DeepSeek V4 Flash 0731

DeepSeekReleased Jul 31, 2026

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Try it in the estimate Compare

Input, per 1M tokens: $0.022$0.020 for holders
Output, per 1M tokens: $0.38$0.35 for holders
Context: 1M tokens
Tokens this week: None yet

Price

Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.

Charge	Agents	Holders	Per
Inputper 1M tokens	$0.022	$0.020	per 1M tokens
Outputper 1M tokens	$0.38	$0.35	per 1M tokens
Cached inputper 1M tokens	$0.022	$0.020	per 1M tokens

Price history

What an agent paid per million tokens, by day.

Unchanged since Sep 29, 2026: $0.022 in and $0.38 out per million tokens.

Usage through bInference

Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.

Last 7 days: 0
Last 30 days: 0
All time: 0

InputOutputReasoning

Where it runs

The hosts serving this model now, and how often each answered over the last day.

Use it

Two settings: our address and your agent’s key. The model is set in each call.

import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://binference.io/api/v1",Address  apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({  model: "deepseek/deepseek-v4-flash-0731",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address  -H "Authorization: Bearer $BINF_API_KEY" \Key  -H "Content-Type: application/json" \  -d '{    "model": "deepseek/deepseek-v4-flash-0731",    "messages": [{ "role": "user", "content": "Hello" }],    "max_tokens": 1024  }'

Questions

More from DeepSeek

DeepSeek V4.1 FlashDeepSeek1M$0.36 in · $1.44 out$0.33 in · $1.32 out DeepSeek V4 Flash Vision ExpDeepSeek1M$0.26 in · $0.78 out$0.24 in · $0.71 out DeepSeek V4 Pro 0813DeepSeek1M$0.47 in · $4.19 out$0.43 in · $3.85 out DeepSeek V4 Pro 0423DeepSeek1M$1.10 in · $2.20 out$1.01 in · $2.02 out

Agents

Holders

Inputper 1M tokens

$0.022

$0.020

per 1M tokens

Outputper 1M tokens

$0.38

$0.35

per 1M tokens

Cached inputper 1M tokens

$0.022

$0.020

per 1M tokens

Host	Answered, last day	Context
OpenInferenceFp8fp8, answering	97.1%	1M
RelaceFp4fp4, answering	99.8%	1M
Sail ResearchFp4fp4, answering	97.8%	1M
Sail ResearchUSfp4, answering	96.4%	1M
Reka, answering	99.5%	262K
StreamLakeFp8fp8, answering	99.5%	1M
InceptronFp4fp4, answering	100%	1M
DeepInfraFp8fp8, answering	99.9%	1M
WaferFast, answering	100%	1M
Makora, answering	99.5%	1M
DigitalOcean, answering	99.8%	1M
BaseTenFp8fp8, answering	99.9%	1M
BaseTenFp8fp8, answering	100%	1M
CoreWeaveFp8fp8, answering	99.9%	262K
NebiusFp8fp8, having trouble	92.4%	1M
Cohere, answering	99.6%	1M
Together, answering	99.7%	1M
ParasailFp8fp8, answering	99.3%	1M
MorphBf16bf16, answering	99.2%	1M
AtlasCloudFp4fp4, answering	99.8%	1M
Venice, answering	99.7%	1M
Alibaba, answering	99.7%	1M
Mancer 2Fp8fp8, answering	99.4%	1M
SiliconFlowFp8fp8, answering	99.5%	1M
GMICloudFp8fp8, answering	100%	1M
Phala, answering	100%	1M
NextBitFp8fp8, answering	99.9%	1M
NovitaFp8fp8, answering	100%	1M
BaiduFp8fp8, answering	100%	1M
Cloudflare, answering	100%	1M

Host

Answered, last day

Context

OpenInferenceFp8fp8

97.1%

RelaceFp4fp4

99.8%

Sail ResearchFp4fp4

97.8%

Sail ResearchUSfp4

96.4%

Reka

99.5%

262K

StreamLakeFp8fp8

99.5%

InceptronFp4fp4

100%

DeepInfraFp8fp8

99.9%

WaferFast

100%

Makora

99.5%

DigitalOcean

99.8%

BaseTenFp8fp8

99.9%

BaseTenFp8fp8

100%

CoreWeaveFp8fp8

99.9%

262K

NebiusFp8fp8

92.4%

Cohere

99.6%

Together

99.7%

ParasailFp8fp8

99.3%

MorphBf16bf16

99.2%

AtlasCloudFp4fp4

99.8%

Venice

99.7%

Alibaba

99.7%

Mancer 2Fp8fp8

99.4%

SiliconFlowFp8fp8

99.5%

GMICloudFp8fp8

100%

Phala

100%

NextBitFp8fp8

99.9%

NovitaFp8fp8

100%

BaiduFp8fp8

100%

Cloudflare

100%

import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://binference.io/api/v1",Address apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({ model: "deepseek/deepseek-v4-flash-0731", messages: [{ role: "user", content: "Summarize today's trades" }], max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address -H "Authorization: Bearer $BINF_API_KEY" \Key -H "Content-Type: application/json" \ -d '{ "model": "deepseek/deepseek-v4-flash-0731", "messages": [{ "role": "user", "content": "Hello" }], "max_tokens": 1024 }'

DeepSeek V4 Flash 0731

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

More from DeepSeek

Similar models

DeepSeek V4 Flash 0731

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

More from DeepSeek

Similar models

Where it runs

DeepSeek V4 Flash 0731

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

How much does DeepSeek V4 Flash 0731 cost?

How does my agent use DeepSeek V4 Flash 0731?

How much can DeepSeek V4 Flash 0731 read at once?

What can DeepSeek V4 Flash 0731 do?

Are my prompts stored?

More from DeepSeek

Similar models

DeepSeek V4 Flash 0731

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

How much does DeepSeek V4 Flash 0731 cost?

How does my agent use DeepSeek V4 Flash 0731?

How much can DeepSeek V4 Flash 0731 read at once?

What can DeepSeek V4 Flash 0731 do?

Are my prompts stored?

More from DeepSeek

Similar models

Where it runs