Qwen2.5 72B Instruct API pricing
Alibaba · Budget price tier · Qwen · released 2024-09. Prices in USD per 1 million tokens. Data snapshot: 2026-10-22.
Qwen2.5 72B Instruct has held the same list price since 2026-10-18 and is the 79th cheapest of 164 models in the Budget price tier. Only one host, DeepInfra, sells it, so there is no second price to shop. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.36 per 1M tokens
- Output: $0.40 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 33K tokens
- Arena ELO: 1303 as of 2026-10-08
Market position
On blended price ($0.388 per 1M tokens at 30% input, 70% output) it is cheaper than 52% of models in the Budget price tier: 79th cheapest of 164. Across every price tier it is cheaper than 75% of priced text models in the catalogue: 79th cheapest of 308. Its Arena ELO of 1303 ranks 142nd of the 156 models that carry one, tied with 2 others, above 8% of them. With an Arena score of 1303, Qwen2.5 72B Instruct sits below OptimNow's lowest working quality threshold, Standard (Arena 1415+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. Each threshold is a distance below the best ranked model, which scores 1525 on Arena scores as of 8 Oct 2026.
Licence, size and capabilities
Qwen2.5 72B Instruct is open weights, which is not the same as open source: the weights are published, but under Qwen, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 72B parameters. Listed capabilities: Text, Agents. Filling its 33K context window once costs $0.0119 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
DeepInfra is the only host with a published rate, $0.36 input / $0.40 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra (price we quote) | $0.36 | $0.40 | fp8 |
List prices as published on 2026-10-22, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Alibaba publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $74 |
| Knowledge Q&A | 2,000 / 800 | $104 |
| Meeting Summary | 10,000 / 1,200 | $408 |
| Marketing Content | 2,500 / 1,800 | $162 |
| Coding Task | 3,000 / 2,000 | $188 |
| Invoice Processing | 1,500 / 600 | $78 |
| Call Summary | 2,000 / 700 | $100 |
| Agent Workflow | 6,000 / 3,000 | $336 |
Price history
Qwen2.5 72B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.36 input / $0.40 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
Alternatives to Qwen2.5 72B Instruct
- Next cheaper model in the Budget price tier: Qwen3 30B A3B (Alibaba) at $0.386 blended, 1% less.
- Next more expensive: Nemotron 3.5 Super VL (Nvidia) at $0.395 blended, 2% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Qwen2.5 72B Instruct.
- Mistral Small 3.1 24B (Mistral): $0.351 in / $0.555 out per 1M, Arena ELO 1303 (27% more expensive, same Arena ELO)
- Gemma 3 4B (Google): $0.04 in / $0.05 out per 1M, Arena ELO 1303 (88% cheaper, same Arena ELO)
- Llama 3.1 70B Instruct (Meta): $0.40 in / $0.40 out per 1M, Arena ELO 1293 (3% more expensive, 10 ELO points lower)
- Nemotron 3 Nano 30B A3B (Nvidia): $0.06 in / $0.24 out per 1M, Arena ELO 1314 (52% cheaper, 11 ELO points higher)
- Cheapest within 15 Arena points: Gemma 3 4B (Google), 88% cheaper, same Arena ELO, out of 11 models in that band.
- Highest Arena ELO within 20% of this price: Hy3 (Tencent), 5% more expensive, 151 ELO points higher, out of 13 models in that price band.
Other models from Alibaba
The 8 nearest to Qwen2.5 72B Instruct in price, of 41 other Alibaba models in the catalogue. Prices per 1M tokens, input then output.
- Qwen3 30B A3B Instruct 2507: $0.09 / $0.30
- Qwen3.8 Flash: $0.15 / $0.47
- Qwen3.8 Omni Flash: $0.15 / $0.47
- Qwen3 30B A3B: $0.12 / $0.50
- Qwen3 235B A22B Instruct 2507: $0.09 / $0.55
- Qwen3 VL 30B A3B Instruct: $0.15 / $0.60
- Qwen3 Coder Next: $0.12 / $0.80
- Qwen3 VL 8B Instruct: $0.25 / $0.75
All 42 Alibaba models and prices
Common questions about Qwen2.5 72B Instruct pricing
- How much does Qwen2.5 72B Instruct cost?
- Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens at DeepInfra, the host whose rate we quote. DeepInfra serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-10-22.
- Which host is cheapest for Qwen2.5 72B Instruct?
- DeepInfra is the only host with a published rate, $0.36 input / $0.40 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model. Host rates as listed on 2026-10-22.
- Does Qwen2.5 72B Instruct offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Qwen2.5 72B Instruct as of 2026-10-22.
- What would Qwen2.5 72B Instruct cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $74 on Qwen2.5 72B Instruct at the list price quoted on 2026-10-22.
- Can Qwen2.5 72B Instruct be self-hosted?
- Yes, within the terms of its licence. Qwen2.5 72B Instruct is open weights, which is not the same as open source: the weights are published, but under Qwen, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Qwen2.5 72B Instruct changed?
- Qwen2.5 72B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.36 input / $0.40 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server