DeepSeek V4 Pro 0423
$0.955 per 1M input tokens and $1.91 per 1M output tokens · 1.05M context · tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What DeepSeek V4 Pro 0423 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $315 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $92.42 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $153 |
| Content generation 30 long articles a day | $6.88 |
| Classification / extraction 100,000 short items a day | $946 |
Price history
We started tracking DeepSeek V4 Pro 0423 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run DeepSeek V4 Pro 0423: 16 providers
Parasail is the cheapest at $0.45 input / $3.48 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| Parasail | $0.45 | $3.48 | 1.05M | 74.9% | fp8 |
| Relace | $0.90 | $1.50 | 1.05M | 99.7% | fp4 |
| StreamLake | $0.955 | $1.91 | 1.02M | 99.8% | fp8 |
| GMICloud | $0.957 | $1.91 | 1.05M | 99.9% | fp8 |
| DigitalOcean | $1.04 | $2.09 | 1.05M | 99.5% | — |
| Reka | $1.05 | $2.10 | 1.05M | 97.5% | — |
| Cloudflare | $1.15 | $2.55 | 1.05M | 99.2% | — |
| DeepInfra | $1.30 | $2.60 | 1.05M | 100% | fp8 |
| Alibaba | $1.42 | $2.83 | 1M | 99.3% | fp8 |
| SiliconFlow | $1.50 | $3.13 | 1.05M | 99.4% | fp8 |
| Alibaba | $1.56 | $3.12 | 1M | 100% | fp8 |
| Novita | $1.60 | $3.20 | 1.05M | 99.9% | fp8 |
| Venice | $1.65 | $3.30 | 1M | 91.8% | — |
| AtlasCloud | $1.68 | $3.38 | 1.05M | 99.1% | fp4 |
| Baidu | $1.69 | $3.38 | 1.05M | 98.7% | fp8 |
| Azure | $1.91 | $3.83 | 1.05M | 99.9% | — |
Cheaper alternatives to DeepSeek V4 Pro 0423
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| GLM 5.3 Z.ai | $0.079 | $1.40 | 1.05M | toolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.1 Flash inclusionAI | $0.075 | $0.225 | 262K | toolsreasoningJSON |
How to pay less for DeepSeek V4 Pro 0423
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $504 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to MiMo-V2.6-Pro (similar capabilities) | $136 | $368 (73%) |
| Use prompt caching (60% of input cached) | $315 | $189 (37%) |
| Route to Relace | $450 | $54.38 (11%) |
Other workloads: cut-your-bill tool for DeepSeek V4 Pro 0423.
Specifications
| Model ID | deepseek/deepseek-v4-pro |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — deepseek-ai/DeepSeek-V4-Pro |
| Released | Apr 24, 2026 |
FAQ
- How much does DeepSeek V4 Pro 0423 cost?
- $0.955 per million input tokens and $1.91 per million output tokens; cached input costs $0.08 per million. Prices as of Oct 21, 2026.
- What is the context window of DeepSeek V4 Pro 0423?
- 1.05M tokens, with up to 384K output tokens per response.
- Does DeepSeek V4 Pro 0423 support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to DeepSeek V4 Pro 0423?
- Models with the same key capabilities for at least 20% less include MiMo-V2.6-Pro ($0.435 / $0.87), GLM 5.3 ($0.079 / $1.40), Claude Haiku 5.5 ($0.10 / $0.50).
More from DeepSeek: all DeepSeek models · how we collect prices