Qwen 3.7 Plus
Alibaba Cloud (Qwen) · Model release
Catalog checked 2026-09-29
- Input $/1M
- $0.40
- Output $/1M
- $1.60
- Context
- 1M
- Max output
- 131K
- Reasoning
- Yes
- Included in
- 8 plans
API model id
qwen3.7-plusInput
$0.40
Output
$1.60
Cache read
$0.08
- Above 256K input tokens (all tokens in the request)
- Input $1.20 · Output $4.80 · Cache read $0.24 / 1M tokens
Published rate checked 2026-09-29. Sources below.
Rates are the Singapore (International) list prices. Other Model Studio regions list different rates, and limited-time promotions are excluded. Explicit cache creation and explicit cache reads are billed at separate published rates.
Current published base rates. Context tiers, cache-write duration and other conditions may change the rate for a request. These are not a reconstructed historical invoice.
- Context window
- 1,000,000
- Maximum output
- 131,072
- Input
- text · image · video
- Output
- text
- Reasoning
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Hybrid thinking mode; thinking is on by default and can be turned off with enable_thinking.
- Thinking
- Hybrid thinking. Thinking is on by default and can be turned off per request with enable_thinking.
- Released on Model Studio
- Listed for Singapore (International) on June 1, 2026.
- Long-context pricing
- Requests above 256K input tokens bill all tokens at $1.20 input and $4.80 output per MTok.
- Prompt caching
- Up to 256K input: implicit cache hits $0.08, explicit cache creation $0.50 and explicit cache reads $0.04 per MTok. Above 256K: $0.24, $1.50 and $0.12.
- Regions
- Rates shown are for Singapore (International). China (Beijing) and the Global regions (Frankfurt, Virginia, Tokyo, Hong Kong) list different rates.
- Snapshot
- qwen3.7-plus is functionally equivalent to qwen3.7-plus-2026-05-26.
Pricing, assumptions & evidence
Published base rate
Input $0.40 · Output $1.60 · Cache read $0.08 · Cache write Not listed
Above 256K input tokens (all tokens in the request): input $1.20, output $4.80, cache read $0.24.
- Official model capabilities and context limits (Singapore, International)
- Default thinking behavior
- Official capabilities, limits and regional prices
- Model Studio release date
Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.
Aliases, routes and identity
Catalog ID qwen-3-7-plus
Model release (kind: release)
Developer: Alibaba Cloud (Qwen)
qwen/qwen3.7-plusharness_alias