Requesty
Sign in

identity

open weights
DeepSeek logo

deepseek-v4-flash-0731DeepSeek

from /1M in$0.07deepinfra inc.
context1.0M1.0M out
best ttft64mssference
price spread6.4x9 endpoints
endpoints
9
regions
2
best tok/s
239
api
chat
released
July 2026
eu routing
available

capabilities 4/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 6.4x more on scaleway sas than on deepinfra inc.. That is what the endpoints table is for.

endpoints

9 / 2 regions
Providers serving deepseek-v4-flash-0731, with pricing and measured performance. Best value in each column is coloured.
#flags
1DeepInfra Inc.Global1.0M$0.07$0.14$0.01931ms79.0zdr
2Runware Inc.Global1.0M$0.08$0.15$0.012.18s116.0-zdr
3DeepInfra Inc.Global1.0M$0.09$0.18$0.02931ms79.0zdr
4Sail Research Co.Global1.0M$0.09$0.18$0.024.44s169.0-zdr
5Novita AIGlobal1.0M$0.14$0.28$0.032.36s71.0-zdr
6Fireworks AIGlobal1M$0.22$0.66$0.00701.01s78.0zdr
7TensorX Ltd.EU1.0M$0.25$0.30$0.06899ms78.0zdr
8sferenceEU1.0M$0.28$0.56$0.0764ms172.0zdr
9Scaleway SASEU256K$0.46$0.93$0.091.14s239.0-zdr
provider price, no markupper 1M tokensblank where no qualifying sample

measured

through Sep 12
median
-791ms4.13s9.06s07-0608-0309-073.45s2.21s2.06s1.71s1.47s1.36s999ms789ms90ms
hover the plot for weekly values
time to first token per provider: current value, window low and high, and change across the window
providernowlowhighchange
sference64ms30ms506ms-82%
DeepSeek881ms716ms958ms-5.1%
TensorX Ltd.899ms999ms2.11s-12%
DeepInfra Inc.931ms874ms1.83s-6.6%
Fireworks AI1.01s1.09s1.54s+8.5%
Scaleway SAS1.14s385ms1.36s+253%
Runware Inc.2.18s1.31s2.21s+69%
Novita AI2.36s1.97s5.47s-5.2%
Sail Research Co.4.44s3.45s8.24s-58%

median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.

Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond90.8
Coding Index69.1
SciCode50.3
Humanity's Last Exam38.6
Intelligence Index34.5
5 evalsmean56.7

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-07-31.

call it

model=
deepseek-v4-flash-0731

requesty routes this id across every provider serving deepseek-v4-flash-0731, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it

Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.

quickstart

openai compatible
main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="deepseek-v4-flash-0731",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models

notes

reference

DeepSeek V4 Flash 0731 is the official release of DeepSeek V4 Flash, superseding the preview version, with substantially enhanced agentic capabilities. A 304B parameter open-source Mixture-of-Experts model with speculative decoding, 1M token context, optimized for fast, cost-efficient inference with strong reasoning, coding, and function calling performance.

questions 7

Which providers serve deepseek-v4-flash-0731?
deepseek-v4-flash-0731 is available from 8 providers through Requesty: DeepInfra Inc., Runware Inc., Sail Research Co., Novita AI, Fireworks AI, TensorX Ltd.. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does deepseek-v4-flash-0731 cost?
Pricing starts at $0.07 per million input tokens and $0.14 per million output tokens on the cheapest provider. Prices vary by provider and region; the table above shows every endpoint. Requesty charges exactly what the upstream provider charges, with no markup.
Is deepseek-v4-flash-0731 open weights?
Yes. deepseek-v4-flash-0731 is an open-weights model from DeepSeek, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of deepseek-v4-flash-0731?
deepseek-v4-flash-0731 supports up to 1.0M tokens of context, with up to 1.0M output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for deepseek-v4-flash-0731?
In recent production traffic through Requesty, sference had the lowest median time to first token (64ms) for deepseek-v4-flash-0731. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use deepseek-v4-flash-0731 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "deepseek-v4-flash-0731" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call deepseek-v4-flash-0731 by its managed id or a provider id?
Use the managed id, "deepseek-v4-flash-0731". Requesty picks which of the 8 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "deepseek-v4-flash-0731@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "deepinfra/deepseek-v4-flash-0731:flex" only when you need one specific deployment and want no failover.

more from deepseek 6

Other DeepSeek models
modelcontextfrom /Mproviders
deepseek-v4.1-flash1.0M$0.223
deepseek-v4-flash-vision-exp1.0M$0.221
deepseek-v4-pro-08131.0M$1.304
deepseek-v4-pro-04241.0M$1.044
deepseek-v4-flash-04241.0M$0.074
deepseek-v3.2164K$0.272

route deepseek-v4-flash-0731 through one endpoint

One key for 8 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology

deepseek-v4-flash-07318 providers9 endpointsfrom $0.07 /1M inctx 1.0Mttft 64msspread 6.4xupdated Sep 12