DeepSeek V4 Pro 0423 API pricing
As of October 21, 2026, DeepSeek V4 Pro 0423 costs $1.225 per million input tokens and $2.716 per million output tokens, the median of 16 providers on OpenRouter, with cached input at $0.0342 per million.
DeepSeek V4 Pro 0423 benchmarks and specs · Every DeepSeek model's price
- Input, per million tokens$1.225
- Output, per million tokens$2.716
- Cached input, per million$0.0342
- Context window1.05M tokens
- Max output384K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0026 | $2.58 | Yes |
| Repository review | 50K input + 3K output tokens | $0.069 | $69.40 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.272 | $272.16 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.57 | $570.00 |
Price history
The price of DeepSeek V4 Pro 0423 here is the median across 16 providers on OpenRouter, so we do not track price changes for it.
Cheaper models as good as DeepSeek V4 Pro 0423
Models within two points of DeepSeek V4 Pro 0423 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Qwen3.5-Flash$0.26 Overall 50.1 against 50.0 · 90% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 50.0 · 90% cheaper output
- DeepSeek V4 Flash 0731$0.28 Overall 55.2 against 50.0 · 90% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 50.0 · 88% cheaper output
- Claude Haiku 5.5$0.50 Overall 67.6 against 50.0 · 82% cheaper output
DeepSeek V4 Pro 0423 pricing questions
- How much does DeepSeek V4 Pro 0423 cost per million tokens?
- $1.225 per million input tokens and $2.716 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does DeepSeek V4 Pro 0423 support prompt caching?
- Yes. OpenRouter lists cached input at $0.0342 per million tokens, against $1.225 for uncached input.
- Is there a cheaper model as good as DeepSeek V4 Pro 0423?
- Qwen3.5-Flash scores 50.1 on the LLMBenchmark Index, within two points of DeepSeek V4 Pro 0423 or above it, and costs $0.26 per million output tokens.
- Has the price of DeepSeek V4 Pro 0423 changed?
- The price of DeepSeek V4 Pro 0423 here is the median across 16 providers on OpenRouter, so we do not track price changes for it.