---
title: DeepSeek V4 Flash
description: A throughput-oriented DeepSeek model (April snapshot 0423): mixture-of-experts with 284B total and 13B active parameters, plus hybrid attention for cheaper long inputs. It fits coding assistants, chat products and agents where latency and price matter, offers reasoning levels up to xhigh, a 1M-token context and tool calling.
keywords: deepseek-v4-flash
---

## Overview {#overview}

:::figures
| label | value | unit |
| --- | --- | --- |
| Context | 1M | tokens |
| Max output | 943.7K | tokens |
| Input | 0.1 USD (0.106 USD) | per 1M tokens |
| Output | 0.2 USD (0.212 USD) | per 1M tokens |
| Released | 24 April 2026 |  |
:::

:::deflist
| field | what it is |
| --- | --- |
| Model ID | **deepseek-v4-flash** |
:::

## Start with DeepSeek V4 Flash {#quickstart}

The model name is already filled in. Mint a key in the console, put it in an environment variable, and the call below runs as it stands — provided the organization’s wallet holds funds: a call with nothing to pay with answers 402.

:::code-group
```bash title=cURL
curl https://api.kumorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $KUMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-flash",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain tokens in one line."
    }
  ]
}'
```
```python title=Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.kumorouter.com/v1",
    api_key=os.environ["KUMO_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain tokens in one line."}],
)
print(response.choices[0].message.content)
```
```typescript title=TypeScript
import OpenAI from "openai";

const apiKey = process.env.KUMO_API_KEY;
if (!apiKey) throw new Error("Set KUMO_API_KEY before running this example.");

const client = new OpenAI({
  baseURL: "https://api.kumorouter.com/v1",
  apiKey,
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain tokens in one line." }],
});

process.stdout.write(`${response.choices[0]?.message.content ?? ""}\n`);
```
```javascript title=JavaScript
import OpenAI from "openai";

const apiKey = process.env.KUMO_API_KEY;
if (!apiKey) throw new Error("Set KUMO_API_KEY before running this example.");

const client = new OpenAI({
  baseURL: "https://api.kumorouter.com/v1",
  apiKey,
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain tokens in one line." }],
});

process.stdout.write(`${response.choices[0]?.message.content ?? ""}\n`);
```
:::

## OpenAI — API parameters {#chat_completions-parameters}

Authorization: Bearer $KUMO_API_KEY

:::matrix
| Parameter | Type | Default / range | Description |
| --- | --- | --- | --- |
| model | string | Required | Published model identifier. |
| messages | array | 1–512 | Conversation messages in chronological order. |
| max_tokens | integer | ≥ 1 | Optional. A request stating neither max_tokens nor max_completion_tokens is answered under the surface default of 32768 output tokens. Model limits also apply. |
| temperature | number | 0–2 | Sampling randomness. Omission leaves the choice to the model. |
| top_p | number | 0–1 | Nucleus sampling probability mass. Omission leaves the choice to the model. |
| stop | array | ≤ 4 | Array of strings that stop generation. |
| max_completion_tokens | integer | ≥ 1 | Optional alternative to max_tokens. Stating both with DIFFERENT values is refused: a precedence rule would silently discard one of two numbers the caller deliberately wrote. |
| stream | boolean | false | Stream response events using Server-Sent Events. |
| stream_options | object | {include_usage: boolean} | Only with stream: true. include_usage adds a final usage event before [DONE]; its default is false. |
| tools | array | ≤ 128 | Function declarations. parameters carries the original JSON Schema object, up to 65536 bytes per tool, including nested objects and arrays. |
| tool_choice | string | object | auto | none | required | {type: "function", function: {name}} | auto leaves the choice to the model; none forbids a call while the declarations stay visible; required requires a call to some declared tool; the object form requires the named one. Omission leaves the choice to the model. |
:::

One completion per request. The gateway rejects frequency_penalty, presence_penalty, seed, logprobs, top_logprobs and logit_bias: each of them would change the generation or the shape of the reply, and accepting one silently would misdescribe the answer you got. n is accepted only at 1 — the protocol default and exactly what the gateway does — and an n above one is rejected. user is accepted but is not forwarded to the model, not stored and not echoed back. The same applies to strict on a function declaration and name on a tool-role message: both are accepted and not forwarded. reasoning_effort is accepted and not forwarded either: no supplier request on this platform carries a reasoning budget, so the answer comes back at the default of the model itself whatever the field says. cache_control on a message, on a content part or on a replayed tool call is accepted and not forwarded either: the supplier wire this protocol is served by has no member for a prompt-cache anchor, so the cached-token counts come back as though the anchor had not been sent. messages[].content is accepted both as a string and as a list of parts: text parts are joined in order into one text, so a request written in parts and the same request written as a string are one request. A part of kind image_url, input_audio, file or refusal is rejected naming its own type: no multimodal capability is verified on this platform for any pair, and a replayed refusal would reach the supplier as ordinary assistant speech. The developer role is accepted and forwarded as system — it is the newer name this protocol gives the instruction role. stop is array-only; tool_choice is the string mode auto, none or required, or an object naming a declared tool. json_object is refused by name: promising valid JSON says nothing about its shape.

## Identifiers {#identifiers}

:::deflist
| field | what it is |
| --- | --- |
| Canonical name | **deepseek-v4-flash** |
| Aliases | none |
| Vendor code | deepseek |
| Protocols | chat_completions |
| Modalities | text_generation |
:::

## Capabilities {#capabilities}

:::matrix
| Protocol and modality | Streaming | Tools | Structured output | Strict semantics | Structured streaming |
| --- | --- | --- | --- | --- | --- |
| Chat Completions text generation | Yes | Yes | Unverified | Unverified | Unverified |
:::

A row describes one protocol-and-modality pair rather than the model as a whole: a capability is proved on a particular surface, and the answer beside it may differ.

