Qwen2 72B Instruct

Open weights

Qwen2 72B Instruct is a language model from Togethercomputer with a 32K-token context window. Provider list price is $0.90 per million input tokens and $0.90 per million output; on Allocate you pay $0.96 and $0.96 with the 7% transaction fee. The weights are open under Qwen license, so you can fine-tune it and own the result.

Route Qwen2 72B Instruct Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.90$0.96

Output, per M tokens$0.90$0.96

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

Qwen3 Next 80B A3b Instruct$0.15$1.50

Qwen3 Next 80B A3b Thinking$0.15$1.50

Qwen3 Coder Next Fp8$0.50$1.20

Deepseek Coder 33B Instruct$0.80$0.80

Meta Llama 3 70B Instruct Turbo$0.88$0.88

Meta Llama 3.1 70B Instruct Turbo$0.88$0.88

Llama 3.1 Nemotron 70B Instruct HF$0.88$0.88

Qwen2 72B Instruct$0.90$0.90

InputOutput

Provider list prices per M tokens, Qwen2 72B Instruct against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.90 + 350 × $0.90 = $1,395 a month. Billed on Allocate it is $1,493 with the 7% transaction fee.

Qwen2 72B Instruct is an open-weights model under the Qwen license license. Read the license terms once before you build on it; fine-tuned weights on Allocate stay inside your boundary.

Example usage

Point a route at qwen/qwen2-72b-instruct and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "qwen/qwen2-72b-instruct",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · qwen/qwen2-72b-instruct · inside your boundary

Common questions

How much does Qwen2 72B Instruct cost per million tokens?

Provider list price is $0.90 per million input tokens and $0.90 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.96 in and $0.96 out.

What context window does Qwen2 72B Instruct have?

32,768 tokens (32K). At roughly 0.75 words per token, that is about 25k words of English text per request.

Can I fine-tune Qwen2 72B Instruct?

Yes. Qwen2 72B Instruct is an open-weights model under the Qwen license license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call Qwen2 72B Instruct on Allocate?

Send qwen/qwen2-72b-instruct in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.