tokenstat
tokenstat

Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct · rates as of · Benchmarks · Plans · Calculator

Qwen vision-language model for visual reasoning, documents, and agent tasks

Cheapest input
$0.13
$/MTok · LiteLLM
Cheapest output
$0.4
$/MTok
Context
128K
tokens
Offers
7
3 sources

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
LiteLLMcheapestQwen/Qwen2.5-VL-72B-Instruct$0.13$0.4$0.013
LiteLLMcheapestnebius/Qwen/Qwen2.5-VL-72B-Instruct$0.13$0.4$0.013
models.devQwen/Qwen2.5-VL-72B-InstructNebius$0.25$0.75$0.025128K
models.devqwen/qwen2.5-vl-72b-instructNovita AI$0.8$0.8$033K
models.devqwen/qwen2.5-vl-72b-instructKilo Gateway$0.8$1$0.4128K
OpenRouterqwen/qwen2.5-vl-72b-instructOpenRouter$0.8$1$0.4128K
LiteLLMqwen/qwen2.5-vl-72b-instruct$0.8$0.8$0.08

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • Out: text
Knowledge cutoff: 2024-12Released: 2025-02-01Family: qwen

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