Qwen 2.5 72B — pricing & specs
Qwen 2.5 72B is a balanced model from Alibaba, at capability tier 4 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-05-03.
$/M-token pricing
as of 2026-05-03 · OpenRouter (lowest)What Qwen 2.5 72B costs in practice
At $0.40/M output tokens, Qwen 2.5 72B is the 2nd-cheapest of 9 priced tier-4 models in the Mintok catalog — about 39% below the tier median of $0.65/M.
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $0.760 |
| A 10K-token request (8K in / 2K out) | $0.0037 |
| 1,000 agent runs (~2K in / 500 out each) | $0.920 |
| 1M-token RAG chat session (900K cached in / 100K out) | $0.364 |
Estimated from list price (as of 2026-05-03) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- Alibaba
- Family
- Qwen
- Capability tier
- 4 / 8
- Size class
- BALANCED
- Category
- GENERAL
- Parameters
- 72B total · 72B active (MoE)
- Context window
- 131,072 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference Cerebras Cerebras WSE-3 Turbo at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 4
Same capability tier, sorted by output price — the cheaper-capable options.
- LLaMA 4 ScoutMeta$0.30/M out
- DeepSeek V4 FlashDeepSeek$0.60/M out
- GPT-4o miniOpenAI$0.60/M out
- LLaMA 4 MaverickMeta$0.65/M out
- Qwen 3 235B (MoE)Alibaba$1.82/M out
- Claude Haiku 3.5Anthropic$4/M out
FAQ
How much does Qwen 2.5 72B cost per token?
Qwen 2.5 72B costs $0.36 per million input tokens and $0.40 per million output tokens, via OpenRouter (lowest), as of 2026-05-03.
Is Qwen 2.5 72B expensive?
At $0.40/M output tokens, Qwen 2.5 72B is the 2nd-cheapest of 9 priced tier-4 models in the Mintok catalog — about 39% below the tier median of $0.65/M.
What does a typical request with Qwen 2.5 72B cost?
At list price, a 10K-token request (8K in / 2K out) with Qwen 2.5 72B costs about $0.0037, and 1,000 agent runs (~2K in / 500 out each) about $0.920.
What is Qwen 2.5 72B's context window?
Qwen 2.5 72B supports a 131,072-token context window.
What capability tier is Qwen 2.5 72B?
Qwen 2.5 72B sits at capability tier 4 of 8 on the Mintok scale (BALANCED size class).
Is Qwen 2.5 72B open-source or proprietary?
Qwen 2.5 72B is a proprietary model from Alibaba, accessed via API.
Put Qwen 2.5 72B to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.