# Cheapest DeepSeek V4.1 Flash API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/deepseek-v4-1-flash

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

DeepSeek V4.1 Flash is an open-weight model from DeepSeek. On OpenRouter, 39 listings from 31 providers sell it, and the blended price runs from $0.0887 to $0.788 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput | With ernd card |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Baidu Qianfan | $0.0507 | $0.203 | $0.0887 | $0.001 | 1.05M | FP8 | 1.02 s | 103 tok/s | – |
| Morph | $0.022 | $0.40 | $0.117 | $0.004 | 1.05M | FP8 | 0.71 s | 73 tok/s | – |
| Relace | $0.006 | $0.50 | $0.13 | $0.005 | 1.05M | FP4 | 0.56 s | 116 tok/s | – |
| Alibaba Cloud Int. | $0.075 | $0.30 | $0.131 | $0.0075 | 1M | Not listed | 0.65 s | 120 tok/s | – |
| DeepInfra (Flex), down when checked | $0.112 | $0.336 | $0.168 | $0.0034 | 1.05M | FP8 | 2.16 s | 64 tok/s | – |
| Open Inference | $0.03 | $0.60 | $0.172 | $0.006 | 1.05M | FP4 | 0.74 s | 98 tok/s | – |
| Wafer (US), ernd partner | $0.051 | $0.567 | $0.18 | $0.018 | 1.05M | MXFP4 | 0.29 s | 188 tok/s | $0.162 after 10% cash back |
| DeepInfra | $0.14 | $0.42 | $0.21 | $0.0042 | 1.05M | FP8 | 0.64 s | 90 tok/s | – |
| inference.net | $0.103 | $0.60 | $0.227 | $0.008 | 1.04M | FP8 | 0.27 s | 107 tok/s | – |
| inference.net (US) | $0.103 | $0.60 | $0.227 | $0.008 | 1.04M | FP8 | 0.28 s | 93 tok/s | – |
| AtlasCloud | $0.135 | $0.54 | $0.236 | $0.0135 | 1.05M | FP8 | 0.71 s | 70 tok/s | – |
| Mancer | $0.15 | $0.50 | $0.237 | $0.05 | 1.05M | FP8 | 0.74 s | 58 tok/s | – |
| StreamLake | $0.147 | $0.588 | $0.257 | $0.0029 | 1.02M | FP8 | 1.46 s | 70 tok/s | – |
| CoreWeave | $0.13 | $0.65 | $0.26 | $0.002 | 1.05M | FP8 | 0.54 s | 168 tok/s | – |
| Wafer, ernd partner | $0.19 | $0.65 | $0.305 | $0.012 | 1.05M | MXFP4 | 0.27 s | 189 tok/s | $0.275 after 10% cash back |
| DeepInfra (Priority) | $0.21 | $0.63 | $0.315 | $0.0063 | 1.05M | FP8 | 0.88 s | 78 tok/s | – |
| GMICloud | $0.18 | $0.72 | $0.315 | $0.0036 | 1.05M | FP8 | 2.11 s | 59 tok/s | – |
| Reka AI | $0.12 | $0.96 | $0.33 | $0.008 | 1.05M | Not listed | 0.43 s | 88 tok/s | – |
| NovitaAI | $0.195 | $0.78 | $0.341 | $0.0039 | 1.05M | FP8 | 0.96 s | 99 tok/s | – |
| Fireworks Spot | $0.21 | $0.84 | $0.367 | $0.0042 | 1.05M | Not listed | 0.60 s | 132 tok/s | – |
| Phala | $0.21 | $0.84 | $0.367 | $0.0042 | 1.05M | Not listed | 1.13 s | 104 tok/s | – |
| DigitalOcean | $0.225 | $0.90 | $0.394 | $0.006 | 1.05M | Not listed | 0.69 s | 171 tok/s | – |
| Prime Intellect | $0.156 | $1.20 | $0.417 | $0.0048 | 1.05M | Not listed | 0.76 s | 149 tok/s | – |
| Relace (Fast) | $0.30 | $0.90 | $0.45 | $0.008 | 1.05M | FP4 | – | – | – |
| Makora | $0.26 | $1.17 | $0.487 | $0.0058 | 1.05M | FP8 | 0.54 s | 130 tok/s | – |
| Crusoe | $0.29 | $1.20 | $0.517 | $0.007 | 1.05M | FP8 | 0.54 s | 158 tok/s | – |
| Baseten | $0.30 | $1.20 | $0.525 | $0.007 | 1.05M | Not listed | 0.42 s | 196 tok/s | – |
| Baseten (US) | $0.30 | $1.20 | $0.525 | $0.007 | 1.05M | Not listed | 0.34 s | 197 tok/s | – |
| Cohere | $0.30 | $1.20 | $0.525 | $0.003 | 1.05M | FP8 | 0.38 s | 172 tok/s | – |
| Fireworks | $0.30 | $1.20 | $0.525 | $0.006 | 1.05M | Not listed | 0.64 s | 125 tok/s | – |
| Google Vertex (Global) | $0.30 | $1.20 | $0.525 | $0.03 | 1.05M | Not listed | 0.77 s | 91 tok/s | – |
| Modal | $0.30 | $1.20 | $0.525 | $0.03 | 1.05M | Not listed | 0.47 s | 130 tok/s | – |
| Nebius Token Factory | $0.30 | $1.20 | $0.525 | $0.01 | 1.05M | FP8 | 0.85 s | 112 tok/s | – |
| Parasail | $0.30 | $1.20 | $0.525 | $0.006 | 1.05M | FP8 | 0.41 s | 172 tok/s | – |
| SiliconFlow | $0.30 | $1.20 | $0.525 | $0.006 | 1.05M | FP8 | 1.52 s | 95 tok/s | – |
| Together | $0.30 | $1.20 | $0.525 | $0.006 | 1.05M | Not listed | 0.29 s | 217 tok/s | – |
| Venice | $0.30 | $1.20 | $0.525 | $0.0075 | 1M | FP8 | 0.58 s | 165 tok/s | – |
| Fireworks (US) | $0.45 | $1.80 | $0.788 | $0.009 | 1.05M | Not listed | 0.37 s | 200 tok/s | – |
| Parasail (Fast) | $0.45 | $1.80 | $0.788 | $0.009 | 1.05M | FP8 | 0.42 s | 137 tok/s | – |

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 V4.1 Flash API provider?

Baidu Qianfan, at $0.0887 per million tokens blended ($0.0507 input, $0.203 output), in OpenRouter's listings on November 7, 2026.

### How much does DeepSeek V4.1 Flash cost per million tokens?

Input runs from $0.006 to $0.45 per million tokens across 39 listings, and output from $0.203 to $1.80. The middle listing comes to $0.367 blended.

### Which DeepSeek V4.1 Flash provider is fastest?

Together had the most throughput over the last 7 days, about 217 tokens per second. Wafer was quickest to the first token at 0.27 s.

### How do I pay for DeepSeek V4.1 Flash 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).