tokenstat
tokenstat

Qwen3 8B

qwen/qwen3-8b · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.06
$/MTok · models.dev
Cheapest output
$0.06
$/MTok
Context
131K
tokens
Offers
6
2 sources

Price changes

Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ dropOutput $0.4 → $0.06
  • ↑ riseInput $0.05 → $0.06

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestQwen/Qwen3-8BSiliconFlow (China)$0.06$0.06$0131K
models.devQwen/Qwen3-8BSiliconFlow$0.06$0.06$0131K
models.devqwen/qwen3-8bKilo Gateway$0.117$0.455$0131K
OpenRouterqwen/qwen3-8bOpenRouter$0.117$0.455$0131K
models.devQwen/Qwen3-8BPioneer$0.2$0.2$0.2131K
models.devqwen/Qwen3-8BNanoGPT$0.47$0.47$041K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-03-31Released: 2025-04-28Family: qwen

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash