DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Context
1Mtokens
About 1,498 pages of text at once
Max output
393Ktokens
About 562 pages in one answer
Intelligence
—
No score published for this model.
Output speed
47tokens/s
A 500-word answer in about 15 s
From public market statistics for this model
First token
1.6s
Reasoning models start later
From public market statistics for this model
Health, 30 days
84.49%
10 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 | 4,385,589 | IRR / 1M tokens |
|---|---|---|
| Output | 8,771,178 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 8,771,178 | IRR / 1M tokens |
| Cache read | 370,034 | 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
552.58MIRR
18.42M IRR a day, 9,210 IRR each request
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 health84.49%
Time to first token1.60 s
Output speed47 tokens/s
Place in the market
By usage across the global model market.
Daily rank#37
Share of the day’s tokens0.3%
Capabilities
- Input
- Text
- Output
- Text
Parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pOther benchmarks
Design contests
- 3DElo: 1,251Win rate: 57%
- Code (overall)Elo: 1,239Win rate: 52%
- WebsitesElo: 1,233Win rate: 51%
- Game devElo: 1,229Win rate: 52%
4 moreShow less
- UI componentsElo: 1,216Win rate: 51%
- Data vizElo: 1,203Win rate: 49%
- ASCII artElo: 1,146Win rate: 46%
- SVGElo: 1,136Win rate: 45%
Standard tests
- GPQA DiamondScore: 87%Tasks: 1,584
- τ-bench Verified AirlineScore: 77%Tasks: 400
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
# 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", 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.
Technical specs
- ID
deepseek/deepseek-v4-pro- Maker
- DeepSeek
- Tokenizer
- DeepSeek
- Released
- Apr 24, 2026
- Added to IranRouter
- Aug 19, 2026
- Context
- 1,048,576 tokens
- Max output
- 393,216 tokens
- Weights
- deepseek-ai/DeepSeek-V4-Pro
Default parameters
top_p=1temperature=1Scores by Artificial Analysis, Design Arena, as of Oct 31, 2026