# Cheapest DeepSeek V4 Flash 0423 API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/deepseek-v4-flash

> ernd partners with [Wafer](https://ernd.ai/partners/wafer). Prices are from OpenRouter's public listings.

DeepSeek V4 Flash 0423 is an open-weight model from DeepSeek. On OpenRouter, 14 listings from 14 providers sell it, and the blended price runs from $0.0544 to $0.492 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput | With ernd card |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| StreamLake | $0.0435 | $0.0871 | $0.0544 | $0.0087 | 1.02M | FP8 | 2.30 s | 35 tok/s | – |
| Baidu Qianfan | $0.0442 | $0.0885 | $0.0553 | $0.0088 | 1.05M | FP8 | 0.80 s | 85 tok/s | – |
| DeepInfra | $0.09 | $0.18 | $0.113 | $0.018 | 1.05M | FP8 | 0.94 s | 38 tok/s | – |
| GMICloud | $0.091 | $0.182 | $0.114 | $0.0182 | 1.05M | FP8 | 1.92 s | 48 tok/s | – |
| Venice | $0.0966 | $0.193 | $0.121 | $0.0196 | 1M | Not listed | 1.05 s | 44 tok/s | – |
| DigitalOcean | $0.098 | $0.196 | $0.123 | $0.0196 | 1.05M | Not listed | 0.89 s | 25 tok/s | – |
| Fireworks, down when checked | $0.105 | $0.21 | $0.131 | $0.021 | 1.05M | Not listed | 0.95 s | 59 tok/s | – |
| Relace | $0.0413 | $0.45 | $0.143 | $0.0413 | 1.05M | FP4 | 0.55 s | 107 tok/s | – |
| SiliconFlow | $0.13 | $0.28 | $0.168 | $0.028 | 1.05M | FP8 | 1.02 s | 44 tok/s | – |
| AtlasCloud | $0.14 | $0.28 | $0.175 | $0.028 | 1.05M | FP4 | 2.57 s | 38 tok/s | – |
| Parasail | $0.14 | $0.28 | $0.175 | $0.07 | 1.05M | FP8 | 0.68 s | 67 tok/s | – |
| Mancer | $0.175 | $0.50 | $0.256 | $0.175 | 1.05M | FP8 | 1.26 s | 30 tok/s | – |
| Azure (US) | $0.21 | $0.56 | $0.297 | $0.031 | 1.05M | Not listed | 1.27 s | 86 tok/s | – |
| Wafer, ernd partner | $0.60 | $0.17 | $0.492 | $0.20 | 1.05M | MXFP4 | 0.28 s | 155 tok/s | $0.443 after 10% cash back |

Blended is three parts input price to one part output, per million tokens. Latency is time to first token and throughput is output tokens per second, both averaged from OpenRouter's daily figures for the last 7 days. Cheapest and fastest only count listings that were up when checked.

Wafer is an ernd partner: 10% back on Wafer inference with the ernd card. With ernd card is the blended price less 10% cash back on Wafer charges. It comes back on the card bill and doesn't change Wafer's list price. It applies when you pay Wafer directly, not through OpenRouter credits.

## Questions

### What is the cheapest DeepSeek V4 Flash 0423 API provider?

StreamLake, at $0.0544 per million tokens blended ($0.0435 input, $0.0871 output), in OpenRouter's listings on November 7, 2026.

### How much does DeepSeek V4 Flash 0423 cost per million tokens?

Input runs from $0.0413 to $0.60 per million tokens across 14 listings, and output from $0.0871 to $0.56. The middle listing comes to $0.137 blended.

### Which DeepSeek V4 Flash 0423 provider is fastest?

Wafer led on both counts over the last 7 days, at about 155 tokens per second and 0.28 s to the first token.

### How do I pay for DeepSeek V4 Flash 0423 inference?

Buy OpenRouter credits and it sends each request to one of these providers, or open an account with a provider and pay it directly. The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. Wafer charges on the card earn 10% back.

Source: OpenRouter public model and provider listings (https://openrouter.ai/models), checked November 7, 2026.

The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. [Request the card at app.ernd.ai](https://app.ernd.ai/login?next=%2Fapp%2Fcard%2Fapply&utm_source=llms&utm_campaign=inference_prices).