[Alibaba Cloud](/ai-gateway/models/labs/alibaba) # Qwen3 235B A22B Thinking 2507 Qwen3 235B A22B Thinking 2507 is Alibaba Cloud's 235B MoE model configured for extended chain-of-thought reasoning, combining 235 billion total parameters with always-on deliberative reasoning for demanding inference tasks. Your use is subject to Alibaba Cloud's [Terms](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0) & [Privacy](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy) Policies. ReasoningTool UseVision (Image) [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) AI SDKChat CompletionsMessagesResponses ``` 1import { streamText } from 'ai' 2 3const result = streamText({ 4 model: 'alibaba/qwen3-235b-a22b-thinking', 5 prompt: 'Why is the sky blue?' 6}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/qwen3-235b-a22b-thinking) [API](/ai-gateway/models/qwen3-235b-a22b-thinking/api) [About](/ai-gateway/models/qwen3-235b-a22b-thinking/about) [Providers](/ai-gateway/models/qwen3-235b-a22b-thinking/providers) [Throughput](/ai-gateway/models/qwen3-235b-a22b-thinking/throughput) [Latency](/ai-gateway/models/qwen3-235b-a22b-thinking/latency) [Uptime](/ai-gateway/models/qwen3-235b-a22b-thinking/uptime) [Status](/ai-gateway/models/qwen3-235b-a22b-thinking/status) [Similar](/ai-gateway/models/qwen3-235b-a22b-thinking/similar) [FAQ](/ai-gateway/models/qwen3-235b-a22b-thinking/faq) ## [Copy link to heading](#playground)Playground Try out Qwen3 235B A22B Thinking 2507 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. ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75)Qwen3 235B A22B Thinking 2507 ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=96&q=75) Qwen3 235B A22B Thinking 2507 ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) [Novita AI](/ai-gateway/models/providers/novita) Legal:[Terms](https://novita.ai/legal/terms-of-service)•[Privacy](https://novita.ai/legal/privacy-policy) | 131K | 33K | 1.0s | 110tps | $0.98/M | $3.95/M | | — | | | | | 07/25/2025 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) [DeepInfra](/ai-gateway/models/providers/deepinfra) Legal:[Terms](https://deepinfra.com/terms)•[Privacy](https://deepinfra.com/privacy) | 262K | 262K | 0.2s | 145tps | $0.23/M | $2.30/M | Read:$0.20/M Write:— | — | | | | | 07/25/2025 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) [Alibaba Cloud](/ai-gateway/models/providers/alibaba) Legal:[Terms](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0)•[Privacy](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy) | 131K | 33K | 0.5s | 121tps | $0.40/M | $4/M | | — | | | | | 07/25/2025 | | ## [Copy link to heading](#throughput)Throughput24 hours 1W 1D P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#latency)Latency24 hours 1W 1D P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#uptime)Uptime24 hours 1W 1D 1H Direct request success rate on AI Gateway and per-provider. Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/uptime) for more info. 1W 1D 1H ## [Copy link to heading](#more-models-by-alibaba-cloud)More models by Alibaba Cloud All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-flash](/ai-gateway/models/qwen3.8-flash) | 991K | 4.3s | 104tps | $0.16/M | $0.47/M | Read:$0.02/M Write:$0.20/M | — | +2 | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) | | | | 08/26/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-27b](/ai-gateway/models/qwen3.8-27b) | 1M | 0.6s | 170tps | $0.10/M | $0.40/M | Read:$0.01/M Write:$0.63/M | — | +1 | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![morph logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fmorph.png&w=48&q=75) +2 | | | | 08/14/2026 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-2.4t-a95b](/ai-gateway/models/qwen3.8-2.4t-a95b) | 262K | 0.3s | 149tps | $1.65/M | $4.95/M | Read:$0.12/M Write:$2.50/M | — | | ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) ![gmicloud logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgmicloud.png%3Fv%3D1785888489595&w=48&q=75) +4 | | | | 08/03/2026 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-max](/ai-gateway/models/qwen3.8-max) | 1M | 2.6s | 126tps | $2/M | $6/M | Read:$0.25/M Write:$2.50/M | — | +1 | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) | | | | 08/02/2026 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.7-flash](/ai-gateway/models/qwen3.7-flash) | 991K | 1.8s | 152tps | $0.03/M+2 more | $0.13/M+2 more | Read: $0.006/M+2 more Write: $0.04/M+2 more | — | +2 | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) | | | | 