deepseek-v4.1-flashDeepSeek
- api
- chat
- hosting
- China
- model lab
- DeepSeek
- weights
- open
- added
- September 2026
- model id
- deepseek/deepseek-v4.1-flash
capabilities 4/8
3 providers serve deepseek-v4.1-flash. This page is one of them. Compare all endpoints
- input
- $0.30
- output
- $1.20
- cache write
- -
- cache read
- $0.0060
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0420 |
| 1M in + 100K out | $0.42 |
| 10M in + 1M out | $4.20 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
- median ttft
- 938ms
- median tok/s
- 89.0
- blended /1M
- $0.01
- cache hit
- 98.1%
- answered
- 99.90%
Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers
| eval | Score as a share of 100 | /100 |
|---|---|---|
| SciCode | 51.9 | |
| Intelligence Index | 39.5 | |
| Humanity's Last Exam | 39.2 | |
| 3 evals | mean | 43.5 |
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 2026-09-10.
- retention
- yes
- trains on prompts
- no
- hosted in
- China
Terms are the provider's, not Requesty's: routing a request here puts it under them. DeepSeek Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
deepseek/deepseek-v4.1-flashthis id pins the deepseek deployment, with no routing and no failover. the managed id on the canonical page routes across all 3 providers instead
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/deepseek-v4.1-flash", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, JSON output and prompt caching. Pricing per 1M tokens starts at $0.003 for cache hits, $0.15 input and $0.60 output off peak, with peak rates at double (01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday). Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants. Replaces deepseek-v4-flash and deepseek-v4-flash-vision-exp, both still accepted as aliases.
questions 6
How much does deepseek-v4.1-flash cost?
What is the context window of deepseek-v4.1-flash?
How does deepseek-v4.1-flash perform on benchmarks?
What can deepseek-v4.1-flash do?
How do I use deepseek-v4.1-flash with the OpenAI SDK?
Can I run deepseek-v4.1-flash through Requesty?
more from deepseek 3
| endpoint | ctx | in /M |
|---|---|---|
| deepseek-v4-pro-0813 | 1M | $1.32 |
| deepseek-reasoner | 1M | $0.14 |
| deepseek-chat | 1M | $0.14 |
call deepseek-v4.1-flash through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology