Qwen2.5-14B-Instruct
Qwen2.5-14B-Instruct is worth evaluating for rag, long context, and classification when its provider route and context window match the workload.
Use it for
- Teams evaluating rag, long context, and classification
- Workloads that can use a 128k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Family
- Qwen2.5
- Released
- 2024-06-07
- Context
- 128k
- Parameters
- 14.7B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 3 routes · SiliconFlow
About
Instruction-optimized 14B variant for complex queries requiring nuanced responses and strong multilingual support.
Qwen2.5-14B-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, Fireworks AI, and SiliconFlow, with the cheapest tracked route listed at $0.08 input and $0.08 output per 1M tokens. Headline tracked benchmarks include Massive Multitask Language Understanding 84.2.
Top use-case fit
RAG
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Classification
Q/$ A1 relevant benchmark in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| SiliconFlow | $0.080 | $0.080 | Serverless |
| DeepInfra | $0.100 | $0.100 | Serverless |
| Fireworks AI | $0.200 | $0.200 | Serverless |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Classification
Benchmark scores(1)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Massive Multitask Language Understanding | 84.2 | 5-shotObserved 2026-03-06 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Compare Qwen2.5-14B-Instruct with other models
Comparison and alternatives
Browse all comparisons →Frequently asked questions
What is the context window of Qwen2.5-14B-Instruct?
Qwen2.5-14B-Instruct has a context window of 128k tokens.
How much does Qwen2.5-14B-Instruct cost?
Qwen2.5-14B-Instruct pricing ranges from $0.08/1M to $0.2/1M input tokens depending on the provider.
When was Qwen2.5-14B-Instruct released?
Qwen2.5-14B-Instruct was released on 2024-06-07.
Which providers offer Qwen2.5-14B-Instruct?
Qwen2.5-14B-Instruct is available from 3 providers: DeepInfra, Fireworks AI, SiliconFlow.
What benchmarks has Qwen2.5-14B-Instruct been tested on?
Qwen2.5-14B-Instruct has been evaluated on 1 benchmark, including Massive Multitask Language Understanding.
Cheapest of 3 routes · SiliconFlow