deepseek-v4-pro-0424DeepSeek
- endpoints
- 6
- regions
- 3
- api
- chat
- released
- April 2026
capabilities 4/8
The same weights cost 1.7x more on nebius ai than on deepinfra inc.. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  DeepInfra Inc. | Global | 1.0M | $1.04 | $2.08 | $0.08 | zdr |
| 2 | DeepInfra Inc. | Global | 1.0M | $1.30 | $2.60 | $0.10 | zdr |
| 3 |  Doubleword | Global | 1.0M | $1.31 | $2.75 | - | no-train |
| 4 | Doubleword | Global | 1.0M | $1.74 | $3.48 | - | no-train |
| 5 |  Nebius AI | UK | 164K | $1.75 | $3.50 | $1.75 | zdr |
| 6 |  TensorX Ltd. | EU | 1.0M | $1.75 | $3.50 | $0.44 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| τ²-Bench | 96.2 | |
| GPQA Diamond | 88.8 | |
| Coding Index | 59.4 | |
| SciCode | 50.8 | |
| Terminal-Bench Hard | 46.2 | |
| Humanity's Last Exam | 37.5 | |
| Intelligence Index | 30.9 | |
| 7 evals | mean | 58.5 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-04-24.
deepinfra/deepseek-v4-pro-0424:flexthis model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="deepinfra/deepseek-v4-pro-0424:flex", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
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 built for advanced reasoning, coding, and long horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it adds a hybrid attention system for efficient long context processing. Reasoning efforts high and xhigh are supported, with xhigh mapping to max reasoning. It is well suited for complex workloads such as full codebase analysis, multi step automation, and large scale information synthesis, where both capability and efficiency are critical.
questions 5
Which providers serve deepseek-v4-pro-0424?
How much does deepseek-v4-pro-0424 cost?
Is deepseek-v4-pro-0424 open weights?
What is the context window of deepseek-v4-pro-0424?
How do I use deepseek-v4-pro-0424 with the OpenAI SDK?
more from deepseek 6
| model | context | from /M | providers |
|---|---|---|---|
| deepseek-v4.1-flash | 1.0M | $0.22 | 3 |
| deepseek-v4-flash-vision-exp | 1.0M | $0.22 | 1 |
| deepseek-v4-pro-0813 | 1.0M | $1.30 | 4 |
| deepseek-v4-flash-0731 | 1.0M | $0.07 | 8 |
| deepseek-v4-flash-0424 | 1.0M | $0.07 | 4 |
| deepseek-v3.2 | 164K | $0.27 | 2 |
route deepseek-v4-pro-0424 through one endpoint
One key for 4 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology