DeepSeekCertifiedReleased 10/17/2026

DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 served by Alibaba Cloud Model Studio for multimodal reasoning, coding, tool calling, and structured output, with implicit prompt caching.

View API reference ↓
Input / output priceFrom$0.022 / $0.29per 1M
24h uptime99.81%
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-1017",
  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
alibaba1M393K1.1 s140 tps$0.15$0.60Read $0.015Write —6 featuresYesYesGlobalCertified
Baseten1.05M262K0.9 s173 tps$0.30$1.20Read $0.0070Write —6 featuresYesYesUSListed
boundless1.05M1.05M2.1 s285 tps$0.24$0.96Read $0.0048Write —6 featuresNoNoEUListed
DeepInfra1.05M1.05M1.7 s133 tps$0.098$0.29Read $0.0029Write —6 featuresNoYesGlobalCertified
DeepSeek1M384K1.4 s204 tps$0.15$0.60Read $0.0030Write —6 featuresNoNoGlobalCertified
digitalocean1.05M1.05M0.8 s159 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalListed
Fireworks1.05M1.05M1.3 s255 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesUSCertified
gmicloud1.05M1.05M0.7 s—$0.18$0.72Read $0.0036Write —6 featuresNoNoGlobalListed
inference-net262K131K0.5 s—$0.30$1.00Read $0.0070Write —6 featuresNoNoGlobalCertified
morph1.05M1.05M0.6 s183 tps$0.022$0.40Read $0.0040Write —6 featuresYesYesGlobalCertified
nebius1.05M1.05M1.2 s—$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalListed
novita1.05M393K1.3 s227 tps$0.30$1.20Read $0.0060Write —6 featuresNoNoGlobalCertified
parasail1.05M1.05M1.0 s224 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalCertified
pareto1M384K2.5 s99 tps$0.075$0.30Read $0.0015Write —6 featuresNoYesGlobalCertified
particle1.05M131K0.7 s56 tps$0.13$0.50Read $0.015Write —6 featuresYesYesUSCertified
relace1.05M1.05M0.9 s199 tps$0.12$0.50Read $0.0030Write —6 featuresYesYesGlobalCertified
runinfra1.05M1.05M0.4 s68 tps$0.12$0.48Read $0.0080Write —6 featuresNoNoGlobalCertified
runware1.05M1.05M1.3 s315 tps$0.23$0.91Read $0.015Write —6 featuresYesYesGlobalListed
sail-research1.05M384K0.5 s—$0.090$0.30Read $0.0060Write —6 featuresNoNoGlobalListed
streamlake1.02M384K1.5 s—$0.30$1.20Read $0.0060Write —6 featuresNoNoGlobalListed
subconscious1M384K1.3 s142 tps$0.30$1.20Read $0.0070Write —6 featuresNoNoGlobalListed
telnyx1.05M64K0.4 s—$0.30$1.20Read $0.0060Write —6 featuresNoNoGlobalListed
Together AI1.05M1.05M1.3 s267 tps$0.30$1.20Read $0.0060Write —6 featuresYesYesGlobalCertified
wafer1M1M0.4 s154 tps$0.079$0.50Read $0.0079Write —6 featuresYesYesUSCertified

Uptime

24 hours

Request success rate per provider.

alibaba99.93%
Baseten100.00%
boundless99.91%
DeepInfra99.92%
DeepSeek99.94%
digitalocean99.97%
Fireworks99.99%
gmicloud99.67%
inference-net99.87%
morph100.00%
nebius99.90%
novita100.00%
parasail99.21%
pareto99.99%
particle100.00%
relace99.97%
runinfra98.56%
runware99.19%
sail-research100.00%
streamlake100.00%
subconscious100.00%
telnyx99.49%
Together AI99.95%
wafer100.00%

Throughput

last hour

P50 output tokens per second.

runware315 tps
boundless285 tps
Together AI267 tps
Fireworks255 tps
novita227 tps
parasail224 tps
DeepSeek204 tps
relace199 tps
morph183 tps
Baseten173 tps
digitalocean159 tps
wafer154 tps
subconscious142 tps
alibaba140 tps
DeepInfra133 tps
pareto99 tps
runinfra68 tps
particle56 tps
gmicloud—
inference-net—
nebius—
sail-research—
streamlake—
telnyx—

Latency

last hour

P50 time to first token.

wafer0.4 s
telnyx0.4 s
runinfra0.4 s
sail-research0.5 s
inference-net0.5 s
morph0.6 s
gmicloud0.7 s
particle0.7 s
digitalocean0.8 s
Baseten0.9 s
relace0.9 s
parasail1.0 s
alibaba1.1 s
nebius1.2 s
subconscious1.3 s
runware1.3 s
Fireworks1.3 s
novita1.3 s
Together AI1.3 s
DeepSeek1.4 s
streamlake1.5 s
DeepInfra1.7 s
boundless2.1 s
pareto2.5 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-1017",
  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-1017. 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 1017 supports up to 262,144 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-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-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