Qwen Text live-fetched
Qwen2.5 VL 72B Instruct
Input$0.250per 1M tokens
Output$0.750per 1M tokens
- Context window
- 128,000 tokens
What that buys
- 1M words of output
- $1.00
- 100k-token chat, 80k in and 20k out
- $0.0350
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-09-02
- Changes recorded
- 0
Where this price sits
609 text models priced per 1M tokensQwen2.5 VL 72B Instruct is number 203 of 609 by price, from cheapest. The median is $2.00; Qwen2.5 VL 72B Instruct is 62% below the median. Among the 57 Qwen models in this group it is number 20 from cheapest.
Computed from the models on APITariff, checked 2026-10-15. Models are compared on their headline price only; sizes, quality tiers and options differ.
Price neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| GPT-3.5 Turbo (batch)OpenAI | OpenAI | $0.750 | source |
| Qwen3.5-35B-A3BQwen | Qwen | $0.750 | source |
| Llama 3.3 Euryale 70BSao10K | Sao10K | $0.750 | source |
Checked 2026-09-02
According to APITariff, Qwen2.5 VL 72B Instruct from Qwen costs $0.250 per 1M input tokens and $0.750 per 1M output tokens as of 2026-09-02.