Mid-tier
US$1.00
Qwen3 Coder Plus
Qwen (Alibaba)
Qwen (Alibaba) · Budget · US$0.20 input/1M · US$0.40 output/1M · 128K context
Typical monthly cost
US$4.54
≈ per day
US$0.21
Blended cost/1M
US$0.23
Context window
128K
Qwen2.5 Coder 32B from Qwen (Alibaba) is a budget model priced at US$0.20 per 1M input tokens and US$0.40 per 1M output tokens. For a typical solo-developer workload (8 hours/day, 22 days/month — 1 medium feature, 5 small bug fixes, 4 PR reviews, 2 stack-trace debugs, ~1500 lines of TypeScript, 1 large-doc read, with prompt caching at the default mix) Qwen2.5 Coder 32B costs about US$5/month. The 128K-token context window covers single-file workloads comfortably.
Move the slider or switch task mix — values update live.
Monthly budget
US$100 / month
≈ $23/wk · ≈ $4.55/day
on Qwen2.5 Coder 32B
Input tokens
425.0M
Output tokens
37.5M
Total tokens
462.5M
Per month this budget delivers
At the default coding-agent mix.
The 22-day month is based on the median working-day count across DE/US.
| Activity | Count | Per task | Daily | Monthly |
|---|---|---|---|---|
| Medium feature (10–15 files) | 1 | US$0.06 | US$0.06 | US$1.39 |
| Small bug fix | 5 | US$0.01 | US$0.03 | US$0.71 |
| PR review | 4 | US$0.01 | US$0.03 | US$0.60 |
| Debug from stack trace | 2 | US$0.01 | US$0.03 | US$0.61 |
| Read a large doc | 1 | US$0.01 | US$0.01 | US$0.23 |
| Micro-interaction (explain / lint fix) | 30 | US$0.00 | US$0.01 | US$0.18 |
| Lines of TypeScript | 1,500 | US$0.00 | US$0.04 | US$0.82 |
| Total | US$0.21 | US$4.54 | ||
The 1500-lines-of-TS row models ~1000 lines read (cache-hit) + ~500 lines written. Headline figures are precise to ~5% — see the FAQ.
What each monthly budget buys on this model (typical solo-developer day, 22 working days).
| Monthly budget | Medium features | PR reviews | Debug sessions | Lines of TS |
|---|---|---|---|---|
| Typical (≈ $5) | 72 | 667 | 329 | 183,061 |
| $50/month | 793 | 7,352 | 3,628 | 2,016,129 |
| $200/month | 3,174 | 29,411 | 14,513 | 8,064,516 |
| $500/month | 7,936 | 73,529 | 36,284 | 20,161,290 |
| $2000/month | 31,746 | 294,117 | 145,137 | 80,645,161 |
Typical mix: coding-agent (85% input, 50% cache hits). Values show the maximum count of each task type at that budget.
Coding
Trained or post-trained for code generation tasks.
Reasoning
Not supported
Multimodal
Not supported
Prompt cache
Not supported
Batch API
50% off when you accept up to 24-hour turnaround.
Tool use
Native function-calling / tool-use API support.
Long context
Not supported
Extended thinking
Not supported
Total models
2
Median input/1M
US$0.60
Median output/1M
US$2.70
Input range
US$0.20–US$1.00
Verified: 2026-05-07
Running the realistic solo-developer day (1 medium feature + 5 small bug fixes + 4 PR reviews + 2 debug sessions + ~1500 lines of TypeScript + 1 large-doc read, 22 working days) on Qwen2.5 Coder 32B costs about US$5/month. Heavier workloads scale proportionally; lighter workloads cost less.
128K tokens total, with up to 8K of output. That fits a few dozen source files in a single call.
Providers charge US$0.40 per 1M output tokens against US$0.20 per 1M input — output requires real compute, input comes mostly from cache. Coding agents read many files (input-heavy) and emit compact diffs (low output), so total spend is usually input-driven.
No. Every input token is billed at the full US$0.20/1M rate. If your workload reuses the same system prompt frequently, compare against a caching-capable model (Claude Sonnet 4.6, GPT-5) where the effective input rate falls sharply.
Yes, if you can tolerate up to 24-hour turnaround: batch input/output are 50% cheaper than real-time rates. Perfect for nightly code reviews, bulk refactors or pre-merge analysis — wrong for inner-loop editing where you need an answer in seconds.
Open the full calculator with your own budget, task mix and region (US or DE with 19% VAT).
Open calculator