Qwen 3.7 Plus
Qwen 3.7 Plus is the Qwen 3.7 Plus-tier model in Alibaba's Qwen 3 family, succeeding Qwen3.6-Plus with stronger reasoning, vision input, and a context window of 1M tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.7-plus', prompt: 'Why is the sky blue?'})Playground
Try out Qwen 3.7 Plus by Alibaba. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Qwen 3.7 Plus
Ask Qwen 3.7 Plus anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Alibaba | 1M | 2.4s | 55tps | $0.40/M | $1.60/M | Read: $0.08/M Write: $0.5/M | — | — | +3 | 06/02/2026 | ||
 Fireworks | 1M | 1.3s | 303tps | $0.40/M | $1.60/M | Read:$0.08/M Write:— | — | — | +3 | 06/02/2026 | ||
 Together AI | 1M | 1.6s | 110tps | $0.32/M | $1.28/M | — | — | +2 | 06/02/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Alibaba
| Model |
|---|
| 991K | 1.9s | 57tps | $1.25/M | $3.75/M | Read:$0.25/M Write:$1.56/M | — | — | +1 | | 05/21/2026 | |||
| 240K | 1.3s | 84tps | $1.30/M | $7.80/M | Read: $0.26/M Write: $1.63/M | — | — | +1 | | 04/20/2026 | |||
| 1M | 0.2s | 118tps | $0.50/M | $3.00/M | Read: $0.1/M Write: $0.63/M | — | — | +3 | | 04/02/2026 | |||
| 1M | 0.9s | 144tps | $0.10/M | $0.40/M | Read:$0.0/M Write:$0.13/M | — | — | +3 | | 02/24/2026 | |||
| 33K | $0.05/M | — | — |  | 06/05/2025 | ||||||||
| 41K | 0.3s | 63tps | $0.12/M | $0.24/M | — | — | | 04/28/2025 |
About Qwen 3.7 Plus
Qwen 3.7 Plus is the Plus-tier release in the Qwen 3.7 generation, succeeding Qwen3.6-Plus in Alibaba's production Qwen 3 lineup. It ships with a context window of 1M tokens and is available through alibaba, fireworks, togetherai on AI Gateway.
The Qwen Plus line targets workloads that need deeper reasoning and stronger instruction following than the Flash tier provides, while keeping per-token cost below the Max tier. Qwen 3.7 Plus continues that positioning and adds vision input, making it the multimodal entry in the 3.7 line. The model is described as a balanced version focused on reasoning and logical expression, with the broader toolchain rolling out over time.
Like earlier Plus releases, Qwen 3.7 Plus supports structured outputs and tool calling, letting the model invoke registered functions or external APIs during multi-turn sessions. For teams already using Qwen3.6-Plus, Qwen 3.7 Plus offers an incremental upgrade path that slots into existing integrations without changes to prompt structure or tool-calling configuration.
You can integrate Qwen 3.7 Plus through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
What To Consider When Choosing a Provider
- Configuration: As a newer Plus-tier release than Qwen3.6-Plus, monitor the AI Gateway cost dashboard to compare per-token spend and confirm the quality uplift justifies any pricing difference for your workload.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Qwen 3.7 Plus
Best For
- Deliberate Multi-Step Reasoning: Analytical workflows, structured document processing, and multi-constraint problem solving
- Multimodal Reasoning Tasks: Pairing text instructions with screenshot analysis, chart interpretation, or UI grounding
- High-Fidelity Code Work: Refactoring and code generation where instruction adherence outweighs raw throughput
- Multi-Turn Agentic Pipelines: Tool-calling across many turns where the model plans and invokes external APIs
- Long-Context Workloads: Passing full documents or codebases using the window of 1M tokens
- Upgrading From Qwen3.6-Plus: Teams moving to the Qwen 3.7 Plus tier without changing their integration
Consider Alternatives When
- Throughput And Cost First: A Flash-tier model is a closer fit when deep reasoning isn't required and latency and price dominate
- Flagship Agent Workloads: Qwen3.7-Max is the flagship in the 3.7 line for long-horizon agent tasks that need maximum reasoning ceiling
- Text-Only Pipelines: A dedicated text model offers lower cost per token when vision input is never used
- Video Or Image Generation: A generation-class model fits tasks that produce pixels rather than read them
Conclusion
Qwen 3.7 Plus extends the Qwen Plus tier with the Qwen 3.7 generation's reasoning improvements and adds vision input as the multimodal entry in the 3.7 line. Routing through AI Gateway gives teams already on Qwen3.6-Plus a direct upgrade path with the same unified API, provider routing, and billing.