DeepSeek: DeepSeek V4 Flash 0731

3 providers live

deepseek/deepseek-v4-flash-0731

3 live providers
100% uptime
0.40 s first token
134 tok/s output

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.

Context: 1M; tokens
Max output: 384K; tokens
Input: $0.461; per million tokens
Output: $0.9219; per million tokens

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 Flash 0731, in the router's order
Who answers now	Input per 1M	First token
ScalewayEUpicked	$0.461	0.40 s
DeepInfra	$0.06	0.69 s
Prime Intellect	$0.44	0.69 s

Scaleway answers now: fastest first token.

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	ScalewayEU Data policy not declared	$0.461	$0.9219	$0.0922	0.40 s	134 tok/s	100%
2	DeepInfraNon-EU Data policy not declared	$0.06	$0.18	$0.015	0.69 s	45 tok/s	100%
3	Prime IntellectNon-EU Data policy not declared	$0.44	$1.32	n/a	0.69 s	134 tok/s	98.6%

Want to serve this model?Become a provider

Price history

Input price since Oct 20, 2026, in USD per million tokens.

DeepInfra
Prime Intellect
Scaleway

Data table

Provider	From	Input	Output
DeepInfra	Oct 20, 2026	$0.06	$0.18
Prime Intellect	Oct 21, 2026	$0.44	$1.32
Scaleway	Oct 21, 2026	$0.4621	$0.9242
Scaleway	Oct 22, 2026	$0.4629	$0.9257
Scaleway	Oct 22, 2026	$0.4617	$0.9233
Scaleway	Oct 23, 2026	$0.4612	$0.9224
Scaleway	Oct 26, 2026	$0.461	$0.9219

Performance

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

Throughput (tok/s)

Scaleway134 tok/s
DeepInfra45 tok/s
Prime Intellect134 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
Scaleway	Oct 26, 08:00	134 tok/s	134 tok/s	134 tok/s
Scaleway	Oct 26, 12:00	78 tok/s	78 tok/s	78 tok/s
Scaleway	Oct 26, 16:00	134 tok/s	134 tok/s	134 tok/s
Scaleway	Oct 26, 20:00	161 tok/s	161 tok/s	161 tok/s
Scaleway	Oct 27, 01:00	193 tok/s	193 tok/s	193 tok/s
Scaleway	Last 24 hours	134 tok/s	78 tok/s	78 tok/s
DeepInfra	Oct 26, 05:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 09:00	26 tok/s	26 tok/s	26 tok/s
DeepInfra	Oct 26, 13:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 17:00	31 tok/s	31 tok/s	31 tok/s
DeepInfra	Oct 26, 22:00	54 tok/s	54 tok/s	54 tok/s
DeepInfra	Oct 27, 03:00	15 tok/s	15 tok/s	15 tok/s
DeepInfra	Last 24 hours	45 tok/s	15 tok/s	15 tok/s
Prime Intellect	Oct 26, 06:00	134 tok/s	134 tok/s	134 tok/s
Prime Intellect	Oct 26, 10:00	401 tok/s	401 tok/s	401 tok/s
Prime Intellect	Oct 26, 15:00	134 tok/s	134 tok/s	134 tok/s
Prime Intellect	Oct 26, 19:00	65 tok/s	65 tok/s	65 tok/s
Prime Intellect	Oct 26, 23:00	65 tok/s	65 tok/s	65 tok/s
Prime Intellect	Last 24 hours	134 tok/s	65 tok/s	65 tok/s

Latency (time to first token)

Scaleway0.40 s
DeepInfra0.69 s
Prime Intellect0.69 s

Data table

Provider	From (UTC)	p50	p90	p99
Scaleway	Oct 26, 08:00	0.40 s	0.40 s	0.40 s
Scaleway	Oct 26, 12:00	0.48 s	0.48 s	0.48 s
Scaleway	Oct 26, 16:00	0.83 s	0.83 s	0.83 s
Scaleway	Oct 26, 20:00	0.40 s	0.40 s	0.40 s
Scaleway	Oct 27, 01:00	0.33 s	0.33 s	0.33 s
Scaleway	Last 24 hours	0.40 s	0.83 s	0.83 s
DeepInfra	Oct 26, 05:00	0.83 s	0.83 s	0.83 s
DeepInfra	Oct 26, 09:00	3.57 s	3.57 s	3.57 s
DeepInfra	Oct 26, 13:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 26, 17:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 26, 22:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 27, 03:00	1.72 s	1.72 s	1.72 s
DeepInfra	Last 24 hours	0.69 s	3.57 s	3.57 s
Prime Intellect	Oct 26, 06:00	0.58 s	0.58 s	0.58 s
Prime Intellect	Oct 26, 10:00	0.58 s	0.58 s	0.58 s
Prime Intellect	Oct 26, 15:00	2.48 s	2.48 s	2.48 s
Prime Intellect	Oct 26, 19:00	0.69 s	0.69 s	0.69 s
Prime Intellect	Oct 26, 23:00	0.69 s	0.69 s	0.69 s
Prime Intellect	Last 24 hours	0.69 s	2.48 s	2.48 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

Scaleway

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 Flash 0731 cost?

DeepSeek: DeepSeek V4 Flash 0731 costs $0.461 per million input tokens and $0.9219 per million output tokens at Scaleway, the provider requests go to first, with cache reads at $0.0922 per million tokens. 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 Flash 0731 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

OpenAI: gpt-oss-120bopenai/gpt-oss-120b

Open weights. 128K context, $0.05 input and $0.25 output. 3 providers.

NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b

Open weights. 256K context, $0.085 input and $0.40 output. 1 provider.

Z.ai: GLM 5.3z-ai/glm-5.3

Open weights. 1M context, $0.98 input and $3.08 output. 5 providers.

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-flash-0731",
    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-flash-0731",
  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-flash-0731",
       "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 Flash 0731 with one keyEach request pays the price of the provider that answered it.

Get API key

DeepSeek: DeepSeek V4 Flash 0731

Providers

Price history

Performance

Throughput (tok/s)

Latency (time to first token)

Uptime

Questions

Similar models

Call it

Authentication

README