Qwen: Qwen-Plus API Pricing
Qwen: Qwen-Plus costs $0.260 per 1M input tokens and $0.780 per 1M output tokens (cache reads: $0.052). Context window: 1M. Prices verified 2026-10-21 · source
Alternatives to consider
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.260 | — |
| Cache read | $0.052 | −80% |
| Cache write (5m) | $0.325 | +25% |
| Output | $0.780 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Training data ends here — newer events require retrieval or web search.
What would Qwen: Qwen-Plus cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $5.20 |
| Coding agent | 5,000 | 8,000 / 2,000 | $18.20 |
| RAG pipeline | 30,000 | 4,000 / 500 | $42.90 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $11.96 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Qwen: Qwen-Plus
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
Compare Qwen: Qwen-Plus with
- Qwen: Qwen-Plus vs OpenAI: GPT-5.6 Terra Pro
- Qwen: Qwen-Plus vs Anthropic: Claude Fable 5
- Qwen: Qwen-Plus vs Anthropic: Claude Opus 5
- Qwen: Qwen-Plus vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Qwen: Qwen-Plus cost?
Qwen: Qwen-Plus costs $0.260 per 1M input tokens and $0.780 per 1M output tokens; cached input tokens cost $0.052 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
1M tokens, with up to 33K output tokens per response. That's roughly 1250 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.052/1M, about 80% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 93% on a typical workload with comparable quality.
Official resources
- Qwen: Qwen-Plus on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Qwen GitHub → — official model repositories and release notes.
- Shred your current bill — paste a CSV and see if switching saves money.