Qwen 3.7 Flash
Qwen 3.7 Flash is the Flash-tier vision-language model in Alibaba Cloud's Qwen 3.7 line, accepting text, image, and video input within a context window of 991K tokens.
View API reference- Input and output price
- Input $0.03, Output $0.13, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.7-flash', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen 3.7 Flash by Alibaba Cloud. 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 Flash
Qwen 3.7 Flash
Copy link to headingProviders
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Qwen 3.7 Flash through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen 3.7 Flash request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. alibaba/qwen3.7-flash. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen 3.7 Flash supports up to 64,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 991K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK alibaba provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['alibaba'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-flash', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Alibaba Cloud
| Model |
|---|
| 991K | 6.0 s | 44 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 | | 09/01/2026 | |||||
| 991K | 5.3 s | 83 tps | $0.16/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +2 | | 08/26/2026 | |||||
| 1M | 0.6 s | 126 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +2 | 08/14/2026 | |||||
| 1M | 3.8 s | 142 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +1 |  | 08/02/2026 | |||||
| 1M | 1.6 s | 58 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +2 | | 06/02/2026 | |||||
| 262K | 3.7 s | 52 tps | $0.20/M | $0.88/M | Read$0.11/M | — | | 09/23/2025 |
Copy link to headingAbout Qwen 3.7 Flash
Qwen 3.7 Flash is the Flash-tier release in Alibaba Cloud's Qwen 3.7 generation, sitting below Qwen3.7-Plus and Qwen3.7-Max. Released July 28, 2026 and available through Alibaba Cloud on AI Gateway, this native vision-language model takes text, images, and video in and returns text, within a context window of 991K tokens and up to 64K tokens per response.
Alibaba Cloud describes the Qwen 3.7 Flash series as a comprehensive upgrade over Qwen3.6-Flash in multimodal understanding and agent execution. The documented gains cover universal object recognition, real-world perception, and spatial intelligence. Qwen 3.7 Flash also targets search-agent and code-interpreter-agent scenarios with steadier end-to-end task execution, alongside tuning for multimodal coding.
Reasoning is on by default. You can turn thinking off per request for short lookups, or cap the thinking budget when latency and token spend matter more than reasoning depth. Reasoning traces can carry across turns, so a long agent loop keeps its chain of thought instead of restarting it on every tool call. Qwen 3.7 Flash supports function calling and structured output, with structured output available in non-thinking mode. Alibaba Cloud also documents built-in web search and code execution tools for the model.
Qwen 3.7 Flash accepts up to 16 million pixels per image, video up to two hours or 2 GB, and as many as 64 videos in one request. Each image consumes tokens in proportion to its resolution, so downscale screenshots that don't need full detail.
You can integrate Qwen 3.7 Flash through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Qwen 3.7 Flash runs reasoning by default, so every request spends thinking tokens unless you turn it off. High-volume classification and extraction jobs usually cost less with thinking disabled, so route simple calls that way.
- Configuration: Alibaba Cloud publishes no benchmark table for Qwen 3.7 Flash, so evaluate the model on representative inputs rather than assuming parity with the Plus tier. Image resolution drives token count directly, and full-resolution screenshots can dominate the cost of a high-volume pipeline.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Qwen 3.7 Flash
Best for
- High-Volume Multimodal Pipelines: Classification, extraction, and routing over images and video at Flash-tier cost
- Visual Agent Workflows: Search and code-interpreter agents that read screens and act on what they see
- Spatial Intelligence Tasks: Stronger universal object recognition and improved real-world perception
- Long Video Understanding: Clips up to two hours or 2 GB in a single request
- Long-Context Multimodal Input: Full documents, screenshot histories, and frame sequences within 991K tokens
Consider alternatives when
- Flagship Multimodal Quality: Qwen3.8-Max leads the Qwen lineup on the hardest visual and coding work
- Balanced Quality And Cost: Qwen3.7-Plus sits between the Flash and Max tiers with a larger image allowance
- Text-Only Agent Workloads: Qwen3.7-Max is the Max-tier release in the 3.7 line for long tool-calling loops
- Image Or Video Generation: A generation-class model fits tasks that produce pixels rather than read them
Copy link to headingConclusion
Qwen 3.7 Flash brings the Qwen 3.7 generation's vision-language work to the cheapest tier in the line, with text, image, and video input inside a context window of 991K tokens. Route alibaba/qwen3.7-flash through AI Gateway to run high-volume multimodal pipelines behind one API key, then escalate to Qwen3.7-Plus or Qwen3.8-Max when a task needs more headroom.
Copy link to headingFrequently Asked Questions
What inputs does Qwen 3.7 Flash accept?
Text, images, and video. Qwen 3.7 Flash is a native vision-language model and returns text only.
What is the context window for Qwen 3.7 Flash?
The context window is 991K tokens, with up to 64K tokens per response.
How does Qwen 3.7 Flash compare to Qwen3.6-Flash?
Alibaba Cloud describes the Qwen 3.7 Flash series as a comprehensive upgrade over Qwen3.6-Flash in multimodal understanding and agent execution. The listed gains cover universal object recognition, real-world perception, spatial intelligence, and steadier end-to-end execution in agent scenarios.
Where does Qwen 3.7 Flash sit in the Qwen 3.7 lineup?
Below Qwen3.7-Plus and Qwen3.7-Max. Qwen 3.7 Flash is the Flash tier, built for throughput and low cost per token rather than the highest reasoning ceiling.
Is reasoning enabled by default on Qwen 3.7 Flash?
Yes. Qwen 3.7 Flash runs in thinking mode by default. You can disable thinking per request for simple queries, or cap the thinking budget to limit how many reasoning tokens the model spends.
Does Qwen 3.7 Flash support tool calling and structured output?
Yes. Qwen 3.7 Flash supports function calling and structured output, with structured output available in non-thinking mode. Alibaba Cloud also documents built-in web search and code execution tools for the model.
How much video can Qwen 3.7 Flash process in one request?
Video up to two hours or 2 GB, and as many as 64 videos in a single request. Images are capped at 16 million pixels each, and higher resolution consumes more tokens.
How do I access Qwen 3.7 Flash through AI Gateway?
Authenticate with an AI Gateway API key or OIDC token and reference
alibaba/qwen3.7-flashas the model. You can call Qwen 3.7 Flash through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.What does Qwen 3.7 Flash cost?
See the pricing section on this page for today's rates. AI Gateway reflects each provider's pricing for Qwen 3.7 Flash with no markup.
Does Qwen 3.7 Flash support zero data retention?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Your use is subject to Alibaba Cloud's Terms & Privacy Policies.