Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Qwen3 4B

NovitaAIOpen weights

Qwen3 4B by NovitaAI costs $0.03 per 1M input tokens and $0.03 per 1M output tokens, with a 128K-token context window.

Pricing

Input (per 1M tokens)
$0.03
Output (per 1M tokens)
$0.03
Cached input (per 1M)
—

Specifications

Provider
NovitaAI
Context window
128K tokens
Parameters
—
Released
Apr 2025
Open weights
Yes
Frontier model
No

Benchmarks

GPQA Diamond
52.3

Compare Qwen3 4B with…

Qwen3 4B vs ERNIE-4.5-21B-A3B-Thinking$0.28/1MQwen3 4B vs ERNIE 4.5 300B A47B$1.10/1MQwen3 4B vs ERNIE-4.5-VL-28B-A3B-Thinking$0.39/1MQwen3 4B vs L31 70B Euryale V2.2$1.48/1MQwen3 4B vs Qwen2.5 VL 72B Instruct$0.80/1MQwen3 4B vs Qwen3 30B A3B$0.45/1M

FAQ

How much does Qwen3 4B cost?

Qwen3 4B is priced at $0.03 per 1M input tokens and $0.03 per 1M output tokens. Output tokens cost more than input.

What is Qwen3 4B's context window?

Qwen3 4B supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.

Is Qwen3 4B open weight?

Yes — Qwen3 4B has openly available weights.

Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.