Qwen/Qwen2.5-72B-Instruct on Deepinfra.

01Overview

Deepinfra serves Qwen/Qwen2.5-72B-Instruct at $0.360 per million input tokens and $0.400 per million output. Context window: 32K tokens. No sharer is online for it at the moment.

02Pricing

03Capabilities

Not supported: image input, extended thinking.

Anything not listed here, we don't publish for this model yet.

04Availability

No sharer is online for this model at the moment.

See what is available now, or share capacity for it yourself.

05Usage

This model has not been served through Aile yet.

06Call it

Any OpenAI- or Anthropic-compatible SDK works. Use this exact model id:

curl https://aile.sh/v1/chat/completions \
  -H "Authorization: Bearer $AILE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepinfra/Qwen/Qwen2.5-72B-Instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Quickstart · API reference

07Alternatives

Other providers serve Qwen/Qwen2.5-72B-Instruct too, at their own rates — compare every provider for Qwen/Qwen2.5-72B-Instruct.

Other models from Deepinfra:

Similar published rates elsewhere: