DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Context
1Mtokens
About 1,498 pages of text at once
Max output
393Ktokens
About 562 pages in one answer
Intelligence
23.1/ 100
Above 37% of the catalogue
Output speed
52tokens/s
A 500-word answer in about 13.4 s
From public market statistics for this model
First token
1.2s
Reasoning models start later
From public market statistics for this model
Health, 30 days
62.95%
5 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 283,693 | IRR / 1M tokens |
|---|---|---|
| Output | 21,927,944 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 21,927,944 | IRR / 1M tokens |
| Cache read | 274,099 | IRR / 1M tokens |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
420.24MIRR
14.01M IRR a day, 7,004 IRR each request
The same work on peer models
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health62.95%
Time to first token1.33 s
Output speed52 tokens/s
Place in the market
By usage across the global model market.
Daily rank#33
Share of the day’s tokens0.4%
Among its peers
Cost of one message against intelligence; this model is highlighted.
Cost of one message, IRR (log scale)
Capabilities
- Input
- Text
- Output
- Text
Parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pOther benchmarks
Standard tests
- GPQA DiamondScore: 90%Tasks: 2,175
- τ-bench Verified AirlineScore: 78%Tasks: 500
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
https://iranrouter.com/v1deepseek/deepseek-v4-pro-0813# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="deepseek/deepseek-v4-pro-0813", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
| Model | Against this model | ||||
|---|---|---|---|---|---|
| Qwen: Qwen3.8 27BQwen | 3,370 | 20.1 | 51 | 1M | 71% cheaper |
| MiniMax: MiniMax M3Minimax | 3,288 | 18.7 | 87 | 1M | 71% cheaper |
| Z.ai: GLM 5.3 FlashZ.ai | 292 | 27.8 | 77 | 1M | 97% cheaper |
| Qwen: Qwen3.6 Max PreviewQwen | 14,070 | 28.4 | — | 262K | 22% dearer |
| MoonshotAI: Kimi K3Moonshot AI | 21,602 | 17.4 | 63 | 1M | 87% dearer |
Technical specs
- ID
deepseek/deepseek-v4-pro-0813- Maker
- DeepSeek
- Tokenizer
- DeepSeek
- Released
- Aug 12, 2026
- Added to IranRouter
- Aug 19, 2026
- Context
- 1,048,576 tokens
- Max output
- 393,216 tokens
Default parameters
top_p=1temperature=1Scores by Artificial Analysis, as of Oct 31, 2026