This model was retired on 2028-02-20. The pricing below is the last-known rate, kept for migration reference.
DeepSeek V4 Flash 0423Deprecated
Tool useReasoningPrompt cachingStructured output
Context
1M
Max output
393K
Serving providers
12
Cheapest input
$0.09 /1M
Prices are on-demand list rates. 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
119 t/s
tokens / second
Time to first token
1.12s
latency
Headline indices
Intelligence Index
51.8
of 100
Coding Index
69.1
of 100
Agentic Index
48.4
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 16% | — | — | |||||||||||||||||
| CritPt | 17% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxy | 2979.7 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval | 1558.9 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 91% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 39% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 79% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 32% | default | — | |||||||||||||||||
| Long-Context Reasoning | 74% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Mlcr Overall | 0.1 | default | — | |||||||||||||||||
| Omniscience | -14.3 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 50% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Verified | 79% | default | — | |||||||||||||||||
| TerminalBench Hard | 39% | high | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 79% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 39% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ²-bench | 96% | high | — | |||||||||||||||||
| ||||||||||||||||||||
Pricing detail
cost beyond the standard rate · source: models.devReasoning tokens
$0.28
per 1M · thinking output
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | $0.09 | $0.17 | 1 | |||||||||||||
| ||||||||||||||||
| DeepInfra | $0.09 | $0.18 | 1 | |||||||||||||
| ||||||||||||||||
| Pinstripes | $0.10 | $0.20 | 1 | |||||||||||||
| ||||||||||||||||
| Fireworks AI | $0.14 | $0.28 | 1 | |||||||||||||
| ||||||||||||||||
| Novita | $0.14 | $0.28 | 1 | |||||||||||||
| ||||||||||||||||
| Wandb | $0.14 | $0.28 | 1 | |||||||||||||
| ||||||||||||||||
| Tencent | $0.14 | $0.28 | 1 | |||||||||||||
| ||||||||||||||||
| Tensormesh | $0.14 | $0.28 | 1 | |||||||||||||
| ||||||||||||||||
| DeepSeek is dearest at $0.44 / $1.32 | ||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 39% since first tracked
Cost calculator
estimate your monthly spend on this model$31
estimated / month
Model IDs
copy the exact identifier for your platformdeepseek/deepseek-v4-flashdeepinfra/deepseek-ai/DeepSeek-V4-Flashpinstripes/ps/deepseek-v4-flashfireworks_ai/accounts/fireworks/models/deepseek-v4-flashnovita/deepseek/deepseek-v4-flashwandb/deepseek-ai/DeepSeek-V4-Flashtencent/deepseek-v4-flashtensormesh/deepseek-ai/DeepSeek-V4-Flashazure_ai/deepseek-v4-flashdashscope/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?
DeepSeek V4 Flash 0423 was retired on 2028-02-20. The pricing on this page is the last-known rate, kept for migration reference.
How much did DeepSeek V4 Flash 0423 cost?
DeepSeek V4 Flash 0423's last-known pricing, before it was retired on 2028-02-20, was $0.09 per 1M input tokens and $0.17 per 1M output tokens.
What was the context window of DeepSeek V4 Flash 0423?
DeepSeek V4 Flash 0423 had a 1M token context window and could return up to 393K output tokens.
What could DeepSeek V4 Flash 0423 do?
DeepSeek V4 Flash 0423 supported tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineup Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI