DeepSeekCertifiedReleased 04/23/2026

DeepSeek V4 Flash 0731

View API reference ↓
Input / output priceFrom$0.040 / $0.14per 1M
24h uptime99.96%
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-flash-0731",
  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
alibaba1M384K2.1 s—$0.22$0.66Read $0.022Write —4 featuresYesYesGlobalCertified
Baseten1M384K0.4 s155 tps$0.13$0.26Read $0.028Write —4 featuresYesYesUSCertified
boundless1.05M1.05M0.9 s—$0.040$0.21Read $0.020Write —5 featuresNoNoGlobalCertified
DeepInfra1.05M1.05M0.7 s58 tps$0.060$0.18Read $0.015Write —4 featuresNoYesGlobalCertified
digitalocean1.05M1.05M0.6 s233 tps$0.080$0.25Read $0.025Write —5 featuresYesYesGlobalCertified
gmicloud1.05M384K1.6 s—$0.29$0.86Read $0.0091Write —4 featuresNoNoGlobalCertified
inceptron1M1M0.8 s—$0.13$0.28Read $0.070Write —5 featuresNoYesGlobalCertified
morph1.05M1.05M0.6 s107 tps$0.14$0.40Read $0.036Write —4 featuresYesYesGlobalCertified
novita1.05M393K1.1 s—$0.44$1.32Read $0.028Write —4 featuresNoNoGlobalCertified
parasail1.05M1.05M0.4 s183 tps$0.14$0.28Read $0.070Write —5 featuresYesYesGlobalCertified
relace1M1M0.8 s140 tps$0.070$0.14Read $0.014Write —5 featuresYesYesGlobalCertified
runware1M384K1.1 s164 tps$0.11$0.22Read $0.022Write —5 featuresYesYesGlobalCertified
streamlake1.02M384K1.8 s—$0.44$1.32Read $0.014Write —5 featuresNoNoGlobalCertified
wafer1M1M0.4 s103 tps$0.14$0.23Read $0.14Write —4 featuresYesYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

alibaba100.00%
Baseten100.00%
boundless99.86%
DeepInfra99.99%
digitalocean100.00%
gmicloud100.00%
inceptron100.00%
morph100.00%
novita100.00%
parasail100.00%
relace99.65%
runware99.98%
streamlake99.93%
wafer100.00%

Throughput

last hour

P50 output tokens per second.

digitalocean233 tps
parasail183 tps
runware164 tps
Baseten155 tps
relace140 tps
morph107 tps
wafer103 tps
DeepInfra58 tps
alibaba—
boundless—
gmicloud—
inceptron—
novita—
streamlake—

Latency

last hour

P50 time to first token.

wafer0.4 s
Baseten0.4 s
parasail0.4 s
morph0.6 s
digitalocean0.6 s
DeepInfra0.7 s
relace0.8 s
inceptron0.8 s
boundless0.9 s
runware1.1 s
novita1.1 s
gmicloud1.6 s
streamlake1.8 s
alibaba2.1 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-flash-0731",
  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-flash-0731. 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 Flash 0731 supports up to 384,000 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 1M-token context window

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-v4.1-flash1.05M$0.30$1.20Read $0.0060Write —09/08/2026
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-pro1.05M$1.32$3.96Read $0.13Write —04/23/2026
deepseek/deepseek-v3.2128K$0.62$1.85Read —Write —12/01/2025