## How it compares {#compare}

:::matrix
| Model | Context | Max output | Input $/M | Output $/M | Modalities |
| --- | --- | --- | --- | --- | --- |
| **DeepSeek V4 Flash** | 1M | 943.7K | 0.1 USD (0.106 USD) | 0.2 USD (0.212 USD) | text generation |
| [Claude Sonnet 5](/models/claude-sonnet-5) | 1M | 128K | 1.2 USD | 6 USD | text generation |
| [Gemini 3.6 Flash](/models/gemini-3.6-flash) | 1M | 65.5K | 0.4 USD (0.351 USD) | 1.8 USD (1.753 USD) | text generation |
| [Gemini 3.8 Flash](/models/gemini-3.8-flash) | 1M | 65.5K | 0.4 USD (0.413 USD) | 2.1 USD (2.063 USD) | text generation |
| [Kimi K3](/models/kimi-k3) | 1M | 1M | 1.7 USD (1.65 USD) | 8.3 USD (8.25 USD) | text generation |
| [Claude Opus 4.8](/models/anthropic~-claude-opus-4-8) | 1M | 128K | 2.6 USD (2.55 USD) | 12.8 USD (12.75 USD) | text generation |
| [Claude Fable 5](/models/anthropic~-claude-fable-5) | 1M | 128K | 5.1 USD | 25.5 USD | text generation |
| [Claude Fable 5.1](/models/anthropic~-claude-fable-5-1) | 1M | 128K | 6 USD | 30 USD | text generation |
| [Claude Haiku 4.5](/models/anthropic~-claude-haiku-4-5) | 200K | 64K | 0.6 USD | 3 USD | text generation |
| [Claude Opus 4.5](/models/anthropic~-claude-opus-4-5-20251101) | 200K | 64K | 2.6 USD (2.55 USD) | 12.8 USD (12.75 USD) | text generation |
| [Claude Opus 4.6](/models/anthropic~-claude-opus-4-6) | 1M | 128K | 2.6 USD (2.55 USD) | 12.8 USD (12.75 USD) | text generation |
| [Claude Opus 4.7](/models/anthropic~-claude-opus-4-7) | 1M | 128K | 2.6 USD (2.55 USD) | 12.8 USD (12.75 USD) | text generation |
| [Claude Opus 5.5](/models/anthropic~-claude-opus-5-5) | 1M | 128K | 2.2 USD | 11 USD | text generation |
| [Claude Opus 5](/models/anthropic~-claude-opus-5) | 1M | 128K | 2.6 USD (2.55 USD) | 12.8 USD (12.75 USD) | text generation |
| [Claude Sonnet 5.5](/models/anthropic~-claude-sonnet-5-5) | 1M | 128K | 1.1 USD | 5.5 USD | text generation |
| [Claude Sonnet 4.5](/models/anthropic~-claude-sonnet-4-5-20250929) | 200K | 64K | 1.5 USD (1.53 USD) | 7.7 USD (7.65 USD) | text generation |
| [Claude Sonnet 4.6](/models/anthropic~-claude-sonnet-4-6) | 1M | 128K | 1.5 USD (1.53 USD) | 7.7 USD (7.65 USD) | text generation |
| [Gemini 3 Flash Preview](/models/google~-gemini-3-flash-preview) | 1M | 65.5K | 0.3 USD (0.255 USD) | 1.5 USD (1.53 USD) | text generation |
| [Gemini 3.1 Flash Lite](/models/google~-gemini-3.1-flash-lite) | 1M | 65.5K | 0.2 USD (0.15 USD) | 0.9 USD | text generation |
| [Gemini 3.1 Pro Low](/models/google~-gemini-3.1-pro-low) | 1M | 65.5K | 1.1 USD | 6.6 USD | text generation |
| [Gemini 3.6 Flash High](/models/google~-gemini-3.6-flash-high) | 1M | 65.5K | 0.4 USD (0.383 USD) | 1.9 USD (1.913 USD) | text generation |
| [Gemini 3.7 Flash High](/models/google~-gemini-3.7-flash-high) | 1M | 65.5K | 0.4 USD (0.383 USD) | 1.9 USD (1.913 USD) | text generation |
| [Gemini 3.8 Flash High](/models/google~-gemini-3.8-flash-high) | 1M | 65.5K | 0.5 USD (0.45 USD) | 2.3 USD (2.25 USD) | text generation |
| [Codex Auto Review](/models/openai~-codex-auto-review) | 1.1M | 128K | 3 USD | 18 USD | text generation |
| [GPT-5.3 Codex Spark](/models/openai~-gpt-5.3-codex-spark) | 128K | 32K | 0.9 USD (0.893 USD) | 7.1 USD (7.14 USD) | text generation |
| [GPT-5.5](/models/openai~-gpt-5.5) | 1.1M | 128K | 2.6 USD (2.55 USD) | 15.3 USD | text generation |
| [GPT-5.6 Luna](/models/openai~-gpt-5.6-luna) | 1.1M | 128K | 0.1 USD (0.102 USD) | 0.6 USD (0.612 USD) | text generation |
| [GPT-5.6 Sol](/models/openai~-gpt-5.6-sol) | 1.1M | 128K | 2 USD (2.04 USD) | 10.2 USD | text generation |
| [GPT-6.1 Sol](/models/openai~-gpt-6.1-sol) | 1.1M | 128K | 1.1 USD | 5.5 USD | text generation |
| [GPT-6 Astra](/models/openai~-gpt-6-astra) | 1.1M | 128K | 6 USD | 30 USD | text generation |
| [GPT-5.6 Terra](/models/openai~-gpt-5.6-terra) | 1.1M | 128K | 1 USD (1.02 USD) | 6.1 USD (6.12 USD) | text generation |
| [GPT-6 Sol](/models/openai~-gpt-6-sol) | 1.1M | 128K | 1.1 USD | 5.5 USD | text generation |
| [GPT-6 Luna](/models/openai~-gpt-6-luna) | 1.1M | 128K | 0.06 USD (0.055 USD) | 0.3 USD (0.275 USD) | text generation |
| [Grok 4.5](/models/xai~-grok-4.5) | 500K | 500K | 1 USD (1.02 USD) | 3.1 USD (3.06 USD) | text generation |
| [Grok 4.6](/models/xai~-grok-4.6) | 500K | 500K | 1 USD (1.02 USD) | 3.1 USD (3.06 USD) | text generation |
| [Grok 4.7](/models/xai~-grok-4.7) | 500K | 500K | 1.1 USD | 3.3 USD | text generation |
| [GLM-5.2](/models/zai~-glm-5.2) | 1M | 131.1K | 0.7 USD (0.714 USD) | 2.2 USD (2.244 USD) | text generation |
| [GLM-5.3](/models/zai~-glm-5.3) | 1M | 131.1K | 0.8 USD (0.84 USD) | 2.6 USD (2.64 USD) | text generation |
| [Claude Haiku 5.5](/models/anthropic~-claude-haiku-5-5) | 1M | 128K | 0.06 USD (0.055 USD) | 0.3 USD (0.275 USD) | text generation |
| [Mistral Large 4](/models/mistral-large-4) | 1M | 262.1K | 0.8 USD (0.79 USD) | 2.4 USD (2.426 USD) | text generation |
| [Mistral Medium 3.5](/models/mistral-medium-3-5) | 262.1K | 209.7K | 1.7 USD (1.741 USD) | 8.7 USD (8.704 USD) | text generation |
| [Devstral 2](/models/devstral-2) | 262.1K | 209.7K | 0.5 USD (0.465 USD) | 2.3 USD (2.321 USD) | text generation |
| [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) | 1M | 393.2K | 0.3 USD (0.349 USD) | 1.4 USD (1.393 USD) | text generation |
| [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | 1M | 393.2K | 1.5 USD (1.532 USD) | 4.6 USD (4.596 USD) | text generation |
| [Qwen3.8 Max 0902](/models/qwen3-8-max-0902) | 1M | 131.1K | 2.3 USD (2.321 USD) | 7 USD (6.963 USD) | text generation |
| [Qwen3.8 Flash](/models/qwen3-8-flash) | 1M | 131.1K | 0.2 USD (0.175 USD) | 0.5 USD (0.546 USD) | text generation |
| [Qwen3.8 27B](/models/qwen3-8-27b) | 1M | 235.9K | 0.05 USD (0.047 USD) | 2.7 USD (2.67 USD) | text generation |
| [Qwen3.7 Plus](/models/qwen3-7-plus) | 1M | 131.1K | 0.4 USD (0.372 USD) | 1.5 USD (1.486 USD) | text generation |
| [Qwen3 Coder Next](/models/qwen3-coder-next) | 262.1K | 235.9K | 0.1 USD (0.14 USD) | 0.9 USD (0.929 USD) | text generation |
| [MiniMax M3](/models/minimax-m3) | 1M | 512K | 0.3 USD (0.349 USD) | 1.4 USD (1.393 USD) | text generation |
| [MiniMax M2.7](/models/minimax-m2-7) | 204.8K | 176.9K | 0.3 USD (0.349 USD) | 1.4 USD (1.393 USD) | text generation |
| [Kimi K2.7 Code](/models/kimi-k2-7-code) | 262.1K | 235.9K | 0.8 USD (0.779 USD) | 3.9 USD (3.888 USD) | text generation |
| [Kimi K2.6](/models/kimi-k2-6) | 262.1K | 235.9K | 0.8 USD (0.755 USD) | 4 USD (3.958 USD) | text generation |
| [GLM-5.3 FlashX](/models/glm-5-3-flashx) | 1M | 131.1K | 0.4 USD (0.43 USD) | 1.5 USD (1.451 USD) | text generation |
| [MiMo V2.6 Pro](/models/mimo-v2-6-pro) | 1.1M | 131.1K | 0.5 USD (0.505 USD) | 1 USD (1.01 USD) | text generation |
| [MiMo V2.6 Flash](/models/mimo-v2-6-flash) | 1.1M | 131.1K | 0.2 USD (0.163 USD) | 0.3 USD (0.325 USD) | text generation |
| [Step 5 Preview](/models/step-5-preview) | 1M | 64K | 1.2 USD (1.161 USD) | 3.1 USD (3.134 USD) | text generation |
| [Step 3.7 Flash](/models/step-3-7-flash) | 262.1K | 230.4K | 0.2 USD (0.233 USD) | 1.3 USD (1.335 USD) | text generation |
| [Muse Glimmer 30B](/models/muse-glimmer-30b) | 131.1K | 16.4K | 0.3 USD (0.349 USD) | 1.4 USD (1.393 USD) | text generation |
| [Nemotron 3 Ultra](/models/nemotron-3-ultra) | 262.1K | 182.5K | 0.7 USD (0.697 USD) | 2.8 USD (2.786 USD) | text generation |
| [Nemotron 3 Super](/models/nemotron-3-super) | 262.1K | 235.9K | 0.09 USD (0.093 USD) | 0.5 USD (0.523 USD) | text generation |
| [Seed 2.1 Turbo](/models/seed-2-1-turbo) | 262.1K | 235.9K | 0.6 USD (0.581 USD) | 2.9 USD (2.902 USD) | text generation |
| [Seed 2.0 Code](/models/seed-2-0-code) | 262.1K | 131.1K | 0.6 USD (0.581 USD) | 3.5 USD (3.482 USD) | text generation |
| [Hy4 Preview](/models/hy4-preview) | 1M | 64K | 1 USD (0.968 USD) | 2.9 USD (2.903 USD) | text generation |
| [Command A+](/models/command-a-plus) | 192K | 64K | 0.3 USD (0.349 USD) | 1.7 USD (1.741 USD) | text generation |
| [Inkling](/models/inkling) | 524.3K | 471.9K | 1.2 USD (1.161 USD) | 4.7 USD (4.701 USD) | text generation |
| [LongCat 2.0](/models/longcat-2-0) | 1M | 262.1K | 0.3 USD (0.349 USD) | 1.4 USD (1.393 USD) | text generation |
| [Nova 2 Lite](/models/nova-2-lite) | 1M | 65.5K | 0.3 USD (0.349 USD) | 2.9 USD (2.902 USD) | text generation |
| [Trinity Large Thinking](/models/trinity-large-thinking) | 262.1K | 80K | 0.3 USD (0.291 USD) | 0.9 USD (0.929 USD) | text generation |
| [Solar Pro 4](/models/solar-pro-4) | 524.3K | 131.1K | 0.1 USD (0.105 USD) | 0.4 USD (0.418 USD) | text generation |
| [Aion 3.5](/models/aion-3-5) | 262.1K | 32.8K | 3.5 USD (3.482 USD) | 7 USD (6.963 USD) | text generation |
| [Laguna S 2.1](/models/laguna-s-2-1) | 1M | 131.1K | 0.1 USD (0.105 USD) | 0.2 USD (0.209 USD) | text generation |
| [Mercury 2.5](/models/mercury-2-5) | 260K | 65.5K | 0.05 USD (0.047 USD) | 0.2 USD (0.175 USD) | text generation |
| [Llama 4 Maverick](/models/llama-4-maverick) | 1M | 16.4K | 0.2 USD (0.218 USD) | 0.8 USD (0.758 USD) | text generation |
| [Granite 4.2 8B](/models/granite-4-2-8b) | 131.1K | 118K | 0.07 USD | 0.3 USD (0.291 USD) | text generation |
:::

