z-ai
DeepSeek V4 Pro 0423 vs GLM 5.3 Flash
71.6 overall · $0.237 / 1M
// deepseek
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro
reasoningtool callingprompt caching
DeepSeek V4 Pro 0423 costs $0.865 per 1M input tokens and $1.73 per 1M output tokens with a 1.0M-token context window.
A reasoning, tool-calling model from deepseek, released Apr 24, 2026. On LiveBench it scores 71.6 overall — #43 of 55 benchmarked models — and ranks highest in mathematics (#26).
- Input / 1M
- $0.865
- Output / 1M
- $1.73
- Context
- 1.0M
- LiveBench overall
- 71.6 · #43
Specs and pricing
| Input price USD per 1M prompt tokens | $0.865 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $1.73 |
| Blended price 3:1 input:output — #128 most expensive of 343 listed models | $1.08 |
| Cached input read Blank means not priced separately — not free | $0.072 |
| Cache write | — |
| Context window | 1,048,576 tokens |
| Max output | 384,000 tokens |
| Input modalities | text |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Apr 24, 2026 |
Benchmarks by category
LiveBench scores out of 100, with DeepSeek V4 Pro 0423's rank among the 55 benchmarked models listed here. Run: deepseek-v4-pro.
Language#32 of 55
78.1
$0.0091 measured per point
What DeepSeek V4 Pro 0423 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $289.01/mo |
| RAG assistant 8K in / 600 out × 100K requests | $478.80/mo |
| Coding agent 40K in / 4K out × 20K requests | $386.50/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $955.44/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,940/mo |
Compare DeepSeek V4 Pro 0423 with
The benchmarked models closest to it on overall score.
thinkingmachines
DeepSeek V4 Pro 0423 vs Inkling
71.9 overall · $1.76 / 1M
openai
DeepSeek V4 Pro 0423 vs GPT-6 Luna
72.0 overall · $0.200 / 1M
anthropic
DeepSeek V4 Pro 0423 vs Claude Opus 4.5
72.6 overall · $10.00 / 1M
moonshotai
DeepSeek V4 Pro 0423 vs Kimi K2.6
70.5 overall · $1.71 / 1M
anthropic
DeepSeek V4 Pro 0423 vs Claude Sonnet 4.6
73.0 overall · $6.00 / 1M
DeepSeek V4 Pro 0423 FAQ
How much does DeepSeek V4 Pro 0423 cost?
DeepSeek V4 Pro 0423 lists at $0.865 per 1M input tokens and $1.73 per 1M output tokens, with cached input reads at $0.072 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $478.80 at list price.
What is the context window of DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 accepts up to 1,048,576 tokens of context and can return up to 384,000 output tokens per response.
Does DeepSeek V4 Pro 0423 support tool calling?
Yes — DeepSeek V4 Pro 0423 supports tool (function) calling and exposes extended reasoning. It accepts text input.
How does DeepSeek V4 Pro 0423 score on benchmarks?
On LiveBench release 2026-06-25 (run: deepseek-v4-pro), DeepSeek V4 Pro 0423 scores 71.6 overall, ranking #43 of 55 benchmarked models.
What is the API model ID for DeepSeek V4 Pro 0423?
On OpenRouter the model ID is "deepseek/deepseek-v4-pro". It was listed on Apr 24, 2026.
More from deepseek
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.