---
title: 'DeepSeek V4.1 Flash 1017 API: Release Notes and Model ID | RunAPI'
description: DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.
url: https://runapi.ai/models/deepseek/v4.1-flash.md
canonical: https://runapi.ai/models/deepseek/v4.1-flash
locale: en
site: RunAPI
image: https://runapi.ai/assets/opengraph-bfaaa0f0.png
alternates:
  en: https://runapi.ai/models/deepseek/v4.1-flash
  zh-CN: https://runapi.ai/zh-CN/models/deepseek/v4.1-flash
  es: https://runapi.ai/es/models/deepseek/v4.1-flash
  ja: https://runapi.ai/ja/models/deepseek/v4.1-flash
  de: https://runapi.ai/de/models/deepseek/v4.1-flash
  fr: https://runapi.ai/fr/models/deepseek/v4.1-flash
  pt-BR: https://runapi.ai/pt-BR/models/deepseek/v4.1-flash
  ko: https://runapi.ai/ko/models/deepseek/v4.1-flash
  it: https://runapi.ai/it/models/deepseek/v4.1-flash
  nl: https://runapi.ai/nl/models/deepseek/v4.1-flash
  pl: https://runapi.ai/pl/models/deepseek/v4.1-flash
  tr: https://runapi.ai/tr/models/deepseek/v4.1-flash
  zh-TW: https://runapi.ai/zh-TW/models/deepseek/v4.1-flash
  zh-HK: https://runapi.ai/zh-HK/models/deepseek/v4.1-flash
  ar: https://runapi.ai/ar/models/deepseek/v4.1-flash
  x-default: https://runapi.ai/models/deepseek/v4.1-flash
model: DeepSeek
provider: DeepSeek
variant_id: deepseek-flash
sdk_model_id: deepseek-flash
modality: text
billing_unit: 1K tokens
status: active
---

> HTML version: https://runapi.ai/models/deepseek/v4.1-flash
> Site index for agents: https://runapi.ai/llms.txt


# DeepSeek V4.1 Flash 1017 API

Call deepseek-flash from the DeepSeek family through RunAPI. Billing is per token with no subscription, and a request that fails before its response starts is not charged.

**DeepSeek / [DeepSeek](https://runapi.ai/models/deepseek.md)**
**Operational · text · Commercial OK**

## What changed in DeepSeek V4.1 Flash 1017

DeepSeek put V4.1 Flash on its API on September 10, 2026. It is the smallest model in a new architecture family: a 552B-parameter Mixture-of-Experts built as a causal encoder-decoder, with 8B parameters active while it reads input and 16B while it writes output. V4 Flash kept the V4 Preview architecture through its July update, and image input needed a separate experimental model. DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.

The KV cache also got smaller. DeepSeek says it needs a quarter of the HBM and an eighth of the SSD storage of the previous generation, and links that to lower cache-hit charges in agent workloads. DeepSeek credits new pre-training methods and larger-scale RL post-training for benchmark scores above its own V4-Pro.

The release kept the old model name. DeepSeek serves V4.1 Flash as deepseek-flash, an ID that moves to each new Flash release, and there is no deepseek-v4.1-flash ID. RunAPI uses the same ID on its OpenAI-compatible and Anthropic-compatible endpoints.

**Released:** September 10, 2026
**Architecture:** 552B MoE, causal encoder-decoder
**Active parameters:** 8B for input, 16B for output
**Context window:** 1M tokens. DeepSeek official specification; not tested across all RunAPI service options
**Max output:** 384K tokens. DeepSeek official specification; not tested across all RunAPI service options
**Thinking:** On by default, non-thinking mode available
**API model ID:** deepseek-flash



<!-- catalog-model-detail-slot: model-playground -->

## Try DeepSeek V4.1 Flash 1017

Pick any model and generate in seconds.


**Model:**
- **Chat completion** — `chat_completion` · `deepseek-flash` · Input $0.24 / 1M tokens | Output $0.96 / 1M tokens
- **Message**

**Prompt:** Describe what you want to create...

**Estimated:** Input $0.24 / 1M tokens | Output $0.96 / 1M tokens

- [Generate](https://runapi.ai/login)
Sign in to generate with RunAPI.
<!-- /catalog-model-detail-slot: model-playground -->

### Switch variant

- **deepseek-flash** (current)
- [deepseek-v4-flash](https://runapi.ai/models/deepseek/v4-flash.md)
- [deepseek-v4-flash-vision-exp](https://runapi.ai/models/deepseek/v4-flash-vision-exp.md)
- [deepseek-v4-pro](https://runapi.ai/models/deepseek/v4-pro.md)
- [deepseek-v4-pro-0813](https://runapi.ai/models/deepseek/v4-pro-0813.md)
- [deepseek-v4.1-flash-1017](https://runapi.ai/models/deepseek/v4.1-flash-1017.md)

6 versions available



[Full model reference: endpoints, parameters and pricing](https://runapi.ai/models/deepseek/flash.md)



deepseek-flash is one of the DeepSeek models on RunAPI. It uses the same API key as every other model, and you switch to it by changing the model ID in your request. Each call is synchronous and billed in USD by input, output, and cache tokens, with no subscription or minimum spend. A request that fails before the response starts is not charged; once a response is streaming, the tokens already generated are billed, even if the client disconnects.

- Per-token billing in USD with no subscription
- No charge when a request fails before its response starts
- Token-by-token streaming
- Switch models by changing one model ID
- One API key and one bill for every model and provider

## Usage metrics

- **API Calls / Day:** 305
- **Success Rate:** 97.4%
- **Avg Generation:** 7.9s

Verified customer feedback is not available for this model yet.



## Technical details

| Field | Value |
|---|---|
| Provider | DeepSeek |
| Model ID | deepseek-flash |
| Modality | Text |
| Task types | Synchronous |
| API endpoint | `/v1/chat/completions` |
|  | `/v1/responses` |
|  | `/v1/messages` |
|  | `/v1beta/models/deepseek-flash:generateContent` |
|  | `/v1beta/models/deepseek-flash:streamGenerateContent` |
| Billing unit | 1K tokens |
| Catalog status | Operational |



**HOW IT WORKS**

## Use This Model in 3 Steps

1. **Get Your Key** - Sign up for free and create an API key for deepseek-flash from the dashboard.
2. **Send a Request** - POST to /v1/chat/completions with the deepseek-flash model slug and your parameters.
3. **Get Results** - Read the completed deepseek-flash response directly from the endpoint.



<!-- catalog-model-detail-slot: feature-cards -->

## What this model offers

- **Endpoint coverage** — Exposes 2 public endpoint(s): chat_completion, message.
- **Usage-based billing** — Metered by 1K tokens with no subscription requirement.
<!-- /catalog-model-detail-slot: feature-cards -->



## DeepSeek V4.1 Flash 1017 Pricing

| Endpoint | Price |
|---|---|
| `chat_completion` | Input: $0.24 / 1M tokens<br>Output: $0.96 / 1M tokens<br>Cache read: $0.01 / 1M tokens |
| `message` | Input: $0.24 / 1M tokens<br>Output: $0.96 / 1M tokens<br>Cache read: $0.01 / 1M tokens |



**API REFERENCE**

## Endpoint Specification

| Field | Value |
|---|---|
| Endpoint | `POST /v1/chat/completions` |
| Model ID | `deepseek-flash` |
| Task Types | `chat_completion, message` |


<!-- catalog-model-detail-slot: request-parameters -->

## Request parameters

No request parameters are published for this endpoint.
<!-- /catalog-model-detail-slot: request-parameters -->

**Request example**

```json
{
  "model": "deepseek-flash",
  "messages": [
    {
      "role": "user",
      "content": "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."
    }
  ]
}
```

### Model skill — deepseek-flash

Install the skill once, then use the variant ID from this page while building.

Base URL: `https://runapi.ai`

| Endpoint | Protocol |
|---|---|
| `POST /v1/chat/completions` | OpenAI compatible |
| `POST /v1/responses` | OpenAI Responses |
| `POST /v1/messages` | Anthropic compatible |
| `POST /v1beta/models/deepseek-flash:generateContent` | Gemini generateContent |
| `POST /v1beta/models/deepseek-flash:streamGenerateContent` | Gemini streamGenerateContent |

Use the OpenAI / Anthropic / Google Gen AI SDK with your RunAPI API key and `model: "deepseek-flash"`.

### Use deepseek-flash with a model skill

1. **Install** — Install the model skill for the DeepSeek line. It loads docs, request formats, and pricing notes into your coding workspace.
2. **Configure** — Point your SDK at https://runapi.ai and set your RunAPI API key. The same key works for every model and provider.
3. **Call** — Send a request in an API format this model supports, with the model field set to the model ID on this page. RunAPI forwards it to the provider.
4. **Receive** — Read the response from the same call, or stream it as it is generated. The usage field shows the tokens you are billed for.

