Compare

Qwen2.5-Coder-32b-Instruct vs Qwen3-30b-A3b-Fp8

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Qwen2.5-Coder-32b-Instruct
qwen/qwen2.5-coder-32b-instruct
Qwen3-30b-A3b-Fp8
qwen/qwen3-30b-a3b-fp8
Provider
Alibaba Qwen
Alibaba Qwen
Family
Qwen
Qwen
Modality
text
text
Context window
131,072 tok
131,072 tok
Max output
4,096 tok
4,096 tok
Released
2025-02-27
2025-04-30
License
Open-weight
Open-weight
Input price
$0.660 /1M
$0.250 /1M
Output price
$1.00 /1M
$0.500 /1M
Tools
yes
Streaming
yes
yes
Vision
JSON mode
yes
Reasoning
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Qwen2.5-Coder-32b-Instruct
qwen/qwen2.5-coder-32b-instruct
Full spec →

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

Strengths
  • Code-tuned
  • Tool calling
  • Multi-lingual code
Use cases
Code generationRepo-scale Q&ACoding agents
Qwen3-30b-A3b-Fp8
qwen/qwen3-30b-a3b-fp8
Full spec →

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Qwen2.5-Coder-32b-Instruct vs Qwen3-Embedding-0.6b
qwen/qwen2.5-coder-32b-instruct · qwen/qwen3-embedding-0.6b
Qwen3-30b-A3b-Fp8 vs Qwen3-Embedding-0.6b
qwen/qwen3-30b-a3b-fp8 · qwen/qwen3-embedding-0.6b
Deepseek-R1-Distill-Qwen-32b vs Qwen2.5-Coder-32b-Instruct
deepseek/deepseek-r1-distill-qwen-32b · qwen/qwen2.5-coder-32b-instruct
Deepseek-R1-Distill-Qwen-32b vs Qwen3-30b-A3b-Fp8
deepseek/deepseek-r1-distill-qwen-32b · qwen/qwen3-30b-a3b-fp8
Qwen2.5-Coder-32b-Instruct vs Qwq-32b
qwen/qwen2.5-coder-32b-instruct · qwen/qwq-32b
Qwen 3 Max vs Qwen2.5-Coder-32b-Instruct
alibaba/qwen3-max · qwen/qwen2.5-coder-32b-instruct
Qwen 3.5 397B A17B vs Qwen2.5-Coder-32b-Instruct
alibaba/qwen3.5-397b-a17b · qwen/qwen2.5-coder-32b-instruct
Qwen3-30b-A3b-Fp8 vs Qwq-32b
qwen/qwen3-30b-a3b-fp8 · qwen/qwq-32b
Qwen 3 Max vs Qwen3-30b-A3b-Fp8
alibaba/qwen3-max · qwen/qwen3-30b-a3b-fp8
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Qwen2.5-Coder-32b-Instruct
client.chat.completions.create(
    model="qwen/qwen2.5-coder-32b-instruct",
    messages=[{"role":"user","content":"hello"}],
)

# Qwen3-30b-A3b-Fp8
client.chat.completions.create(
    model="qwen/qwen3-30b-a3b-fp8",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →