ZMIME
Alibaba (Qwen) · Released Apr 28, 2025

Qwen3 8B

Qwen instruction model for multilingual chat, reasoning, and tool use.

  • Open weights
  • Reasoning
  • Tool calling
Capability
136.2ECI · #113 of 148
Input
$0.18per 1M tokens
Output
$0.70per 1M tokens
Context
131K8K max output
Pricing

What it costs

Input
$0.18per million tokens
Output
$0.70per million tokens
Blended (3:1)
$0.31cheaper than 70% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.71
Team assistant25M input + 5M output tokens$8.00
Production app250M input + 50M output tokens$80.00

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

136.2Epoch Capabilities Index
#113 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (129.7–138.1); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions56.8%
  • OTIS Mock AIME 2024–2025Competition mathematics56.1%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Apr 28, 2025
Knowledge cutoff
Apr 2025
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text
Output
Text
Reasoning
Thinking budget
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
qwen3-8bon Alibaba
Availability
1 API providerlisted on models.dev

Alibaba model documentation

Same lab

More from Alibaba (Qwen)

Questions

About Qwen3 8B

How much does Qwen3 8B cost?

Qwen3 8B costs $0.18 input / $0.70 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.31 per million tokens, cheaper than 70% of the 360 priced models we track.

What is the context window of Qwen3 8B?

Qwen3 8B accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.

How good is Qwen3 8B?

Epoch AI gives Qwen3 8B a Capabilities Index score of 136.2 (likely range 129.7–138.1), ranking it #113 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 56.8%, OTIS Mock AIME 2024–2025 56.1%.

Is Qwen3 8B open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen3 8B support?

Qwen3 8B accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Qwen3 8B released?

Alibaba (Qwen) released Qwen3 8B on Apr 28, 2025. Its training data runs to Apr 2025.

What are the best alternatives to Qwen3 8B?

The closest current models from other labs on capability, price and release date are DeepSeek V3 0324 (DeepSeek, ECI 135.9, $0.24 / $0.90), GPT-4.1 mini (OpenAI, ECI 135.0, $0.40 / $1.60), Gemini 2.5 Flash-Lite (Google, ECI 133.9, $0.10 / $0.40) and Llama 4 Maverick 17B Instruct (Meta, ECI 132.2, $0.321 / $0.91).