### What's different about deepseek-flash

- **VS DEEPSEEK-V4-FLASH: DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.** — Fast, low-cost reasoning; toggle thinking per request
- **VS DEEPSEEK-V4-FLASH-VISION-EXP: DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.** — 1M context; image input for vision tasks; JPEG, PNG, GIF, and WebP
- **VS DEEPSEEK-V4-PRO: DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.** — Flagship reasoning and analysis for complex agentic work

## USE CASES

**Customer support**

Answer customer questions from a private knowledge base, reducing ticket volume.

**Document analysis**

Draft contract summaries and flag key clauses for attorney review.

**Code generation**

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.



## Frequently asked questions about DeepSeek V4.1 Flash 1017

### Is DeepSeek V4.1 Flash a new model or a retrained V4 Flash?

It is a new model. DeepSeek built it on a new causal encoder-decoder architecture with 552B total parameters, then trained it with new pre-training methods and larger-scale RL. The July 2026 V4 Flash update had kept the earlier architecture and was only post-trained again.

### How does V4.1 Flash score against V4 Flash?

On DeepSeek's published numbers, Terminal-Bench 2.1 went from 82.7 to 90.6, CyberGym from 76.7 to 88.1, and Agents' Last Exam from 25.2 to 31.8. All three figures are DeepSeek's own, taken from its change log.

### What context window and output limit does V4.1 Flash have?

DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.

### Does V4.1 Flash support tool calling and JSON output?

Yes. DeepSeek's model table for V4.1 Flash marks tool calls and JSON output as supported.

### Do requests to deepseek-v4-flash still work?

Use deepseek-flash for new code. DeepSeek documents that its official direct API serves the retired names deepseek-v4-flash and deepseek-v4-flash-vision-exp with DeepSeek-V4.1-Flash-1017 at the Flash price. Third-party mappings to 1017 remain unconfirmed.

### How do I select deepseek-flash?

Pass the model ID shown in the quickstart.

### What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

### Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

### Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

### Where do I report quality issues?

Open an issue on the public GitHub repo or email support at contact@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation.

### Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.


### RELATED

- [deepseek-v4-flash](https://runapi.ai/models/deepseek/v4-flash.md) — by DeepSeek · Input $0.24 / 1M tokens | Output $0.96 / 1M tokens
- [deepseek-v4.1-flash-1017](https://runapi.ai/models/deepseek/v4.1-flash-1017.md) — by DeepSeek · Input $0.24 / 1M tokens | Output $0.96 / 1M tokens
- [deepseek-v4-flash-vision-exp](https://runapi.ai/models/deepseek/v4-flash-vision-exp.md) — by DeepSeek · Input $0.45 / 1M tokens | Output $1.80 / 1M tokens
- [deepseek-v4-pro](https://runapi.ai/models/deepseek/v4-pro.md) — by DeepSeek · Input $1.06 / 1M tokens | Output $3.17 / 1M tokens

### Start building with DeepSeek.

- [Create free account](https://runapi.ai/login)
- [Read the quickstart →](https://runapi.ai/docs/api/openai/chat-completions)
## Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

[Contact Us](https://runapi.ai/contact.md)



---

## More from RunAPI

- [Home](https://runapi.ai/.md)
### Product
- [Model Catalog](https://runapi.ai/models.md)
- [Pricing](https://runapi.ai/pricing.md)
- [Providers](https://runapi.ai/models#all-models)
### Developers
- [Documentation](https://runapi.ai/docs/guides)
- [SDKs](https://runapi.ai/sdk.md)
- [CLI](https://runapi.ai/cli.md)
- [MCP Server](https://runapi.ai/mcp.md)
- [x402](https://runapi.ai/x402.md)
### Guides
- [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md)
- [Cursor API Setup](https://runapi.ai/cursor-api-setup.md)
- [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md)
### Company
- [Enterprise](https://runapi.ai/contact.md)
- [Contact](https://runapi.ai/contact.md)
### Legal
- [Terms](https://runapi.ai/terms.md)
- [Privacy](https://runapi.ai/privacy.md)
- [Site index for agents](https://runapi.ai/llms.txt)

