Qwen2.5 Coder 32B Instruct is Alibaba's language model with a 131K context window and up to 33K output tokens, available from 8 providers, starting at $0.050 / 1M input and $0.100 / 1M output. A 32-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, excelling at code generation, debugging, and explanation across many programming languages.
Specifications
Canonical IDalibaba-qwen2-5-coder-32b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window131K tokens
Max Output33K tokens
Input ModalitiesText
Output ModalitiesText
Parameters32B
HuggingFace Likes2,008
HuggingFace Downloads (30d)1,257,495
HuggingFace Downloads (all-time)5,998,607
Release Date · 2 years ago
Knowledge Cutoff
Benchmarks
Intelligence Index
12.9
#337
MMLU-Pro
0.6
#238
GPQA
0.4
#354
HLE
0.0
#401
LiveCodeBench
0.3
#207
AIME
0.1
#108
Time to First Token
SciCode
0.3
#269
MATH-500
0.8
#106
Output TPS
0.0
#274

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Dolphin 2.9.2 Qwen2 72B131K$0.900$0.900Available
DeepSeek R1 Distill Qwen 32B131K$0.150$0.150Available
DeepSeek R1 Distill Qwen 14B131K$0.070$0.070Available
DeepSeek R1 Distill Qwen 1.5B131K$0.090$0.090Available
Cogito V1 Preview Qwen 14B131K$0.200$0.200Available
Cogito V1 Preview Qwen 32B131K$0.900$0.900Available
DeepSeek R1 Distill Qwen 7B131K$0.072$0.144Available
QwQ 32B131K$0.150$0.200Available
Qwen2.5 Coder 32B Instruct131K$0.050$0.100Current
Qwen2.5 7B Instruct131K$0.040$0.070Available
Qwen2.5 72B Instruct131K$0.120$0.300Available

Model IDs