All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Qwen3 8B

API ID qwen3-8b

qwen3-8b was a Qwen model.

Status
Retired
Released
—
Shutdown
Oct 10, 2026

qwen3-8b stopped serving on October 10, 2026. Recommended replacement: qwen3.6-flash.

How to migrate to Qwen3.6 Flash

Benchmarks

Scores as each source published them
or

No comparison. Pick a model to see the difference on each benchmark.

Epoch AI

BenchmarkQwen3 8BSettingRunSource
GPQA Diamond
Other settings
  • 47.5% no reasoning
56.8%Aug 27, 2026source
OTIS Mock AIME 2024-2025
Other settings
  • 22.2% no reasoning
56.1%Aug 27, 2026source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Price history

USD per 1M tokens, standard tier
$0.00$0.20$0.40$0.60$0.80Oct 2026In $0.18Out $0.70Oct 5, 2026 to Oct 12, 2026: Input $0.18, Output $0.70
$0.00$0.20$0.40$0.60$0.80Oct 2026In $0.18Out $0.70Oct 5, 2026 to Oct 12, 2026: Input $0.18, Output $0.70

We started recording this model's prices on Oct 5, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 5, 2026Input$0.18
Oct 5, 2026Output$0.70

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$0.18
output$0.70

Changelog

Changes we detected on Qwen's pages
  1. Retired

    qwen3-8b has been retired

    Info

  2. Feature changed

    qwen3-8b: Fine-tuning not supported → not supported (supported in the Beijing region only)

    Info

  3. Feature changed

    qwen3-8b: Function calling not supported → not supported (supported in the Beijing region only)

    Info

Last checked · Sources: Qwen models, Qwen deprecations, Qwen free terms