Claude models and GPT-5.6 Luna are now available to accounts that have topped up at least once. Top up any amount to unlock them — bonus credits can pay for them too. All other models are unaffected.Top up
DeepSeek

DeepSeek V4 Flash

Official

deepseek/deepseek-v4-flash

DeepSeek V4 Flash — fast, cheapest V4, thinking + non-thinking modes.

Context window
1M
Max output
393K
Input modalities
text
Output modalities
text
Capabilities
Reasoning · Tool Calling · Coding · Cache
Upstream release
2026-07-31
RouteMux name
deepseek/deepseek-v4-flash
Live model playground

Try DeepSeek V4 Flash here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

streamchat
1Configure input
0 / 20,000
Maximum estimated cost
2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

conversation

DeepSeek V4 Flash API pricing

Source: deepseek_official_2026-08-17_peak_fx7.15 · Verified 2026-06-08

InputOfficial $0.41958 / M tokens
$0.41958/ M tokens
OutputOfficial $1.258741 / M tokens
$1.258741/ M tokens

Cache read $0.013986/M · Cache write /M

Estimate cost

Estimated cost$0.005455

Limited time20% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Sign up and claimNo subscription. Pay for what you use.

Key capabilities

ReasoningTool CallingCodingCache

Interface and protocols

OpenAI Chat CompletionsStreamingOpenAI ResponsesStreamingAnthropic MessagesStreaming

Use either ID to call this model via the API.

RouteMux namedeepseek/deepseek-v4-flash

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Performance (last 30 days)

DeepSeek V4 Flash FAQ

What is DeepSeek V4 Flash?

DeepSeek V4 Flash — fast, cheapest V4, thinking + non-thinking modes.

How large is the context window of DeepSeek V4 Flash?

DeepSeek V4 Flash supports a context window of up to 1M tokens, with up to 393K output tokens per request.

How much does the DeepSeek V4 Flash API cost?

Through RouteMux, DeepSeek V4 Flash costs $0.41958 for input and $1.258741 for output (USD per 1M tokens), below the official list price.

How do I call DeepSeek V4 Flash via API?

DeepSeek V4 Flash is OpenAI-compatible: point your base URL at RouteMux and set the model field to deepseek/deepseek-v4-flash — no code changes needed.

Which input and output modalities does DeepSeek V4 Flash support?

DeepSeek V4 Flash accepts text as input and produces text as output.

When was DeepSeek V4 Flash released?

DeepSeek V4 Flash was released on July 31, 2026.