DeepSeek v4.1 Flash Beta on Vercel

Vercel has released an experimental beta of DeepSeek V4.1 Flash, available through its AI Gateway, with pricing set at $0.22 per 1 million input tokens and $0.66 per 1 million output tokens, and the beta expires on September 10, 2026. The model supports up to 384,000 output tokens and can be accessed via the AI SDK or OpenAI-compatible APIs, with free users receiving $5 of credits every 30 days.

DeepSeek V4.1 Flash Beta An experimental beta version of DeepSeek V4.1 Flash that expires on September 10th 2026. View API reference api - Input and output price - Input $0.22, Output $0.66, Per 1M tokens - 24h uptime - Loading AI Gateway uptime js 1import { streamText } from 'ai'2 3const result = streamText {4 model: 'deepseek/deepseek-v4.1-flash-beta',5 prompt: 'Why is the sky blue?'6} Copy link to heading playground Playground Try out DeepSeek V4.1 Flash Beta by DeepSeek. 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. DeepSeek V4.1 Flash Beta 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 | |---| Copy link to heading uptime Uptime24 hours 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. Copy link to heading throughput Throughput24 hours 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 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. Getting started Call DeepSeek V4.1 Flash Beta 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 /d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway%2Fapi-keys&title=AI+Gateway+API+Keys , and set it as AI GATEWAY API KEY in your environment. Full setup is covered in the text generation quickstart /docs/ai-gateway/getting-started/text . js 1import { generateText } from 'ai';2import 'dotenv/config';3 4async function main {5 const result = await generateText {6 model: 'deepseek/deepseek-v4.1-flash-beta',7 prompt: 'Why is the sky blue?',8 } ;9 10 console.log result.text ;11}12 13main .catch console.error ; Top-level parameters The same DeepSeek V4.1 Flash Beta request in each API format AI Gateway supports. js 1import { generateText } from 'ai';2import 'dotenv/config';3 4async function main {5 const result = await generateText {6 model: 'deepseek/deepseek-v4.1-flash-beta',7 system: 'You are a concise technical assistant.',8 prompt: 'Summarize the tradeoffs between static generation and SSR.',9 maxOutputTokens: 1024,10 } ;11 12 console.log result.text ;13}14 15main .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. deepseek/deepseek-v4.1-flash-beta . AI Gateway routes the request to an available provider. | | maxOutputTokens | number | No | Hard cap on generated tokens. DeepSeek V4.1 Flash Beta supports up to 384,000 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 1M-token context window | | Image | — | URL, base64, Uint8Array | — | — | Sent as image 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 deepseek provider docs https://ai-sdk.dev/providers/ai-sdk-providers/deepseek . js 1import { generateText } from 'ai';2import 'dotenv/config';3 4async function main {5 const result = await generateText {6 model: 'deepseek/deepseek-v4.1-flash-beta',7 prompt: 'Why is the sky blue?',8 providerOptions: {9 gateway: {10 only: 'deepseek' ,11 },12 },13 } ;14 15 console.log result.text ;16}17 18main .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 /docs/ai-gateway/models-and-providers/reasoning . js 1import { generateText } from 'ai';2import 'dotenv/config';3 4async function main {5 const result = await generateText {6 model: 'deepseek/deepseek-v4.1-flash-beta',7 prompt: 'Explain the Monty Hall problem step by step.',8 reasoning: 'high',9 } ;10 11 console.log result.text ;12}13 14main .catch console.error ; Image input Send images alongside text as message parts. Images count as input tokens. js 1import { generateText } from 'ai';2import 'dotenv/config';3 4async function main {5 const result = await generateText {6 model: 'deepseek/deepseek-v4.1-flash-beta',7 messages: 8 {9 role: 'user',10 content: 11 { type: 'text', text: 'Describe this image.' },12 { type: 'image', image: 'https://example.com/photo.jpg' },13 ,14 },15 ,16 } ;17 18 console.log result.text ;19}20 21main .catch console.error ; Tool calling Expose tools the model can call. Define each tool’s inputs with a Zod schema. js 1import { generateText, tool } from 'ai';2import { z } from 'zod';3import 'dotenv/config';4 5async function main {6 const result = await generateText {7 model: 'deepseek/deepseek-v4.1-flash-beta',8 prompt: 'What is the weather in San Francisco?',9 tools: {10 getWeather: tool {11 description: 'Get the current weather for a location',12 inputSchema: z.object { location: z.string } ,13 execute: async { location } = { location, temperatureC: 18 } ,14 } ,15 },16 } ;17 18 console.log result.text ;19}20 21main .catch console.error ;