DeepSeek: DeepSeek V4.1 Flash 1017

3 providers live

deepseek/deepseek-v4.1-flash-1017

3 live providers
100% uptime
0.58 s first token
193 tok/s output
25% off

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

Context: 1M; tokens
Max output: 128K; tokens
Input: ~~$0.20~~ $0.15; per million tokens, 25% off
Output: ~~$0.60~~ $0.45; per million tokens, 25% off

Providers

Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.Benchmarks

Live providers of DeepSeek V4.1 Flash 1017, in the router's order
Who answers now	Input per 1M	First token
llm.buzz25% offpicked	~~$0.20~~ $0.15	4.29 s
DeepInfra	$0.20	0.69 s
Prime Intellect	$0.30	0.58 s

llm.buzz answers now: lowest price.

First token is the 24-hour median. If the pick fails, the next one answers at its own price.

#	Provider	Input	Output	Cache read	Latency	Throughput	Uptime (3d)
1	llm.buzzAuto25% offNon-EU Data policy not declared	~~$0.20~~ $0.15	~~$0.60~~ $0.45	~~$0.006~~ $0.0045	4.29 s	112 tok/s	95.8%
2	DeepInfraNon-EU Data policy not declared	$0.20	$0.60	$0.006	0.69 s	45 tok/s	98.6%
3	Prime IntellectNon-EU Data policy not declared	$0.30	$1.20	$0.006	0.58 s	193 tok/s	100%

Want to serve this model?Become a provider

Price history

No price changes since Oct 20, 2026. The history shows prices before discounts.

DeepInfra$0.20 in, $0.60 out
Prime Intellect$0.30 in, $1.20 out

Performance

Last 24 hours, from llm.buzz's test requests

Throughput (tok/s)

llm.buzz112 tok/s
DeepInfra45 tok/s
Prime Intellect193 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 09:00	112 tok/s	112 tok/s	112 tok/s
llm.buzz	Oct 26, 13:00	54 tok/s	54 tok/s	54 tok/s
llm.buzz	Oct 26, 18:00	54 tok/s	54 tok/s	54 tok/s
llm.buzz	Oct 26, 22:00	161 tok/s	161 tok/s	161 tok/s
llm.buzz	Oct 27, 02:00	161 tok/s	161 tok/s	161 tok/s
llm.buzz	Last 24 hours	112 tok/s	54 tok/s	54 tok/s
DeepInfra	Oct 26, 08:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 12:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 16:00	31 tok/s	31 tok/s	31 tok/s
DeepInfra	Oct 26, 21:00	78 tok/s	78 tok/s	78 tok/s
DeepInfra	Oct 27, 02:00	54 tok/s	54 tok/s	54 tok/s
DeepInfra	Last 24 hours	45 tok/s	31 tok/s	31 tok/s
Prime Intellect	Oct 26, 08:00	161 tok/s	161 tok/s	161 tok/s
Prime Intellect	Oct 26, 12:00	193 tok/s	193 tok/s	193 tok/s
Prime Intellect	Oct 26, 17:00	193 tok/s	193 tok/s	193 tok/s
Prime Intellect	Oct 26, 21:00	232 tok/s	232 tok/s	232 tok/s
Prime Intellect	Oct 27, 02:00	93 tok/s	93 tok/s	93 tok/s
Prime Intellect	Last 24 hours	193 tok/s	93 tok/s	93 tok/s

Latency (time to first token)

llm.buzz4.29 s
DeepInfra0.69 s
Prime Intellect0.58 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 09:00	4.29 s	4.29 s	4.29 s
llm.buzz	Oct 26, 13:00	31.8 s	31.8 s	31.8 s
llm.buzz	Oct 26, 18:00	7.41 s	7.41 s	7.41 s
llm.buzz	Oct 26, 22:00	1.72 s	1.72 s	1.72 s
llm.buzz	Oct 27, 02:00	2.07 s	2.07 s	2.07 s
llm.buzz	Last 24 hours	4.29 s	31.8 s	31.8 s
DeepInfra	Oct 26, 08:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 26, 12:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 26, 16:00	1.20 s	1.20 s	1.20 s
DeepInfra	Oct 26, 21:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 27, 02:00	0.69 s	0.69 s	0.69 s
DeepInfra	Last 24 hours	0.69 s	1.20 s	1.20 s
Prime Intellect	Oct 26, 08:00	0.69 s	0.69 s	0.69 s
Prime Intellect	Oct 26, 12:00	0.58 s	0.58 s	0.58 s
Prime Intellect	Oct 26, 17:00	0.48 s	0.48 s	0.48 s
Prime Intellect	Oct 26, 21:00	0.48 s	0.48 s	0.48 s
Prime Intellect	Oct 27, 02:00	0.58 s	0.58 s	0.58 s
Prime Intellect	Last 24 hours	0.58 s	0.69 s	0.69 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

DeepInfra

Prime Intellect

Up: 95% or more served
Degraded: 85% to 95%
Down: below 85%
No data
From llm.buzz's test requests

Questions

How much does DeepSeek: DeepSeek V4.1 Flash 1017 cost?

DeepSeek: DeepSeek V4.1 Flash 1017 costs $0.15 per million input tokens and $0.45 per million output tokens at llm.buzz, the provider requests go to first, with cache reads at $0.0045 per million tokens. These prices are 25% off until 2026-11-06 00:00 UTC. Each provider sets its own price, and you pay the price of the provider that answered.

Do providers train on my prompts?

Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.

Can I serve DeepSeek: DeepSeek V4.1 Flash 1017 myself?

Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.

Similar models

Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash

Open weights. 1M context, $0.15 input and $0.50 output. 4 providers.

Google: Gemma 4 31Bgoogle/gemma-4-31b-it

Open weights. 256K context, $0.15 input and $0.30 output (25% off). 2 providers.

Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash

Open weights. 1M context, $0.14 input and $0.28 output. 1 provider.

Call it

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm.buzz/api/v1",
    api_key=os.environ["LLM_BUZZ_KEY"],
)
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llm.buzz/api/v1",
  apiKey: process.env.LLM_BUZZ_KEY,
});
const reply = await client.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash-1017",
  messages: [{ role: "user", content: "Hello" }],
});

curl https://api.llm.buzz/api/v1/chat/completions \
  -H "Authorization: Bearer $LLM_BUZZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek/deepseek-v4.1-flash-1017",
       "messages": [{"role": "user", "content": "Hello"}]}'

Endpoints

POST /api/v1/chat/completionsPOST /api/v1/responsesPOST /api/v1/messages

Authentication

Send your llm.buzz key as a Bearer token: Authorization: Bearer $LLM_BUZZ_KEY. Create keys in the console. The same key calls every model; each request pays the price of the provider that answered it.

More in Authentication and the API reference.

Call DeepSeek: DeepSeek V4.1 Flash 1017 with one keyEach request pays the price of the provider that answered it.

Get API key