This model was retired on 2028-02-20. The pricing below is the last-known rate, kept for migration reference.
DeepSeek V4 Pro 0423Deprecated
Tool useReasoningPrompt cachingStructured output
Context
1M
Max output
512K
Serving providers
10
Cheapest input
$0.43 /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
68 t/s
tokens / second
Time to first token
1.75s
latency
Headline indices
Intelligence Index
53.2
of 100
Coding Index
68.8
of 100
Agentic Index
49.6
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.2 | default | — | |||||||||||||||||
| AA-Briefcase | 22% | — | — | |||||||||||||||||
| APEX Agents | 24% | default | — | |||||||||||||||||
| CritPt | 18% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxy | 8552.3 | high | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval | 1590.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 93% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 41% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 76% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 38% | default | — | |||||||||||||||||
| Long-Context Reasoning | 75% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Mlcr Overall | 0.2 | default | — | |||||||||||||||||
| Omniscience | 0.8 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.5 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| SciCode | 49% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Pro | 55% | default | — | |||||||||||||||||
| SWE-bench Verified | 81% | default | — | |||||||||||||||||
| TerminalBench Hard | 46% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 79% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 40% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ²-bench | 96% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Pricing detail
cost beyond the standard rate · source: models.devReasoning tokens
$0.87
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 | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Tencent | $0.43 | $0.87 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouter | $0.69 | $1.38 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Wandb | $1.15 | $2.55 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepInfra | $1.30 | $2.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepSeek | $1.32 | $3.96 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Novita | $1.60 | $3.20 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Fireworks AI | $1.74 | $3.48 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Azure | $1.74 | $3.48 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Dashscope is dearest at $2.40 / $4.80 | ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 75% since first tracked
Cost calculator
estimate your monthly spend on this model$157
estimated / month
Model IDs
copy the exact identifier for your platformtencent/deepseek-v4-prodeepseek/deepseek-v4-prowandb/deepseek-ai/DeepSeek-V4-Prodeepinfra/deepseek-ai/DeepSeek-V4-Prodeepseek-v4-pronovita/deepseek/deepseek-v4-profireworks_ai/accounts/fireworks/models/deepseek-v4-proazure_ai/deepseek-v4-protogether_ai/deepseek-ai/DeepSeek-V4-Prodashscope/deepseek-v4-pro
Frequently asked questions
DeepSeek V4 Pro 0423 pricing, context and availabilityIs DeepSeek V4 Pro 0423 still available?
DeepSeek V4 Pro 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 Pro 0423 cost?
DeepSeek V4 Pro 0423's last-known pricing, before it was retired on 2028-02-20, was $0.43 per 1M input tokens and $0.87 per 1M output tokens.
What was the context window of DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 had a 1M token context window and could return up to 512K output tokens.
What could DeepSeek V4 Pro 0423 do?
DeepSeek V4 Pro 0423 supported tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupPopular comparisons
head-to-head pages featuring DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 vs Claude Fable 5side-by-side pricing & benchmarks DeepSeek V4 Pro 0423 vs Claude Opus 4.8side-by-side pricing & benchmarks DeepSeek V4 Pro 0423 vs Claude Sonnet 5side-by-side pricing & benchmarks
DeepSeek V4 Pro 0423 vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks DeepSeek V4 Pro 0423 vs Gemini 3.5 Flashside-by-side pricing & benchmarks 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