Contact: contact@runapi.ai

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "WebSite",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "potentialAction": {
      "@type": "SearchAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://runapi.ai/models?q={search_term_string}"
      },
      "query-input": "required name=search_term_string"
    }
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "Organization",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "logo": {
      "@type": "ImageObject",
      "url": "https://runapi.ai/icon.svg"
    },
    "sameAs": [
      "https://github.com/runapi-ai"
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "SoftwareApplication",
    "name": "DeepSeek V4.1 Flash 1017",
    "applicationCategory": "DeveloperApplication",
    "alternateName": "deepseek-flash"
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "BreadcrumbList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "position": 1,
        "name": "Home",
        "item": "https://runapi.ai/"
      },
      {
        "@type": "ListItem",
        "position": 2,
        "name": "Models",
        "item": "https://runapi.ai/models"
      },
      {
        "@type": "ListItem",
        "position": 3,
        "name": "DeepSeek",
        "item": "https://runapi.ai/models/deepseek"
      },
      {
        "@type": "ListItem",
        "position": 4,
        "name": "DeepSeek V4.1 Flash 1017",
        "item": "https://runapi.ai/models/deepseek/v4.1-flash"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "HowTo",
    "name": "Use deepseek-flash with a model skill",
    "description": "Call deepseek-flash from the DeepSeek family through RunAPI: per-token pricing, model ID, supported API formats, and setup guide.",
    "totalTime": "PT5M",
    "step": [
      {
        "@type": "HowToStep",
        "position": 1,
        "name": "Install",
        "text": "Install the model skill for the DeepSeek line. It loads docs, request formats, and pricing notes into your coding workspace.",
        "url": "https://runapi.ai/models/deepseek/v4.1-flash#how-step-1"
      },
      {
        "@type": "HowToStep",
        "position": 2,
        "name": "Configure",
        "text": "Point your SDK at https://runapi.ai and set your RunAPI API key. The same key works for every model and provider.",
        "url": "https://runapi.ai/models/deepseek/v4.1-flash#how-step-2"
      },
      {
        "@type": "HowToStep",
        "position": 3,
        "name": "Call",
        "text": "Send a request in an API format this model supports, with the model field set to the model ID on this page. RunAPI forwards it to the provider.",
        "url": "https://runapi.ai/models/deepseek/v4.1-flash#how-step-3"
      },
      {
        "@type": "HowToStep",
        "position": 4,
        "name": "Receive",
        "text": "Read the response from the same call, or stream it as it is generated. The usage field shows the tokens you are billed for.",
        "url": "https://runapi.ai/models/deepseek/v4.1-flash#how-step-4"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "Is DeepSeek V4.1 Flash a new model or a retrained V4 Flash?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "It is a new model. DeepSeek built it on a new causal encoder-decoder architecture with 552B total parameters, then trained it with new pre-training methods and larger-scale RL. The July 2026 V4 Flash update had kept the earlier architecture and was only post-trained again."
        }
      },
      {
        "@type": "Question",
        "name": "How does V4.1 Flash score against V4 Flash?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "On DeepSeek's published numbers, Terminal-Bench 2.1 went from 82.7 to 90.6, CyberGym from 76.7 to 88.1, and Agents' Last Exam from 25.2 to 31.8. All three figures are DeepSeek's own, taken from its change log."
        }
      },
      {
        "@type": "Question",
        "name": "What context window and output limit does V4.1 Flash have?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options."
        }
      },
      {
        "@type": "Question",
        "name": "Does V4.1 Flash support tool calling and JSON output?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes. DeepSeek's model table for V4.1 Flash marks tool calls and JSON output as supported."
        }
      },
      {
        "@type": "Question",
        "name": "Do requests to deepseek-v4-flash still work?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Use deepseek-flash for new code. DeepSeek documents that its official direct API serves the retired names deepseek-v4-flash and deepseek-v4-flash-vision-exp with DeepSeek-V4.1-Flash-1017 at the Flash price. Third-party mappings to 1017 remain unconfirmed."
        }
      },
      {
        "@type": "Question",
        "name": "How do I select deepseek-flash?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Pass the model ID shown in the quickstart."
        }
      },
      {
        "@type": "Question",
        "name": "What's the rate limit on this variant?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades."
        }
      },
      {
        "@type": "Question",
        "name": "Can I switch variants later?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape."
        }
      },
      {
        "@type": "Question",
        "name": "Does it stream?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery."
        }
      },
      {
        "@type": "Question",
        "name": "Where do I report quality issues?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Open an issue on the public GitHub repo or email support at contact@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation."
        }
      },
      {
        "@type": "Question",
        "name": "Do I need a separate provider account?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider."
        }
      }
    ]
  }
]
```