07/28/2026 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.7-plus](/ai-gateway/models/qwen3.7-plus) | 1M | 2.0s | 58tps | $0.40/M+1 more | $1.60/M+1 more | Read: $0.08/M+1 more Write: $0.50/M+1 more | — | +2 | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) | | | | 06/02/2026 | | ## [Copy link to heading](#about-qwen3-235b-a22b-thinking-2507)About Qwen3 235B A22B Thinking 2507 Qwen3 235B A22B Thinking 2507 is the Qwen3-235B-A22B configured with thinking mode as the default. The base model can switch between extended reasoning and direct response per request. This variant targets applications that need deliberate, chain-of-thought processing on every query. The underlying architecture is the same 235B MoE: 235 billion total parameters with 22 billion activated per inference step. That MoE structure makes thinking mode tractable at this scale. Because only 22 billion parameters activate per token, Qwen3 235B A22B Thinking 2507 sustains long reasoning traces without the serving costs of a fully dense 235B model generating the same sequence length. Chain-of-thought behavior is a first-class capability rather than something coaxed out by prompting. Alibaba Cloud reports that response quality scales smoothly with the computational reasoning budget allocated, so thinking longer genuinely helps on hard problems. For the hardest categories of tasks (competitive mathematics, multi-hop logical reasoning, complex code debugging, and structured scientific analysis), this thinking-configured variant makes fuller use of the 235B parameter capacity. Benchmark results for the underlying model are competitive with other strong reasoning models on reasoning-heavy evaluations. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: Provider selection may affect time-to-first-token for reasoning models, since longer thinking traces amplify any latency differences between providers. - Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-qwen3-235b-a22b-thinking-2507)When to Use Qwen3 235B A22B Thinking 2507 ### Best for - Mathematical problem solving requiring detailed derivation: When answers need to show work, such as proofs, step-by-step calculations, or theorem verification, the always-on thinking mode ensures the model reasons carefully before committing to an answer - Complex debugging and code analysis: Tracing through multi-file codebases, identifying subtle bugs, or reasoning about race conditions and edge cases benefits from extended deliberation rather than pattern-matched output - Structured decision-support tasks: Applications in legal analysis, medical information synthesis, or financial modeling that require the model to consider multiple factors and surface its reasoning process explicitly - Difficult multi-hop question answering: Tasks where the final answer requires correctly executing a chain of dependent reasoning steps are where thinking models show the largest quality gains over non-thinking alternatives - Research assistance requiring transparent reasoning: When users need to audit or follow the model's reasoning process, the thinking trace provides visibility into how conclusions were reached ### Consider alternatives when - Response latency is critical: Thinking mode generates substantial internal tokens before producing the final answer. For real-time conversational interfaces or latency-sensitive pipelines, the non-thinking variant or a smaller model will respond much faster - Most queries are simple and don't require deliberation: Using a thinking model for routine tasks, formatting, translation, simple extraction, pays the latency and token cost of reasoning without meaningful quality benefit. The base Qwen3-235B-A22B model with thinking disabled is more appropriate for mixed workloads - Budget constraints are strict: Thinking traces add tokens to every response. If your application is cost-constrained, evaluate whether the quality improvement on your specific task distribution justifies the additional token usage ## [Copy link to heading](#conclusion)Conclusion Qwen3 235B A22B Thinking 2507 is built for the class of tasks where getting the right answer justifies spending more tokens on reasoning. The MoE architecture makes it more economical to sustain long thinking traces than a dense model of comparable total scale, and the reasoning capability is built into the model rather than being a prompting trick. AI Gateway wraps the model with automated failover across Novita AI, DeepInfra, Alibaba Cloud and a unified API surface.