DeepSeek · Model
DeepSeek V4 Pro 0423 pricing, context window and specs
DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens, and reads up to 1,024,000 tokens per request. By blended price it is the most expensive in DeepSeek's current line-up.
- Input / 1M
- $0.9553
- Output / 1M
- $1.9105
- Cached / 1M
- $0.0796
- Context
- 1,024,000
- Max output
- 384,000
- Released
- 2026-04-24
Estimate your cost with DeepSeek V4 Pro 0423Compare all DeepSeek modelsCount tokens for DeepSeek V4 Pro 0423
Pricing
DeepSeek V4 Pro 0423 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.9553 | $1.9105 |
| Cached input (read) | $0.0796 | – |
Output costs 2.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 8% of the normal input price.
Examples
What DeepSeek V4 Pro 0423 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00154 | $46.85 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00564 | $85.71 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.014 | $85.23 |
| Document summariser | 8,000 / 600 | 300 | $0.00879 | $80.19 |
Change any number in the cost calculator.
Context
Context window
DeepSeek V4 Pro 0423 accepts up to 1,024,000 tokens per request, roughly 768,000 English words or 1,536 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 384,000 tokens.
Filling the whole window with one prompt costs about $0.98 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- No
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
DeepSeek
Where DeepSeek V4 Pro 0423 sits in DeepSeek’s line-up
Ranked by blended price (three parts input to one part output, $1.1941 per 1M for DeepSeek V4 Pro 0423), it is the most expensive of DeepSeek’s 11 priced models. See every DeepSeek model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $1.20 | 1,048,576 | 2026-09-10 |
| DeepSeek V4 Flash Vision Exp | $0.2156 | $0.6468 | 1,048,576 | 2026-08-21 |
| DeepSeek V4 Pro 0423 (this page) | $0.9553 | $1.9105 | 1,024,000 | 2026-04-24 |
| DeepSeek V3.2 | $0.259 | $0.42 | 163,840 | 2025-12-01 |
| DeepSeek V3.2 Exp | $0.27 | $0.41 | 163,840 | 2025-09-29 |
| DeepSeek V3.1 Terminus | $0.27 | $1 | 163,840 | 2025-09-22 |
| DeepSeek V3.1 | $0.25 | $0.95 | 163,840 | 2025-08-21 |
| R1 0528 | $0.50 | $2.15 | 163,840 | 2025-05-28 |
Save
Cheaper alternatives
- Seed 1.6 FlashByteDance Seed89% cheaper
- Claude Haiku 5.5Anthropic83% cheaper
- GPT-6 LunaOpenAI83% cheaper
- Qwen3.8 FlashQwen81% cheaper
- DeepSeek V4 Flash Vision ExpDeepSeek73% cheaper
Current models from major providers, one per provider, that keep tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Grok Build 0.1xAI$1 / $2
- Seed-2.0-CodeByteDance Seed$0.50 / $3
- Gemini 3 Flash PreviewGoogle$0.50 / $3
- Qwen3.5 397B A17BQwen$0.55 / $3.50
- Kimi K2 ThinkingMoonshot AI$0.60 / $2.50
Current models from other major providers, closest blended price.
FAQ
DeepSeek V4 Pro 0423 questions
How much does DeepSeek V4 Pro 0423 cost?
DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens, with cached input at $0.0796. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.0022. Use the LLM cost calculator for your own workload.
What is DeepSeek V4 Pro 0423's context window?
1,024,000 tokens, about 768,000 English words or 1,536 printed pages, shared between your prompt and the reply. A single reply can be up to 384,000 tokens.
Does DeepSeek V4 Pro 0423 support prompt caching and batch requests?
Yes, cached input is billed at $0.0796 per million tokens (8% of the normal input price). No batch price is published for it.
What are cheaper alternatives to DeepSeek V4 Pro 0423?
With the same essentials (tool calling), the cheapest options are Seed 1.6 Flash (89% cheaper), Claude Haiku 5.5 (83% cheaper), GPT-6 Luna (83% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is DeepSeek V4 Pro 0423 open source?
Yes, DeepSeek V4 Pro 0423 has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.