Qwen 2.5 72B API Pricing
Open-weight · 128K context · Available from 7 hosts. Cheapest: Novita at $0.28 input / $0.32 output per 1M tokens.
Among Alibaba's 10 open-weight models tracked here, Qwen 2.5 72B ($0.35/$0.4 per 1M tokens) is above Qwen 2.5 Coder 32B ($0.2/$0.2) and below Qwen 3 72B ($0.2/$0.6).
Qwen 2.5 72B price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.28 | $0.32 | $0.6 |
| DeepInfra | $0.2975 | $0.34 | $0.6375 |
| Groq | $0.3325 | $0.38 | $0.7125 |
| Alibaba | $0.35 | $0.4 | $0.75 |
| Together | $0.35 | $0.4 | $0.75 |
| OpenRouter | $0.35 | $0.4 | $0.75 |
| Fireworks | $0.3675 | $0.42 | $0.7875 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Qwen 2.5 72B cost calculator
Frequently asked
Qwen 2.5 72B costs $0.28 per 1M input tokens and $0.32 per 1M output tokens at its cheapest host (Novita).
Qwen 2.5 72B supports a context window of about 128K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Novita is currently cheapest at $0.28/$0.32 per 1M tokens, versus Fireworks at $0.3675/$0.42. Prices change often — use the comparison table above.