B.
Route requests to Ministral 3 3B in minutes
1$ pip install merge-gateway-sdk1from 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)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)1from openai import OpenAI
2
3client = OpenAI(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/openai",
6)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)1npm install merge-gateway-ai-sdk-provider ai1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4 apiKey: "YOUR_API_KEY",
5});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);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 unchanged1from 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
Ministral 3 3B FAQ
Heading
What other models does Mistral AI offer?
Mistral AI ships small edge models alongside general-purpose, coding, and reasoning lines. Here are some other models Mistral AI supports:
- Ministral 3 8B: the mid-size edge model in the same line, with more capability than the 3B tier
- Ministral 3 14B: the largest edge model in the line, for on-device tasks that need the most headroom
- Mistral Small: a compact, open-weight general model that sits above the Ministral edge tier
- Mistral Nemo: a small, open-weight 12B model for affordable, self-hostable inference
- Mistral Medium 3.5: the mid-tier general model, balancing quality and cost with multimodal input
How does Ministral 3 3B differ from Mistral AI's other models?
Ministral 3 3B is the smallest model in Mistral's edge-focused line, built for the most resource-constrained on-device deployments.
- Edge focus: designed to run on constrained hardware with minimal latency, unlike the larger hosted-first general models
- Size: the 3B tier is the lightest Ministral option, below the 8B and 14B models, prioritizing footprint over capability
- Capabilities: supports function calling for its class, which suits simple agentic tasks at the edge
- Position vs Mistral Small: far narrower general-purpose breadth than Small, traded for the smallest possible footprint
Reach for Ministral 3 3B when footprint and latency matter most and the task is focused enough that a 3B model can handle it.
What models should I consider using alongside Ministral 3 3B?
No single model is optimal for every task. Here are models worth pairing with Ministral 3 3B depending on what your product needs:
- Ministral 3 8B as the step up within the edge line when 3B runs short on capability
- Mistral Small for general-purpose tasks that need more breadth than an edge model provides
- Claude Opus 4.8 for the hardest reasoning or coding tasks that need frontier quality in the cloud
- Gemini 3.5 Flash for high-volume, low-cost cloud multimodal tasks
- Mistral Nemo as another small, open-weight model to benchmark against
What are the challenges of using Ministral 3 3B in my product?
Like any production LLM, Ministral 3 3B comes with tradeoffs worth planning for:
- Quality ceiling: as the smallest model in the line, it has the lowest capability ceiling, so keep tasks focused and plan an escalation path
- Deployment operations: running it on-device means owning packaging, updates, and hardware constraints
- Provider dependency: if you use the hosted version, relying only on Mistral is fragile during outages or retirements
- Cost at scale: very cheap per token, but high volumes still compound, so budgeting stays relevant
- Task fit: built for simple, focused tasks, so route anything complex to a larger model rather than pushing 3B past its range
Why should I use Merge Gateway to route LLM requests with Ministral 3 3B and every other model?
Using Ministral 3 3B through Merge Gateway gives you access to the model itself and the infrastructure layer around it:
- One API, every provider: Reach Ministral 3 3B and every other major LLM through a single endpoint and API key, swapping the model string to change providers without touching application code
- Intelligent routing and automatic failover: Merge routes around Mistral outages automatically, and a 3B-to-larger-model quality ladder is easy to express as a policy that can cut spend 40 to 60%
- Cost governance: Set hard or soft project budgets so spend stays in plan, with every request attributed to a model, project, and tag in one billing dashboard
- Build Your Own Router: Define what "best" means with curated benchmarks or your own evals, and the router keeps easy tasks on 3B and escalates only when needed
- Security and compliance controls: Apply DLP rules and prompt injection protection before requests reach Mistral, and enforce per-project model and region policies outside your application
How can I start routing requests to Ministral 3 3B via Merge Gateway?
Getting Ministral 3 3B 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 Ministral 3 3B, the model string is mistral/ministral-3b-2512 (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 Ministral 3 3B as primary with one fallback.
Full setup instructions and SDK references are in the Merge Gateway docs.
Try Ministral 3 3B through Merge Gateway
Route, observe, and control AI requests across providers from one API.
