How was DeepSeek R1 0528 trained differently from other reasoning models?

DeepSeek applied reinforcement learning directly to the base model, bypassing the conventional step of training on human-written reasoning traces. Reasoning patterns like self-verification and reflection emerged from RL exploration rather than curated data.

What are DeepSeek R1 0528's benchmark scores on mathematics?

79.8% Pass@1 on AIME 2024, on par with OpenAI o1 at release. On MATH-500 it scores 97.3%.

What does the MIT License mean for using DeepSeek R1 0528 outputs commercially?

The MIT License permits commercial use. Many proprietary reasoning models impose stricter restrictions.

What is the context window and architecture of DeepSeek R1 0528?

A context window of 160K tokens. The architecture is Mixture-of-Experts (MoE) with 671B total parameters, activating 37B per forward pass.

When should I use DeepSeek R1 0528 versus DeepSeek-V3 or V3.1?

DeepSeek R1 0528 specializes in deep reasoning with extended chain-of-thought. DeepSeek-V3 and later variants are general-purpose models that balance reasoning with faster, lower-cost completions and suit mixed-workload deployments better.

Does the reasoning trace appear in the API response?

Yes. The chain-of-thought trace appears in the response. This helps with debugging and with applications that display the model's reasoning to end users.

DeepSeek

DeepSeek R1 0528

DeepSeek R1 0528 is DeepSeek's open-source reasoning model, released January 20, 2025. It scores 79.8% Pass@1 on AIME 2024 and 97.3% on MATH-500. Weights ship under the MIT License for commercial use.

View API reference

Input and output price: Prices from: Input $0.50, Output $2.15, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'deepseek/deepseek-r1',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out DeepSeek R1 0528 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 R1 0528

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.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

DeepInfra

Legal:Terms•Privacy

160K

16K

0.6 s

19 tps

$0.50/M

$2.15/M

Read$0.35/M

—

01/20/2025

Bedrock

Legal:Terms•Privacy

128K

0.2 s

131 tps

$1.35/M

$5.40/M

—

01/20/2025

Getting started

Call DeepSeek R1 0528 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.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'deepseek/deepseek-r1',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same DeepSeek R1 0528 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'deepseek/deepseek-r1',
    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. `deepseek/deepseek-r1`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. DeepSeek R1 0528 supports up to `16,384` 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 160K-token context window

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.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'deepseek/deepseek-r1',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['deepinfra', 'bedrock'],
      },
    },
  });

  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.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'deepseek/deepseek-r1',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  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.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'deepseek/deepseek-r1',
    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 DeepSeek

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

deepseek/deepseek-v4.1-flash-beta

1.3 s

331 tps

$0.22/M

$0.66/M

Read$0.007/M

—

09/08/2026

deepseek/deepseek-v4-flash-vision-exp

0.4 s

172 tps

$0.22/M

$0.65/M

Read$0.007/M

—

08/21/2026

deepseek/deepseek-v4-pro-0813

0.3 s

107 tps

$0.60/M

$1.90/M

Read$0.02/M

—

08/12/2026

deepseek/deepseek-v4-flash-0731

0.5 s

244 tps

$0.07/M

$0.15/M

Read$0.007/M

—

+16

07/31/2026

deepseek/deepseek-v4-flash

0.5 s

223 tps

$0.08/M

$0.18/M

Read$0.007/M

—

04/23/2026

deepseek/deepseek-v4-pro

0.6 s

139 tps

$0.66/M

$1.98/M

Read$0.02/M

—

04/23/2026

Copy link to headingAbout DeepSeek R1 0528

DeepSeek R1 0528 was released January 20, 2025 and breaks from conventional reasoning model training. Instead of relying on human-written reasoning traces, DeepSeek applied reinforcement learning directly to the base DeepSeek-V3 weights. Unconstrained RL let emergent behaviors like self-verification, self-reflection, and long chain-of-thought generation develop organically.

The architecture is a 671B Mixture-of-Experts (MoE) model that activates 37B parameters per forward pass. On AIME 2024, DeepSeek R1 0528 achieves 79.8% Pass@1, on par with OpenAI o1. On MATH-500 it reaches 97.3%. The release documentation also highlights strong code and general reasoning performance.

The MIT License is permissive: many proprietary reasoning models impose stricter restrictions. DeepSeek released six smaller derivatives alongside the full model. The 32B and 70B versions match OpenAI o1-mini performance, giving teams cost-efficient alternatives to the full 671B model.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: DeepSeek R1 0528 generates verbose reasoning traces before final answers. Budget output tokens generously and account for variable response length when estimating costs.
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 DeepSeek R1 0528

Best for

Competitive mathematics: Formal proof construction and quantitative reasoning where AIME 2024 and MATH-500 benchmark results match your task
Code generation and debugging: Algorithm design where RL-derived problem-solving patterns produce self-correcting chains before final output
Complex analytical reasoning: Multi-step reasoning in finance, science, and engineering where showing work and self-verification build trust

Consider alternatives when

Conversation or summarization: Extended reasoning traces add unnecessary output token cost for content generation workloads
Hybrid thinking modes: DeepSeek-V3.1 or later supports both thinking and non-thinking modes through the same endpoint
Strict latency requirements: Variable response times from long reasoning chains are not acceptable when latency is a hard constraint
Pure creative writing: Structured reasoning adds no quality benefit for open-ended generation tasks

Copy link to headingConclusion

DeepSeek R1 0528 matches closed-source models on published benchmarks while shipping weights under the MIT License. For math, code, and formal reasoning workloads, it fits teams that need open weights.

Copy link to headingFrequently Asked Questions

How was DeepSeek R1 0528 trained differently from other reasoning models?
DeepSeek applied reinforcement learning directly to the base model, bypassing the conventional step of training on human-written reasoning traces. Reasoning patterns like self-verification and reflection emerged from RL exploration rather than curated data.
What are DeepSeek R1 0528's benchmark scores on mathematics?
79.8% Pass@1 on AIME 2024, on par with OpenAI o1 at release. On MATH-500 it scores 97.3%.
What does the MIT License mean for using DeepSeek R1 0528 outputs commercially?
The MIT License permits commercial use. Many proprietary reasoning models impose stricter restrictions.
What is the context window and architecture of DeepSeek R1 0528?
A context window of 160K tokens. The architecture is Mixture-of-Experts (MoE) with 671B total parameters, activating 37B per forward pass.
When should I use DeepSeek R1 0528 versus DeepSeek-V3 or V3.1?
DeepSeek R1 0528 specializes in deep reasoning with extended chain-of-thought. DeepSeek-V3 and later variants are general-purpose models that balance reasoning with faster, lower-cost completions and suit mixed-workload deployments better.
Does the reasoning trace appear in the API response?
Yes. The chain-of-thought trace appears in the response. This helps with debugging and with applications that display the model's reasoning to end users.

Your use is subject to DeepSeek's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

DeepSeek R1 0528

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Tool calling

Copy link to headingMore models by DeepSeek

Copy link to headingAbout DeepSeek R1 0528

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use DeepSeek R1 0528

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions