All AI models · LLM benchmarks · Methodology

Alibaba

Qwen2.5-Coder 7B Instruct

Qwen coding model for software agents, repository edits, and code reasoning

Model facts

Context window
131K tokens
Maximum output
8K tokens
Cheapest paid input
$0.144 per 1M tokens
Cheapest paid output
$0.287 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 5.6 GiB, Q8_0 9.2 GiB, F16 15.8 GiB working memory.

Parameters
7.6 billion
Architecture
qwen2
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default4.1not measurednot measurednot measured

Observed price history

  • 2026-08-24: $0.144 input / $0.287 output per 1M tokens

API providers

  • Alibaba (China) — model id qwen2-5-coder-7b-instruct; $0.144 input / $0.287 output per 1M tokens; provider documentation