Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

DeepSeek V4 Flash

deepseek-v4-flashby DeepSeek
Try in Chat

Context

1.05M

Max output

384K

Price per million tokens

$0.19in$0.028cached$0.51out

Speed

89 tok/s

Released

Apr 2026

Waterfall

  1. 1
    Azure Foundry via Experiential Cloud$0.19/$0.5199.4% up89 tok/s1.37s

Quickstart

I want you to route my LLM calls for "deepseek-v4-flash" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.ai/v1 as the base URL.
2. Securely ask me for my API key. Authenticate with my Experiential key from EXPLABS_API_KEY. I can create one under Settings -> API Keys.
3. Use the model id "deepseek-v4-flash" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text

Sampling

Temperature0-2Top-p0.01-1Stop sequencesLogprobs

Tools & structure

ToolsParallel tool callsStructured output

Reasoning

Reasoningnone · high · maxDefaultnone

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceAzure OpenAI docs

Benchmarks7
BenchmarkScoreSource
MMLU-ProHugging Face · Aug 202686.4%Hugging Face · Aug 2026
GPQA DiamondHugging Face · Aug 202688.1%Hugging Face · Aug 2026
SWE-bench VerifiedHugging Face · Aug 202679.0%Hugging Face · Aug 2026
LiveBenchpublic leaderboard · Aug 202665.5%public leaderboard · Aug 2026
AIME 2026public leaderboard · Aug 202695.8%public leaderboard · Aug 2026
Humanity's Last ExamHugging Face · Aug 202634.8%Hugging Face · Aug 2026
Terminal-BenchHugging Face · Aug 202656.9Hugging Face · Aug 2026
Providers serving this model5
Status
Azure Foundry via Experiential CloudexperientialDeepSeek-V4-Flash89 tok/s1.37s99.4%#1 / 21.05M384K$0.19Free 25% · Pro 50% · Max 75% · Ultra 100% off$0.51cache$0.028-no dataactivemeasured
HHuawei Cloud via Experiential Cloudexperiential63.3 tok/s1.18s37.3%#2 / 21.05M384K$0.14Free 25% · Pro 50% · Max 75% · Ultra 100% off$0.27$0.14-no dataactivemeasured
Azure FoundryFW-DeepSeek-V4-Flash89 tok/s1.37s99.4%-1.05M384K$0.089≈$0.18≈cache$0.018≈-no dataactivemeasured
Azure FoundryDeepSeek-V4-Flash-2026-04-23deployed 2026-04-2389 tok/s1.37s99.4%-1.05M384K$0.089≈$0.18≈cache$0.018≈-no dataactivemeasured
Fireworksno datano data99.9%-1.05M384K$0.089≈$0.18≈cache$0.018≈-ZDRactiveestimated
Hugging Face