impulse

Qwen3.5 4B

Open weights
API id qwen3-5-4b
Input / 1M
$0.04
at EmpirioLabs AI
Output / 1M
$0.07
at EmpirioLabs AI
Context window
262K
tokens
Max output
33K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at EmpirioLabs AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.04$0.07
Cached input
50% off input
$0.02

What it costs a month

At EmpirioLabs AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$15.45
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$16.92
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$35.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$113
Use your own numbers

Where to run it

1 host serve Qwen3.5 4B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
qwen3-5-4b
$0.04 / $0.07

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Features
Prompt caching
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than EmpirioLabs AI.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Gemma3 4B
    Google · on LlamaGate
    $0.03 / $0.08
    Lacks reasoning, caching
    11% less
  • Ministral 3B
    Mistral AI · on Azure AI Foundry
    $0.04 / $0.04
    Lacks reasoning, caching
    16% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedQwen3.5 4BLatest$0.04 / $0.07
  2. UndatedQwen3 4B$0.03 / $0.03

Call it

Using EmpirioLabs AI's API.

Python
from litellm import completion

response = completion(
    model="empiriolabs/qwen3-5-4b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3.5 4B cost?

On EmpirioLabs AI, Qwen3.5 4B costs $0.04 per million input tokens and $0.07 per million output tokens. Cached input costs $0.02 per million tokens.

Which APIs offer Qwen3.5 4B?

Qwen3.5 4B runs on 1 API: EmpirioLabs AI.

What is Qwen3.5 4B's context window?

262K tokens, with up to 33K tokens in one reply.

Is Qwen3.5 4B being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Qwen3.5 4B?

No. Qwen3.5 4B is the newest model in its line.

What are cheaper alternatives to Qwen3.5 4B?

Models that cost less and keep most of what it can do: Gemma3 4B on LlamaGate (11% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Qwen3.5 4B's API model id?

Use qwen3-5-4b with EmpirioLabs AI.

Sources

Raw catalog entry for qwen3-5-4b on EmpirioLabs AI
{
  "litellm_provider": "empiriolabs",
  "mode": "chat",
  "max_input_tokens": 262144,
  "max_output_tokens": 32768,
  "input_cost_per_token": 4e-8,
  "output_cost_per_token": 7e-8,
  "cache_read_input_token_cost": 2e-8,
  "supports_system_messages": true,
  "supports_vision": true,
  "supports_reasoning": true,
  "supports_prompt_caching": true,
  "supports_function_calling": true,
  "supports_response_schema": true,
  "source": "https://empiriolabs.ai/models/qwen3-5-4b"
}