Qwen3.7 Plus
Qwen3.7 Plus is a chat model from Alibaba, offered as part of the Qwen family of large language models served through inference APIs.
API Pricing
Cheapest on Velokey — 18% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.320 | $1.28 | $0.032 | |
| $0.320 | $1.28 | - | |
| $0.320 | $1.28 | $0.064 | |
| $0.600 | $2.40 | - |
Prices updated daily. Last check: Oct 14, 2026
Compare API pricing for every Qwen model →Qwen3.7 Plus pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Reasoning & Knowledge
- GPQA Diamond90.0%
- Humanity's Last Exam35.6%
Coding
- SciCode46.1%
Agentic & Tool Use
- Terminal-Bench Hard47.0%
- Terminal-Bench v2.161.0%
- τ²-bench93.0%
- τ-bench Banking17.5%
Instruction & Long Context
- IFBench78.0%
- Long-Context Reasoning73.0%
Benchmarks measured Oct 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Alibaba
- Modalities
- Text
Capabilities
- Open Source
- No
Strengths & Limitations
Strengths
- Part of Alibaba's Qwen model family, which is widely served across multiple inference providers
- Measured time to first token of approximately 1,391 ms in Artificial Analysis testing, suitable for interactive chat interfaces
- Measured output throughput of approximately 55.7 tokens per second
- "Plus" tier sits above Alibaba's smaller API variants, giving a middle option between cheap high-volume tiers and larger configurations
- Available as a hosted API model, requiring no GPU provisioning or local serving infrastructure
- Multiple providers may offer the model, allowing price and latency comparison rather than single-vendor lock-in
Limitations
- We do not currently track a confirmed context window for this model — check the serving provider's documentation before planning long-context workloads
- Modality support (for example image input) is not confirmed in our metadata
- No standard reasoning, coding, or knowledge benchmark scores are recorded for this entry in our database
- Output throughput of about 55.7 tokens/sec is moderate; latency-critical, high-volume streaming workloads may favour smaller models
- Served through hosted APIs, so availability, rate limits, and versioning depend on the provider
Key Features
About Qwen3.7 Plus
Common Use Cases
Qwen3.7 Plus fits general-purpose assistant and chat workloads where a mid-to-upper commercial tier is warranted: drafting and rewriting text, summarisation, question answering over supplied content, customer-facing conversational interfaces, and internal knowledge assistants. Its sub-two-second time to first token makes it workable for interactive use where a user is waiting on a streamed reply, while its moderate steady-state throughput is better suited to conversational turn lengths than to bulk generation of very long documents. Teams already using other Qwen tiers may consider it as a step up from Alibaba's smaller, cheaper variants when output quality matters more than per-request cost. Because we do not have a confirmed context window or modality list for this entry, verify those specifications with the serving provider before committing it to long-document or multimodal pipelines.
Frequently Asked Questions
How much does Qwen3.7 Plus cost to use?
Pricing for Qwen3.7 Plus varies by inference provider and by pricing type — input tokens, output tokens, and any cached or batch rates are usually billed separately, and providers change rates over time. Check the pricing table on this page for the current per-provider figures rather than relying on a fixed number.
What is Qwen3.7 Plus best used for?
It suits general chat and text-generation work: assistants, summarisation, question answering over provided material, drafting and editing, and conversational product features. Its roughly 1.4-second time to first token supports interactive streaming, while its ~55.7 tokens/sec output rate is better matched to conversational replies than to very long-form bulk generation.
How fast is Qwen3.7 Plus?
Artificial Analysis measured approximately 55.7 output tokens per second with a time to first token of about 1,391 ms. Real-world numbers depend on the provider, region, prompt length, and current load, so use these as reference points when comparing providers in the table above.
What context window does Qwen3.7 Plus support?
We do not currently track a confirmed context window for this model in our database. Consult the documentation of the provider you plan to use, since hosted providers sometimes cap context below a model's maximum.
How does Qwen3.7 Plus compare to other Qwen tiers?
The "Plus" label marks it as a mid-to-upper commercial API tier in Alibaba's Qwen lineup, above the smaller variants aimed at high-volume, low-cost workloads. If your workload is simple classification or extraction at scale, a smaller Qwen tier may be more economical; if it needs stronger general reasoning in a chat format, the Plus tier is the intended step up. Compare measured speed and per-provider pricing on this page before deciding.