stepfun
DeepSeek V4 Pro 0813 vs Step 5 Preview
58.6 overall · $1.43 / 1M
// deepseek
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
reasoningtool callingprompt caching
DeepSeek V4 Pro 0813 costs $0.117 per 1M input tokens and $4.66 per 1M output tokens with a 1.0M-token context window.
A reasoning, tool-calling model from deepseek, released Aug 12, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.117
- Output / 1M
- $4.66
- Context
- 1.0M
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.117 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $4.66 |
| Blended price 3:1 input:output — #125 most expensive of 350 listed models | $1.25 |
| Cached input read Blank means not priced separately — not free | $0.111 |
| Cache write | — |
| Context window | 1,048,576 tokens |
| Max output | 943,718 tokens |
| Input modalities | text |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Aug 12, 2026 |
What DeepSeek V4 Pro 0813 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 | $400.36/mo |
| RAG assistant 8K in / 600 out × 100K requests | $370.60/mo |
| Coding agent 40K in / 4K out × 20K requests | $462.92/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $465.72/mo |
| Bulk classification 500 in / 20 out × 5M requests | $754.50/mo |
Compare DeepSeek V4 Pro 0813 with
Benchmarked models at a similar price.
mistralai
DeepSeek V4 Pro 0813 vs Mistral Large 4
43.9 overall · $1.05 / 1M
DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash
59.2 overall · $1.65 / 1M
thinkingmachines
DeepSeek V4 Pro 0813 vs Inkling
47.0 overall · $1.76 / 1M
openai
DeepSeek V4 Pro 0813 vs GPT-6.1 Terra
77.8 overall · $2.00 / 1M
meta
DeepSeek V4 Pro 0813 vs Muse Spark Open
51.6 overall · $2.00 / 1M
DeepSeek V4 Pro 0813 FAQ
How much does DeepSeek V4 Pro 0813 cost?
DeepSeek V4 Pro 0813 lists at $0.117 per 1M input tokens and $4.66 per 1M output tokens, with cached input reads at $0.111 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $370.60 at list price.
What is the context window of DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 accepts up to 1,048,576 tokens of context and can return up to 943,718 output tokens per response.
Does DeepSeek V4 Pro 0813 support tool calling?
Yes — DeepSeek V4 Pro 0813 supports tool (function) calling and exposes extended reasoning. It accepts text input.
How does DeepSeek V4 Pro 0813 score on benchmarks?
LiveBench has not published a run for DeepSeek V4 Pro 0813 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for DeepSeek V4 Pro 0813?
On OpenRouter the model ID is "deepseek/deepseek-v4-pro-0813". It was listed on Aug 12, 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 2026-10-25. 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.