DeepSeek: DeepSeek V4 Pro 0423
by DeepSeek · Released 2026-04-24
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,...
Context1M tokensMax output393.2K tokensReleased2026-04-24
What it can do
Real jobs this model can take on, based on what it can read and how it’s priced.
Run an agent that calls your own tools and replies in clean JSON
tool calling · structured output
Work through a hard problem step by step, not just answer it
step-by-step reasoning
Hold an entire codebase in one request and answer across it
1M-token context
Power a chat product at high volume, priced per reply
≈ 0,83 DA per typical reply
Good for
- Very long documents — whole books or contract stacks in one request
- Tool calling and structured JSON, for building agents
- High-volume workloads where cost per reply matters
Not for
- Generating images — it replies with text only
- Speaking its replies aloud — no audio output
- Fine-tuning on your own data — not supported
Also supports
Tool callingStructured JSONStep-by-step reasoningStreamingPrompt cachingFine-tuning
Where your request runs
You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.
| Provider | In /M | Out /M | Cache /M | Latency | TPS | Uptime |
|---|---|---|---|---|---|---|
| DigitalOcean | 281,88 DA | 563,76 DA | 56,38 DA | — | — | 96,8 % |
| StreamLake | 337,69 DA | 675,38 DA | 28,14 DA | — | — | 99,8 % |
| GMICloud | 338,26 DA | 676,51 DA | 28,19 DA | — | — | 93,6 % |
| Ionstream | 366,44 DA | 732,89 DA | 30,46 DA | — | — | 98,2 % |
| CoreWeave | 372,60 DA | 826,20 DA | 64,80 DA | — | — | — |
| DeepInfra | 421,20 DA | 842,40 DA | 32,40 DA | — | — | 97,8 % |
| Alibaba | 458,78 DA | 917,57 DA | 38,23 DA | — | — | 100,0 % |
| SiliconFlow | 486,52 DA | 1 015,74 DA | 43,74 DA | — | — | 99,8 % |
| Novita | 518,40 DA | 1 036,80 DA | 43,74 DA | — | — | 100,0 % |
| Venice | 534,60 DA | 1 069,52 DA | 106,92 DA | — | — | 60,7 % |
| AtlasCloud | 544,32 DA | 1 095,12 DA | 42,12 DA | — | — | 99,8 % |
| Baidu | 547,56 DA | 1 095,12 DA | 45,36 DA | — | — | 100,0 % |
| NextBit | 557,28 DA | 1 117,80 DA | 45,36 DA | — | — | 98,4 % |
| BaseTen | 563,76 DA | 1 127,52 DA | 46,98 DA | — | — | 100,0 % |
| Fireworks | 563,76 DA | 1 127,52 DA | 46,98 DA | — | — | — |
| Parasail | 563,76 DA | 1 127,52 DA | 32,40 DA | — | — | 99,9 % |
| Azure | 618,84 DA | 1 240,92 DA | 51,84 DA | — | — | 92,7 % |
Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.
What it costs
Everyday jobs, priced. Each request charges exactly what it uses — no subscription, no minimum.
Answer a quick question≈ 0,22 DA
Reply to a customer email≈ 0,57 DA
Translate a full page of text≈ 0,83 DA
Write a one-page draft≈ 0,81 DA
Top up points
3 000 DA ≈ 3 616 typical replies · the exact charge appears after every request, down to the centime.
Call it in code
OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.
Sign in to run this request on your own wallet.
The same request, in your language
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- 1M tokens
- Max output
- 393.2K tokens
- Longest reply
- ≈ 295.0K words
- Tokenizer
- DeepSeek
- Intelligence index
- 45.3
- Released
- 2026-04-24
Questions about DeepSeek V4 Pro 0423
How much does DeepSeek V4 Pro 0423 cost in Algerian Dinars?
518,40 DA for the text you send and 1 036,80 DA for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,83 DA. You pay for what you actually use: no subscription, no minimum.
How big is DeepSeek V4 Pro 0423's context window?
DeepSeek V4 Pro 0423 reads up to 1M tokens in one request, and writes back up to roughly 295,000 words at once.
What can DeepSeek V4 Pro 0423 handle?
It reads text and replies with text. It also supports calling your own tools, replying in structured JSON, step-by-step reasoning and streaming its answer as it writes.
Can I use DeepSeek V4 Pro 0423 without an international bank card?
Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on DeepSeek V4 Pro 0423 or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.
Who makes DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 is built by DeepSeek, released on Apr 24, 2026. OpenDunes serves it unchanged — same model, same weights, billed in dinars.
Other DeepSeek models, priced in dinars
See all DeepSeek modelsDeepSeek: DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-expText
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
TextImagesText
in142,56 DAout427,68 DAper 1M tokens
by DeepSeekAug 21, 20261M contextReasoningToolsJSON
DeepSeek: DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813Text
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
TextText
in361,39 DAout1 084,17 DAper 1M tokens
by DeepSeekAug 12, 20261M contextReasoningToolsJSON
DeepSeek: DeepSeek V4 Pro 0813 (batch)
deepseek/deepseek-v4-pro-0813:batchText
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
TextText
in427,68 DAout1 283,04 DAper 1M tokens
by DeepSeekAug 12, 20261M contextReasoningToolsJSON
DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731Text
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
TextText
in21,06 DAout58,32 DAper 1M tokens
by DeepSeekJul 31, 20261.3M contextReasoningToolsJSON
DeepSeek: DeepSeek V4 Flash 0731 (batch)
deepseek/deepseek-v4-flash-0731:batchText
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
TextText
in45,36 DAout90,72 DAper 1M tokens
by DeepSeekJul 31, 20261M contextReasoningToolsJSON
DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flashText
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
TextText
in26,22 DAout52,44 DAper 1M tokens
by DeepSeekApr 24, 20261M contextReasoningToolsJSON
DeepSeek: DeepSeek V3.2
deepseek/deepseek-v3.2Text
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
TextText
in87,16 DAout129,60 DAper 1M tokens
by DeepSeekDec 1, 2025164K contextReasoningToolsJSON
DeepSeek: DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminusText
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
TextText
in87,48 DAout324 DAper 1M tokens
by DeepSeekSep 22, 2025164K contextReasoningToolsJSON