Scheduled for retirement on Dec 15, 2026. Still available at the prices below until then.
Context
1M
Max output
1M
Serving providers
12
Cheapest input
$0.01 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
187 t/s
tokens / second
Time to first token
0.96s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.3 | default | — | |||||||||||||
| Automation Bench | 0.7 | default | — | |||||||||||||
| CritPt | 14% | default | — | |||||||||||||
| GDPval (normalized)Frozen Aug 18, 2026 | 55% | default | — | |||||||||||||
| Harvey Lab | 0.0 | default | — | |||||||||||||
| Humanity's Last Exam | 39% | default | — | |||||||||||||
| IT-Bench SRE | 47% | default | — | |||||||||||||
| Long-Context Reasoning | 84% | default | — | |||||||||||||
| MMMU-Pro | 77% | default | — | |||||||||||||
| Omniscience | -5.3 | default | — | |||||||||||||
| Omniscience Accuracy | 0.5 | default | — | |||||||||||||
| Omniscience Non Hallucination | 0.0 | default | — | |||||||||||||
| SciCode | 52% | default | — | |||||||||||||
| Terminal Bench40 | 0.3 | default | — | |||||||||||||
| ||||||||||||||||
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.01 to $0.30 per 1M tokens across 12 providers, so the dearest route costs 2900% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CoralbricksCheapest | $0.01 | $1.20 | 1 | ||||||||||||||||
Standardcoralbricks/deepseek-v4.1-flash
| |||||||||||||||||||
| OpenRouter | $0.013 | $0.891 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v4.1-flash
| |||||||||||||||||||
| Sail | $0.15 | $0.60 | 1 | ||||||||||||||||
Standardsail/deepseek-ai/DeepSeek-V4.1-Flash
| |||||||||||||||||||
| Prism | $0.17 | $0.63 | 1 | ||||||||||||||||
Standardprism/deepseek-v4.1-flash
| |||||||||||||||||||
| Wandb | $0.20 | $0.65 | 1 | ||||||||||||||||
Standardwandb/deepseek-ai/DeepSeek-V4.1-Flash
| |||||||||||||||||||
| Azure | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardazure_ai/deepseek-v4.1-flash
| |||||||||||||||||||
| Baseten | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardbaseten/deepseek-ai/DeepSeek-V4.1-Flash
| |||||||||||||||||||
| Fireworks AI | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash
| |||||||||||||||||||
| Vercel is dearest at $0.60 / $2.40 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 95% since first tracked
Cost calculator
estimate your monthly spend on this model$98
estimated / month
Model IDs
copy the exact identifier for your platformcoralbricks/deepseek-v4.1-flashdeepseek/deepseek-v4.1-flashdeepseek/deepseek-v4.1-flash:batchsail/deepseek-ai/DeepSeek-V4.1-Flashprism/deepseek-v4.1-flashwandb/deepseek-ai/DeepSeek-V4.1-Flashtencent/deepseek-v4.1-flashdeepseek/deepseek-v4.1-flashtogether_ai/deepseek-ai/DeepSeek-V4.1-Flashazure_ai/deepseek-v4.1-flashnebius/deepseek-ai/DeepSeek-V4.1-Flashbaseten/deepseek-ai/DeepSeek-V4.1-Flashfireworks_ai/accounts/fireworks/models/deepseek-v4p1-flashdeepseek/deepseek-v4.1-flash-fast
Frequently asked questions
DeepSeek V4.1 Flash pricing, context and availabilityIs DeepSeek V4.1 Flash still available?
Yes. DeepSeek V4.1 Flash is scheduled for retirement on 2026-12-15.
How much does DeepSeek V4.1 Flash cost?
DeepSeek V4.1 Flash costs $0.01 per 1M input tokens from Coralbricks, and $0.60 per 1M output tokens from Sail. Across 12 serving providers, input prices range from $0.01 to $0.30 per 1M tokens.
What is the context window of DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is available from 12 serving providers, each with its own pricing and model ID. Coralbricks is currently the cheapest.
What can DeepSeek V4.1 Flash do?
DeepSeek V4.1 Flash supports image input (vision), tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0423$0.09/1M · 18 providersDeepSeek V4 Flash 0731$0.016/1M · 16 providersDeepSeek V4 Pro 0423$0.435/1M · 16 providersR1$0.40/1M · 14 providersDeepSeek V3 0324$0.20/1M · 12 providersDeepSeek V4 Pro 0813$0.66/1M · 12 providersDeepSeek R1 Distill Llama 70B$0.20/1M · 11 providersDeepSeek V3.1$0.25/1M · 11 providers
Popular comparisons
head-to-head pages featuring DeepSeek V4.1 Flash
DeepSeek V4.1 Flash vs Claude Fable 5.1side-by-side pricing & benchmarks DeepSeek V4.1 Flash vs Claude Opus 5side-by-side pricing & benchmarks
DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
DeepSeek V4.1 Flash vs Gemini 3.7 Flashside-by-side pricing & benchmarks DeepSeek V4.1 Flash vs Gemini 3.8 Flashside-by-side pricing & benchmarks Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI