DeepSeekCertifiedReleased 09/08/2026

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal interactions. It combines native multimodal capabilities with a new architecture focused on stronger performance, faster responses, and lower computational cost.

View API reference ↓
Input / output priceFrom$0.022 / $0.30per 1M
24h uptime99.84%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
alibaba1M384K1.2 s272 tps$0.15$0.60Read $0.015Write —6 featuresYesYesGlobalCertified
Baseten1.05M33K0.6 s229 tps$0.30$1.20Read $0.0070Write —6 featuresYesYesUSCertified
boundless1M384K0.4 s73 tps$0.20$1.00Read $0.010Write —6 featuresNoNoGlobalCertified
DeepInfra1.05M1.05M1.1 s153 tps$0.14$0.42Read $0.0042Write —6 featuresNoYesGlobalCertified
DeepSeek1M384K1.5 s203 tps$0.15$0.60Read $0.0030Write —6 featuresNoNoGlobalCertified
digitalocean1.05M1.05M0.7 s159 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalListed
Fireworks1.05M1.05M0.8 s93 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesUSCertified
gmicloud1.05M1.05M1.0 s95 tps$0.18$0.72Read $0.0036Write —5 featuresNoNoGlobalCertified
Google Vertex AI1.05M1.05M0.7 s43 tps$0.30$1.20Read $0.030Write —6 featuresYesYesGlobalListed
inference-net1.04M384K0.5 s—$0.30$1.00Read $0.0070Write —6 featuresNoNoGlobalCertified
modal1.05M1.05M1.6 s150 tps$0.30$1.20Read $0.030Write —6 featuresYesYesGlobalCertified
morph1.05M1.05M0.6 s150 tps$0.022$0.40Read $0.0040Write —5 featuresYesYesGlobalCertified
novita1.05M393K3.5 s158 tps$0.20$0.78Read $0.0039Write —5 featuresNoNoGlobalCertified
parasail1.05M1.05M0.3 s251 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalCertified
pareto1M384K2.1 s105 tps$0.075$0.30Read $0.0015Write —6 featuresNoYesGlobalListed
particle1.05M1.05M1.2 s160 tps$0.070$1.00Read $0.030Write —6 featuresYesYesUSCertified
relace1.05M1.05M1.2 s—$0.12$0.50Read $0.0030Write —5 featuresYesYesGlobalCertified
runinfra1.05M1.05M0.4 s—$0.11$0.46Read $0.024Write —5 featuresNoNoGlobalCertified
runware1.05M1.05M0.6 s—$0.23$0.91Read $0.015Write —6 featuresYesYesGlobalCertified
tencent1M384K3.8 s113 tps$0.15$0.60Read $0.0030Write —6 featuresNoNoGlobalListed
Together AI1.05M1.05M0.3 s401 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalCertified
wafer1.05M1.05M0.6 s247 tps$0.19$0.65Read $0.012Write —6 featuresYesYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

alibaba100.00%
Baseten99.99%
boundless99.87%
DeepInfra100.00%
DeepSeek99.99%
digitalocean99.99%
Fireworks100.00%
gmicloud99.87%
Google Vertex AI98.58%
inference-net100.00%
modal100.00%
morph99.98%
novita100.00%
parasail100.00%
pareto100.00%
particle100.00%
relace99.96%
runinfra98.37%
runware99.80%
tencent100.00%
Together AI100.00%
wafer100.00%

Throughput

last hour

P50 output tokens per second.

Together AI401 tps
alibaba272 tps
parasail251 tps
wafer247 tps
Baseten229 tps
DeepSeek203 tps
particle160 tps
digitalocean159 tps
novita158 tps
DeepInfra153 tps
morph150 tps
modal150 tps
tencent113 tps
pareto105 tps
gmicloud95 tps
Fireworks93 tps
boundless73 tps
Google Vertex AI43 tps
inference-net—
relace—
runinfra—
runware—

Latency

last hour

P50 time to first token.

Together AI0.3 s
parasail0.3 s
runinfra0.4 s
boundless0.4 s
inference-net0.5 s
runware0.6 s
wafer0.6 s
Baseten0.6 s
morph0.6 s
Google Vertex AI0.7 s
digitalocean0.7 s
Fireworks0.8 s
gmicloud1.0 s
DeepInfra1.1 s
alibaba1.2 s
relace1.2 s
particle1.2 s
DeepSeek1.5 s
modal1.6 s
pareto2.1 s
novita3.5 s
tencent3.8 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. deepseek/deepseek-v4.1-flash. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. DeepSeek V4.1 Flash supports up to 1,048,576 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1.05M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by DeepSeek

ModelContextInputOutputCacheRelease
deepseek/deepseek-v4.1-flash-1017-ultrafast1.05M$2.40$9.60Read $0.048Write —11/06/2026
deepseek/deepseek-v4.1-flash-10171.05M$0.30$1.20Read $0.0070Write —10/17/2026
deepseek/deepseek-v4.1-flash-1017-fast1.05M$0.60$2.40Read $0.014Write —10/17/2026
deepseek/deepseek-v4.1-flash-fast1.05M$0.60$2.40Read $0.014Write —09/29/2026
deepseek/deepseek-v4-flash-vision-exp1.05M$0.22$0.65Read $0.0068Write —08/21/2026
deepseek/deepseek-v4-pro-08131M$0.66$1.98Read $0.066Write —08/12/2026
deepseek/deepseek-v4-flash1M$0.13$0.26Read $0.028Write —04/23/2026
deepseek/deepseek-v4-flash-07311M$0.13$0.26Read $0.028Write —04/23/2026
deepseek/deepseek-v4-pro1.05M$1.32$3.96Read $0.13Write —04/23/2026
deepseek/deepseek-v3.2128K$0.62$1.85Read —Write —12/01/2025