qwen

Qwen: Qwen3 8B

The Qwen3 8B is an AI model developed by qwen that can process text inputs up to 131,072 tokens in length and generate outputs of up to 8,192 completion tokens. It supports tools, reasoning, but does not have structured output capabilities. For those seeking a high-scoring model with reasonable pricing, Qwen3 8B is worth considering. At $0.117 per million input tokens and $0.455 per million output tokens, it is priced competitively. Its blended benchmark score of 19.1 across two independent benchmarks suggests that it can deliver solid performance for text-related tasks.

Open weights 8.2B parameters, about 4.6 GiB at Q4_K_M: fits comfortably on 18 of 18 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
91/100
price + capability + benchmarks
Input Price
$0.12
per 1M tokens · checked 2026-09-23
Output Price
$0.46
per 1M tokens · checked 2026-09-23
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 18.9 across 2 benchmarks, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 9.9
EQ-Bench emotional understanding in dialogue 36.8
Model ID
qwen/qwen3-8b
Vendor
qwen
Released
April 2025
Tokenizer
Qwen3
Input Modalities
text
Output Modalities
text
Max Output
8,192 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.12/M input and $0.46/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.08
A month of a busy support chatbot 5M in / 2M out $1.50

Similar models

Quick answers

How much does Qwen: Qwen3 8B cost?
$0.12 per million input tokens and $0.46 per million output tokens.
What is Qwen: Qwen3 8B's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Qwen: Qwen3 8B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Qwen: Qwen3 8B process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.