Skip to content
Toolsummary LLM price ledger

Qwen 2.5 72 B Instruct Turbo pricing

Source: litellm · updated 2026-11-17

Short answer: Qwen 2.5 72 B Instruct Turbo costs $1.20 per million input tokens and $1.20 per million output tokens. That is a 3:1 blended rate of $1.20 per million tokens, ranking it #572 of 823 tracked models by input price.
Input / 1M
$1.20
Output / 1M
$1.20
Output ÷ input
1.00×
Context window
131,072

Price breakdown

MetricUSD
Input, per 1M tokens$1.20
Output, per 1M tokens$1.20
Output ÷ input multiple1.00×
3:1 blended, per 1M tokens$1.20
Context window131,072 tokens
Vendortogether_ai

What a typical workload costs

Monthly volumeInput costOutput costTotal
1M in / 250K out$1.20$0.300$1.50
10M in / 2.5M out$12.00$3.00$15.00
100M in / 25M out$120$30.00$150

Other together_ai models

ModelInputOutput
Qwen 2 1.5 B Instruct$0.020$0.020
Trinity Mini$0.045$0.150
Nvidia Nemotron Nano 9 B$0.060$0.250
Qwen 2 1.5 B Instruct$0.100$0.100
Nvidia Nemotron 3.5 Super VL$0.150$0.500

Cheaper alternatives

Next cheaper option: DeepSeek V4 Pro 0813 at $0.111 per 1M input tokens. Next step up: Qwq Plus at $0.800 per 1M input tokens.


Spotted a price that is out of date? Submit a correction.