← Back to the index

Qwen2.5 72B Instruct

qwen/qwen-2.5-72b-instruct

Provider (catalogue)
qwen
Weights
Open
Context
33K
Tokenizer
Qwen

Price components

Input
Output
Reasoning output—
Cache read—
Cache write (5m)—
Cache write (1h)—
Image input—
Audio input—
Audio output—
Web search call—
Per request—
Blended at 3:1$0.370

Not known for this model

  • Measured output tokens/sec and TTFT: no redistributable measurement source is ingested.
  • Per-provider dispersion: only the catalogue-level listing is ingested so far, so provider-to-provider price and speed spread is not shown.
  • Price history: no persistent store yet, so this is a point-in-time observation.

Catalogue entry last fetched 8m ago.