Model pricing
Qwen 3.7 Plus API list price — cost per token
Qwen 3.7 Plus costs $0.40 per million input tokens and $1.60 per million output tokens (USD). Requests with >256K tokens in the prompt, including cache reads and writes, use the premium rates for the whole request. Rates follow the published OpenCode Zen or Go table for this model and gateway (opencode.ai/docs/zen and opencode.ai/docs/go). On OpenCode Zen or Go this is a notional list-price figure for turns logged on this Mac, not a metered vendor bill; free-tier ids stay unpriced and show as tokens.
| Token rate | USD / 1M tokens |
|---|---|
| Effortqualitative reasoning depth | Medium |
| Inputper 1M tokens | $0.40 |
| Output | $1.60 |
| Cache write · 5-minuteper 1M tokens | $0.50 |
| Cache readper 1M tokens | $0.04 |
| Input · >256K context | $1.20 |
| Output · >256K context | $4.80 |
| Cache write · >256K context | $1.50 |
| Cache read · >256K context | $0.12 |
Notional list price. These are OpenCode Zen / Go models API list prices in USD. On OpenCode Zen / Go usage this is a notional list price — what usage would cost at API rates, not metered spend.
Cache & context economics
Cache reads cost $0.04 per million tokens — about a tenth of input. The >256K tokens context tier reprices the whole request.
Common questions
- How much does Qwen 3.7 Plus cost per million tokens?
- $0.40 input and $1.60 output per million tokens (USD list price).
- What is the cache-read price for Qwen 3.7 Plus?
- $0.04 per million cached-read tokens — about a tenth of the input rate.
- Does Qwen 3.7 Plus have a context pricing tier?
- Yes — at >256K tokens input rises to $1.20 per million for the entire request.
Track your real cost with JP the Cat
A live menu-bar total, priced to the cent from your local logs — including the cache-write split most tools miss.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat