Qwen2.5-72B-Instruct
Qwen2.5-72B-Instruct is worth evaluating for coding, rag, and long context when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and long context
- Workloads that can use a 128k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Family
- Qwen2.5
- Released
- 2024-06-07
- Context
- 128k
- Parameters
- 72.7B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 7 routes · SiliconFlow
About
Instruction-optimized flagship variant for demanding production applications requiring high-accuracy complex problem-solving across industries.
Qwen2.5-72B-Instruct is an open-source model in the Qwen2.5 family. The structured metadata tracks a 128k-token context window and structured outputs. This page tracks provider routes through DeepInfra, OpenRouter, Fireworks AI, and 4 more, with the cheapest tracked route listed at $0.18 input and $0.54 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 38.4, HellaSwag 95.6, and HumanEval 86.6.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ B1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 7Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| SiliconFlow | $0.280 | $0.280 | Serverless |
| DeepInfra | $0.360 | $0.400 | Serverless |
| OpenRouter | $0.360 | $0.400 | Serverless |
| Novita AI | $0.380 | $0.400 | Serverless |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(5)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 38.4 | diamondObserved 2024-09-01 | — | Source |
| HellaSwag | 95.6 | standardObserved 2026-03-06 | — | Source |
| HumanEval | 86.6 | pass@1Observed 2024-09-01 | — | Source |
| Massive Multitask Language Understanding | 88.2 | 5-shotObserved 2026-03-06 | — | Source |
| Chatbot Arena | 1270.0 | —Observed 2026-04-15 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Compare Qwen2.5-72B-Instruct with other models
- Qwen2.5-72B-Instruct vs Llama 3.3 70B Instruct (free)1K
- Qwen2.5-72B-Instruct vs Llama 3.3 70B859
- Qwen2.5-72B-Instruct vs Qwen3.6-27B706
- Qwen2.5-72B-Instruct vs DeepSeek R1522
- Qwen2.5-72B-Instruct vs Llama 3 70B Instruct461
- Qwen2.5-72B-Instruct vs DeepSeek V4 Flash289
- Qwen2.5-72B-Instruct vs DeepSeek V4 Pro221
- Qwen2.5-72B-Instruct vs GPT-5.5166
Comparison and alternatives
Browse all comparisons →Show all 23 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Qwen2.5-72B-Instruct?
Qwen2.5-72B-Instruct has a context window of 128k tokens.
How much does Qwen2.5-72B-Instruct cost?
Qwen2.5-72B-Instruct pricing ranges from $0.18/1M to $1.3/1M input tokens depending on the provider.
When was Qwen2.5-72B-Instruct released?
Qwen2.5-72B-Instruct was released on 2024-06-07.
Which providers offer Qwen2.5-72B-Instruct?
Qwen2.5-72B-Instruct is available from 7 providers: DeepInfra, OpenRouter, Fireworks AI, Novita AI, Chutes AI, SiliconFlow, Replicate API.
What benchmarks has Qwen2.5-72B-Instruct been tested on?
Qwen2.5-72B-Instruct has been evaluated on 5 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding, Chatbot Arena.
Cheapest of 7 routes · SiliconFlow