Qwen

Qwen3 8B

qwen/qwen3-8b

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Qwen3 8B

reasoning open weights tools

Qwen qwen/qwen3-8b

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

Input $/1M: $0.12
Output $/1M: $0.46
Context: 131K
Max output: 8K
Released: Apr 28, 2025
Modalities: text

Intelligence index5

Coding index9

Agentic index1

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Qwen3 8B
targets:
  - id: qwen3-8b
    kind: llm
    name: Qwen3 8B
    metadata:
      model: qwen/qwen3-8b          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000286

Price among Qwen models

Input list price per million tokens; Qwen3 8B is the 3rd cheapest of 13 listed.

1
Qwen3.7 Flash
$0.03
2
Qwen3.6 35B A3B
$0.10
3
Qwen3 8B
$0.12
4
Qwen3.8 Flash
$0.15
5
Qwen3.6 Flash
$0.19
6
Qwen3.5 Plus 2026-04-20
$0.30
7
Qwen3.7 Plus
$0.32
8
Qwen3.8 27B
$0.42
9
Qwen3.6 Max Preview
$1.03
10
Qwen3.7 Max
$1.48
11
Qwen3.8 Max (0902)
$2.00
12
Qwen3.8 2.4T A95B
$2.00

More from Qwen

Other models by the same vendor in the catalogue.