Scheduled for retirement on Feb 20, 2028. Still available at the prices below until then.
Context
1M
Max output
1M
Serving providers
18
Cheapest input
$0.09 /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 Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
37 t/s
tokens / second
Time to first token
1.68s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.3 | default | — | |||||||||||||||||
| AA-BriefcaseUndated | 16% | default | — | |||||||||||||||||
| Automation Bench | 0.3 | high | — | |||||||||||||||||
| ||||||||||||||||||||
| CritPt | 7% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval (normalized)Frozen Aug 18, 2026 | 27% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 89% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Harvey Lab | 0.8 | default | — | |||||||||||||||||
| Humanity's Last Exam | 35% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 79% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 32% | default | — | |||||||||||||||||
| Long-Context Reasoning | 74% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -23.1 | high | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.1 | high | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 45% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Verified | 79% | default | — | |||||||||||||||||
| Terminal Bench40 | 0.0 | high | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 39% | high | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 62% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 31% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ²-bench | 96% | high | — | |||||||||||||||||
| ||||||||||||||||||||
We cannot tell whether this benchmark is still being published. Treat these scores as undated.
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 detail
cost beyond the standard rate · source: models.devReasoning tokens
$0.60
per 1M · thinking output
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.09 to $0.30 per 1M tokens across 18 providers, so the dearest route costs 233% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.09 | $0.18 | 1 | ||||||||||||||||
Standarddeepinfra/deepseek-ai/DeepSeek-V4-Flash
| |||||||||||||||||||
| OpenRouter | $0.091 | $0.182 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v4-flash
| |||||||||||||||||||
| Pinstripes | $0.10 | $0.20 | 1 | ||||||||||||||||
Standardpinstripes/ps/deepseek-v4-flash
| |||||||||||||||||||
| VercelVercel reseller quote | $0.13 | $0.26 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v4-flash
| |||||||||||||||||||
| Fireworks AI | $0.14 | $0.28 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v4-flash
| |||||||||||||||||||
| Nebius | $0.14 | $0.28 | 1 | ||||||||||||||||
Standardnebius/deepseek-ai/DeepSeek-V4-Flash
| |||||||||||||||||||
| Novita | $0.14 | $0.28 | 1 | ||||||||||||||||
Standardnovita/deepseek/deepseek-v4-flash
| |||||||||||||||||||
| Tencent | $0.14 | $0.28 | 1 | ||||||||||||||||
Standardtencent/deepseek-v4-flash
| |||||||||||||||||||
| DeepSeek is dearest at $0.30 / $1.20 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 36% since first tracked
Cost calculator
estimate your monthly spend on this model$32
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/deepseek-ai/DeepSeek-V4-Flashdeepseek/deepseek-v4-flashpinstripes/ps/deepseek-v4-flashdeepseek/deepseek-v4-flashfireworks_ai/accounts/fireworks/models/deepseek-v4-flashtensormesh/deepseek-ai/DeepSeek-V4-Flashtencent/deepseek-v4-flashnovita/deepseek/deepseek-v4-flashwandb/deepseek-ai/DeepSeek-V4-Flashnebius/deepseek-ai/DeepSeek-V4-Flashaihubmix/deepseek-v4-flashprism/deepseek-v4-flashazure_ai/deepseek-v4-flashdashscope/deepseek-v4-flashqwen_ai_platform/deepseek-v4-flashqwencloud/deepseek-v4-flashlibertai/deepseek-v4-flashdeepseek-v4-flash
Frequently asked questions
DeepSeek V4 Flash 0423 pricing, context and availabilityIs DeepSeek V4 Flash 0423 still available?
Yes. DeepSeek V4 Flash 0423 is scheduled for retirement on 2028-02-20.
How much does DeepSeek V4 Flash 0423 cost?
DeepSeek V4 Flash 0423 costs $0.09 per 1M input tokens from DeepInfra, and $0.18 per 1M output tokens from DeepInfra. Across 18 serving providers, input prices range from $0.09 to $0.30 per 1M tokens.
What is the context window of DeepSeek V4 Flash 0423?
DeepSeek V4 Flash 0423 accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve DeepSeek V4 Flash 0423?
DeepSeek V4 Flash 0423 is available from 18 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can DeepSeek V4 Flash 0423 do?
DeepSeek V4 Flash 0423 supports image input (vision), tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0731$0.016/1M · 16 providersDeepSeek V4 Pro 0423$0.435/1M · 16 providersR1$0.40/1M · 14 providersDeepSeek V4.1 Flash$0.01/1M · 12 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
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