API pricing per million tokens
qwen2-5-vl-72b-instruct Open weightsChecked 6h ago
- Input
- $0.8
- per 1M, Parasail (fp8)
- Output
- $1
- per 1M tokens
- Cached input
- $0.4
- no batch tier listed
- Context
- 128K
- 115K max output
Where to buy it (1)
Parasailfp8, fp8$0.8 / $1cached $0.4
Through a gateway
Your own numbers100M input and 20M output tokens a month: $100.00 direct.
Helicone$100.00+0%
Kong AI Gateway$100.00+0%
LiteLLM$100.00+0%
Vercel AI Gateway$100.00+0%
AWS Bedrock$100.00+0%
Azure AI Foundry$100.00+0%
Google Vertex AI$100.00+0%
Databricks Mosaic AI$100.00+0%
Hugging Face Inference$100.00+0%
Cloudflare AI Gateway$105.00+5%
Requesty$105.00+5%
Eden AI$105.50+5.5%
OpenRouter$105.50+5.5%
Snowflake Cortex AI$120.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Qwen3.8 Max PrimeQwen (Alibaba) · 1M$4 / $12in / out per 1M$4$12$0.51MSep 23, 2026
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About Qwen2.5 VL 72B Instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.
Takes text, image in and returns text. First listed Sep 23, 2026. Blended price $0.85 per 1M tokens at 3 input to 1 output.
Across fru.devCompany profile
Questions
How much does Qwen2.5 VL 72B Instruct cost?
$0.8 per million input tokens and $1 per million output tokens, with cached input at $0.4.
What is the context window of Qwen2.5 VL 72B Instruct?
128K tokens, with up to 115K tokens of output.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.