Skip to content

Model Library

AlibabaReleased April 28, 2025

Qwen3 8B

Alibaba · Released April 28, 2025

View public research Browse the library

Intelligence score

5

At a glance

Intelligence
5
Speed
39.0tokens/sec
Latency
3.82stime to first token
Input price
$0.18per 1M tokens
Output price
$0.70per 1M tokens
Context window
33Ktokens
Parameters
8.19billions

Summary

Comparison summary

Qwen3 8B (Non-reasoning) scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6). Qwen3 8B (Non-reasoning) generates output at 39.0 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3 8B (Non-reasoning) costs $0.18 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.70 per 1M output tokens (somewhat higher than average, median: $0.32), based on Alibaba's API.

Specifications

Technical specifications

Model nameQwen3 8B
ProviderAlibaba
Release dateApril 28, 2025
Intelligence score5
Speed39.0 tokens/sec
Latency (TTFT)3.82s
Input price$0.18 / 1M tokens
Output price$0.70 / 1M tokens
Context window33,000 tokens
Parameters8.19B
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: qwen3-8b-instruct

Pricing

Token prices

Price per 1M tokens

Qwen3 8B, as listed in the catalog record

Input $0.18 and output $0.70 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.18
  2. Output$0.70

Model Intelligence legacy profile: qwen3-8b-instruct

FAQ · 19

Frequently asked questions

Qwen3 8B (Non-reasoning) was released on April 28, 2025.

Qwen3 8B (Non-reasoning) was created by Alibaba.

Qwen3 8B (Non-reasoning) scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6).

Qwen3 8B (Non-reasoning) generates output at 39.0 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).

Qwen3 8B (Non-reasoning) has a time to first token (TTFT) of 3.82s (based on Alibaba's API), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.54s).

Qwen3 8B (Non-reasoning) costs $0.18 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.70 per 1M output tokens (somewhat higher than average, median: $0.32), based on Alibaba's API.

Qwen3 8B (Non-reasoning) costs $0.18 per 1M input tokens and $0.70 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.23 per 1M tokens. Pricing may vary by provider.

No, Qwen3 8B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Qwen3 8B (Non-reasoning) supports text input.

Qwen3 8B (Non-reasoning) supports text output.

No, Qwen3 8B (Non-reasoning) does not support image input. It can only process text.

No, Qwen3 8B (Non-reasoning) is not multimodal. It only supports text input.

Qwen3 8B (Non-reasoning) has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Qwen3 8B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Qwen3 8B (Non-reasoning) has 8.19 billion parameters.

Qwen3 8B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.

Qwen3 8B (Non-reasoning) achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Qwen3 8B (Non-reasoning) is available via API through 2 providers.

Qwen3 8B (Non-reasoning) is available through 2 API providers.