## Prices {#pricing}

:::matrix
| Dimension | Rate |
| --- | --- |
| Input tokens | 0.1 USD (0.106 USD) per 1M tokens |
| Cache write | 0.1 USD (0.106 USD) per 1M tokens |
| Cache read | 0.02 USD (0.022 USD) per 1M tokens |
| Output tokens | 0.2 USD (0.212 USD) per 1M tokens |
:::

> [The whole price list →](https://kumorouter.com/pricing)

## Integrations {#integrations}

Every link opens its own guide with this model already chosen.

:::cards
- [Codex CLI](/codex-cli?model=deepseek-v4-flash) — A provider in config.toml, the key from an environment variable — Codex CLI runs through the gateway without changing a single habit of yours.
- [Cursor](/cursor?model=deepseek-v4-flash) — Your own key and an overridden base URL in Cursor's model settings, and the editor's chat runs through the gateway. Plus an honest list of what does not.
- [VS Code extensions](/vscode-extensions?model=deepseek-v4-flash) — Cline, Roo Code and Continue all take the same OpenAI-compatible provider: base URL, key, model ID. Here is where those fields live in each of them.
- [SDKs](/sdks?model=deepseek-v4-flash) — The official OpenAI and Anthropic SDKs, Python and Node: install, a client with the gateway's base URL and the key from the environment, one call. Your code stays your code.
- [Integrations](/integrations?model=deepseek-v4-flash) — Point the tool you already use at the gateway: a base URL and a key. A recipe for every client, step-by-step guides, and a prompt that lets your agent do the setup.
:::

> [Errors](page:errors) [Rate limits](page:limits) [Models](page:models)