Most AI tasks no longer need a frontier model Read launch post

Qwen3.5 4B

An open language model that answers prompts and follows your instructions. Qwen/Qwen3.5-4B

  • Accuracy

    59.3%

    MMLU-Pro, answers right

  • Time per request

    Not timed one request at a time

  • Serverless price

    $0.305 in · $1.53 out

    per 1M tokens

Call it

from sie_sdk import SIEClient
​
client = SIEClient(api_key="API keysk-sie-…")
​
messages = [
{"role": "user", "content": "textSummarize this standup in one line and flag any blocker: 'Finished the encoder migration, moved on to reranking, blocked on missing GPU quota.'"},
]
result = client.chat_completions(
"modelQwen/Qwen3.5-4B",
messages,
max_completion_tokens=max tokens256,
extra_body={"temperature":0,"presence_penalty":0},
)
print(result["choices"][0]["message"]["content"])
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient(undefined, { apiKey: 'sk-sie-…' });

const result = await client.chatCompletions({
  model: 'Qwen/Qwen3.5-4B',
  messages: [
    { role: 'user', content: "Summarize this standup in one line and flag any blocker: 'Finished the encoder migration, moved on to reranking, blocked on missing GPU quota.'" },
  ],
  max_completion_tokens: 256,
  temperature: 0,
  presence_penalty: 0,
});
console.log(result.choices[0]?.message.content);
curl https://api.superlinked.com/v1/chat/completions \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"model\":\"Qwen/Qwen3.5-4B\",\"messages\":[{\"role\":\"user\",\"content\":\"Summarize this standup in one line and flag any blocker: 'Finished the encoder migration, moved on to reranking, blocked on missing GPU quota.'\"}],\"max_completion_tokens\":256,\"temperature\":0,\"presence_penalty\":0}"
Build the "Chat" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3.5-4B (OpenAI-compatible endpoint: /v1/chat/completions). Keep the model id configurable.

Task
- Input: a block of text.
- Behaviour: return the model’s answer to the prompt
- Send one POST /v1/chat/completions request (SDK: chat_completions / chatCompletions) with an optional system message for instructions, the user's text as the user message, and max_completion_tokens 256, temperature 0, presence_penalty 0. Read the answer from choices[0].message.content.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Next to the other language models

Next to the other language models
Model MMLU-Pro, answers right Time per request Serverless price Size
Qwen3.8 27B Qwen Tool calling Not measured 0.74 s per complete reply $0.25 in · $2.75 out per 1M tokens 27.8B
GLM-5.3-Flash zai-org Tool calling Not measured Not timed $0.15 in · $0.50 out per 1M tokens 321.3B
Gemma 4 31B google Tool calling Not measured Not timed $0.45 in · $1.50 out per 1M tokens 31.3B
Qwen3 4B Instruct 2507 Qwen 53.3% Not timed Run in your cloud 4.0B
All 11 chat and document models

Measured on public datasets

Measured on public datasets
Dataset Accuracy
MedQA Measured internally 69.3%
MMLU-Pro Measured internally 59.3%
CaseHOLD Measured internally 58.0%
GPQA Diamond Measured internally 47.5%

Facts

Size
4.7B parameters
License
Apache-2.0
Reads
Text (up to 8,192 tokens), image
Endpoint
generate
Evaluation
Accuracy
Run on SIE against the public dataset named in each figure
Time
SIE timed on a GPU server with the client alongside, one request at a time
Prices
Serverless list prices, effective 10 Nov 2026

Run Qwen3.5 4B on Serverless or in your own cloud

SIE Cluster

Kubernetes in your own cloud, backed by our engineers.

  • Terraform modules for your cloud
  • Apache-2.0, same engine as Serverless
  • GPU workers scale to zero between jobs
  • Separate worker pools for each tenant
Agent prompt Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment.

SIE Local

The open-source server on your own machine.

  • NVIDIA GPU
  • One container, no cluster
  • Process your data fully offline
  • Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-sglang

Talk to us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.