DeepSeek V4 Flash (Relay)

Save 50%Relay

deepseek/deepseek-v4-flash-cheap

Discontinued — this relay tier has been merged into DeepSeek V4 Flash. Call deepseek/deepseek-v4-flash instead.

This model has been retired. Its provider no longer serves it, so it can no longer be called — this page is kept for reference. Pick another model.

Context window: 1M
Max output: 384K
Input modalities: text
Output modalities: text
Capabilities: Reasoning · Tool calling · Coding · Prompt cache
Upstream release: 2026-07-31
RouteMux name: deepseek/deepseek-v4-flash-cheap
Official ID: deepseek-v4-flash

DeepSeek V4 Flash (Relay) API pricing

Prices verified 2026-09-23

InputOfficial $0.44 / M tokens

$0.22/ M tokensSave 50%

OutputOfficial $1.32 / M tokens

$0.66/ M tokensSave 50%

Cache read $0.007/M · Cache write —/M

Estimate cost

Input tokensOutput tokens

Estimated cost$0.00286

Limited time10% 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.

Key capabilities

ReasoningTool callingCodingPrompt cache

Interface and protocols

OpenAI Chat CompletionsStreamingOpenAI ResponsesStreamingAnthropic MessagesStreaming

Use any of these IDs to call this model via the API.

RouteMux namedeepseek/deepseek-v4-flash-cheap

Official IDdeepseek-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:cheap",
    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)

0 requests · last 30 days

Total usage—

P50 first-token latencyInsufficient data (0 requests)

Avg throughputInsufficient data (0 requests)

Success rate—

Uptime · 24h

—

Success rate · 60d · from real requests

DeepSeek V4 Flash (Relay) FAQ

›What is DeepSeek V4 Flash (Relay)?

Discontinued — this relay tier has been merged into DeepSeek V4 Flash. Call deepseek/deepseek-v4-flash instead.

›How large is the context window of DeepSeek V4 Flash (Relay)?

DeepSeek V4 Flash (Relay) supports a context window of up to 1M tokens, with up to 384K output tokens per request.

›How much does the DeepSeek V4 Flash (Relay) API cost?

Through RouteMux, DeepSeek V4 Flash (Relay) costs $0.22 for input and $0.66 for output (USD per 1M tokens), below the official list price.

›Which input and output modalities does DeepSeek V4 Flash (Relay) support?

DeepSeek V4 Flash (Relay) accepts text as input and produces text as output.

›When was DeepSeek V4 Flash (Relay) released?

DeepSeek V4 Flash (Relay) was released on July 31, 2026.

View as Markdown