Qwen: Qwen3 4B (free)✓ Catalog verified
Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.
Overview
Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.
Access: available through the official Qwen API. Context window: 41K.
Specifications
| API identifier | qwen/qwen3-4b:free |
| Provider | Qwen |
| Model type | Text LLM |
| Context window | 41K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Apr 30, 2025 |
| Tokenizer | Qwen3 |
| Instruction format | qwen3 |
| Moderated | No |
| Architecture modality | text->text |
Pricing
Live pricing components for qwen/qwen3-4b:free as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $0 | $0.00 / 1M | Per input token |
| Completion tokens | $0 | $0.00 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | ✓ Supported | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Qwen: Qwen3 4B (free) through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="qwen/qwen3-4b:free",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| AllenAI: Molmo2 8B | Allenai | 37K | $0.20 | View → |
| AionLabs: Aion-RP 1.0 (8B) | Aion Labs | 33K | $0.80 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Qwen: Qwen3 4B (free) cost?
$0.00 per 1M input tokens and $0.00 per 1M output tokens on the official Qwen API.
What is the context window of Qwen: Qwen3 4B (free)?
Qwen: Qwen3 4B (free) supports up to 41K tokens of context.
Does Qwen: Qwen3 4B (free) support tool / function calling?
Yes, Qwen: Qwen3 4B (free) supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Qwen: Qwen3 4B (free)?
Use the official Qwen API with the model id `qwen/qwen3-4b:free`. See the Quick start section above for code examples.