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

Qwen3 4B FP8

LLM GatewayOpen weights

Qwen3 4B FP8 by LLM Gateway 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
LLM Gateway
Context window
128K tokens
Parameters
—
Released
Apr 2025
Open weights
Yes
Frontier model
No

Compare Qwen3 4B FP8 with…

Qwen3 4B FP8 vs Mistral Nemo$0.03/1MQwen3 4B FP8 vs Qwen3 4B$0.03/1MQwen3 4B FP8 vs Ministral 3B (latest)$0.04/1MQwen3 4B FP8 vs Gemma 3 4B IT$0.05/1MQwen3 4B FP8 vs Llama 3.1 8B Instruct$0.08/1MQwen3 4B FP8 vs Mistral Small 3$0.08/1M

FAQ

How much does Qwen3 4B FP8 cost?

Qwen3 4B FP8 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 FP8's context window?

Qwen3 4B FP8 supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.

Is Qwen3 4B FP8 open weight?

Yes — Qwen3 4B FP8 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.