Models
DeepSeek V4.1 Flash
deepseek-v4.1-flashby DeepSeekZDR enforceableContext
1.05M
Max output
393K
Price per million tokens
$0.30in$0.006cached$1.20out
Fastest
597 tok/s
Released
Sep 2026
Waterfall
- 1Azure Foundry via Experiential Cloud$0.30/$1.2092.7% up145 tok/s1.83s
- 2Tencent Cloud via Experiential Cloud$0.30/$1.2099% up145 tok/s2.34s
- 3Experiential Cloud$0.30/$1.2099.9% up185 tok/s2.58s
- 4Huawei Cloud via Experiential Cloud$0.30/$1.20100% up145 tok/s2.23s
- 5wally via Experiential Cloud$0.28/$1.1899.2% up597 tok/s1.66s
- 6particle.ai via Experiential Cloud$0.070/$1100% up302 tok/s555ms
- 7wally via Experiential Cloud$0.60/$2.4099.2% up597 tok/s1.66s
- 8prism via Experiential Cloud$0.090/$1.2099.9% up--
Quickstart
I want you to route my LLM calls for "deepseek-v4.1-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. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If it isn't set, stop and tell me to create one under Settings -> API Keys and export it. 3. Use the model id "deepseek-v4.1-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, image
Sampling
Temperature*0-2Top-p*0.01-1Stop sequences*
Tools & structure
Tools*Parallel tool calls*Structured output*
Reasoning
Reasoning*none · minimal · low · medium · high · xhigh · maxDefaulthigh
Streaming
Streaming
Limits
Max-tokens fieldmax_tokens
Sending an unsupported field? See error referenceAzure OpenAI docs
Providers serving this model10
| Status | ||||||
|---|---|---|---|---|---|---|
| Experiential Cloudexperiential | 185 tok/s | 2.58s | 99.9% | $0.30Pro 100% · Max 100% · Ultra 100% off | $1.20 | active |
| wally via Experiential Cloudexperientialdeepseek-v4.1-flash | 597 tok/s | 1.66s | 99.2% | $0.28Pro 100% · Max 100% · Ultra 100% off | $1.18 | active |
| wally via Experiential Cloudexperientialdeepseek-v4.1-flash-fast | 597 tok/s | 1.66s | 99.2% | $0.60Pro 100% · Max 100% · Ultra 100% off | $2.40 | active |
| prism via Experiential Cloudexperiential | no data | no data | 99.9% | $0.090Pro 100% · Max 100% · Ultra 100% off | $1.20 | active |
| particle.ai via Experiential Cloudexperiential | 302 tok/s | 555ms | 100% | $0.070Pro 100% · Max 100% · Ultra 100% off | $1 | active |
| Azure Foundry via Experiential CloudexperientialDeepSeek-V4.1-Flash | 145 tok/s | 1.83s | 92.7% | $0.30Pro 100% · Max 100% · Ultra 100% off | $1.20 | active |
| Huawei Cloud via Experiential Cloudexperiential | 145 tok/s | 2.23s | 100% | $0.30Pro 100% · Max 100% · Ultra 100% off | $1.20 | active |
| Tencent Cloud via Experiential Cloudexperiential | 145 tok/s | 2.34s | 99% | $0.30Pro 100% · Max 100% · Ultra 100% off | $1.20 | active |
| Azure FoundryFW-DeepSeek-V4.1-Flash | 145 tok/s | 1.83s | 92.7% | no data | no data | active |
| Azure FoundryDeepSeek-V4.1-Flash-2026-09-10deployed 2026-09-10 | 145 tok/s | 1.83s | 92.7% | no data | no data | active |