deepseek-v4.1-flash

Chat model from coralbricks. One API key reaches this provider and every other model in the catalog.

Input / 1M$0.20

Output / 1M$0.63

Context1.05M

Providers 1 provider, one key

No card required. Start with 1 million free tokens.

Overview

About deepseek-v4.1-flash

deepseek-v4.1-flash is a chat model published by coralbricks, with a 1,048,576-token context window. It scores 126 on AI IQ, ranked #24. Through TrustedRouter it runs on 1 provider, with options in the US, from $0.20 per million input tokens. One provider offers zero data retention.

Model ID: coralbricks/deepseek-v4.1-flash
Publisher: coralbricks
Modes: chat
Billing: Credits

Quickstart

Set it up with your agent

Paste this into Claude Code, Cursor or any coding agent.

Use deepseek-v4.1-flash through TrustedRouter in this project.

1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
   https://api-azure.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Set the model to coralbricks/deepseek-v4.1-flash.
4. Run the tests, then show me the diff before committing.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api-azure.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
response = client.chat.completions.create(
    model="coralbricks/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)

curl https://api-azure.trustedrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "coralbricks/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Your agent will need an API key.

1 provider

Providers

Open the row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.

deepseek-v4.1-flash providers and prices per 1M tokens
Provider	Input	Cached	Output	Cost per 1M in + out	Details
CoralBricks Zero retention	$0.200	$0.01	$0.633	$0.83
Retention Zero data retention. Verification: provider E2EE not verified. Coral Bricks AI Inc. operates its own serving software on leased US infrastructure. TrustedRouter's account owner confirmed the organization-wide No content + no metadata setting on October 14, 2026. Zero data retention applies to new requests through TrustedRouter-funded routes, not every CoralBricks account. Operational counters and billing records remain; the setting does not purge previously retained data. No training on customer content. No confidential-compute or E2EE claim. TrustedRouter disables paid cache retention; free engine prefix caching remains active. Custom retained-cache TTLs are not supported. Inference is not declared 100% renewable. Provider policy source Location Operator country: US Headquarters / registered office: Not verified. Inference: United States (provider-declared); specific datacenter region is not exposed. Provider-declared US inference and data storage on leased infrastructure; no downstream inference operators. Region pinning through TR: Select provider.only=[coralbricks] with allow_fallbacks=false; no finer regional pin is available. Reviewed 2026-10-14. API documentation Trust center Full location evidence Weight format Unknown Price and speed Input $0.20045/1M · Cached input $0.01/1M · Output $0.633/1M TTFT: insufficient data Speed: insufficient data CoralBricks provider page

FAQ

Questions

What model ID should I use for deepseek-v4.1-flash?

Use coralbricks/deepseek-v4.1-flash as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Do you log my prompts or outputs?

No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.

Which providers serve deepseek-v4.1-flash?

TrustedRouter currently lists CoralBricks for deepseek-v4.1-flash. Provider availability and routing eligibility can change as catalog and health data update.

How much does deepseek-v4.1-flash cost through TrustedRouter?

The current lowest Credits input price is $0.20045/1M and the lowest Credits output price is $0.633/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for deepseek-v4.1-flash?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.

Compare

deepseek-v4.1-flash vs other models

vs GLM 5.3 All comparisons

Start building with deepseek-v4.1-flash.

No card required. Start with 1 million free tokens.