is now an ernd partner: 10% back on inference On this page
Cheapest and fastest
- Cheapest
- Alibaba Cloud Int.
- $0.871 per 1M tokens blended
- $0.581 input, $1.74 output
- Fastest
- CoreWeave
- 104 tokens per second
- $1.97 blended, 0.59 s to first token
Every provider
| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput | With ernd card |
|---|---|---|---|---|---|---|---|---|---|
| Alibaba Cloud Int. | $0.581 | $1.74 | $0.871 | $0.0581 | 1M | Not listed | 1.14 s | 26 tok/s | – |
| Baidu Qianfan | $0.659 | $1.98 | $0.988 | $0.021 | 1.05M | FP8 | 1.32 s | 48 tok/s | – |
| Alibaba Cloud Int. (US-EAST-1) | $0.66 | $1.98 | $0.99 | $0.066 | 1M | Not listed | 1.18 s | 23 tok/s | – |
| DeepSeek | $0.66 | $1.98 | $0.99 | $0.022 | 1.05M | Not listed | 1.20 s | 52 tok/s | – |
| StreamLake | $0.66 | $1.98 | $0.99 | $0.022 | 1.02M | Not listed | 1.73 s | 43 tok/s | – |
| Wafer (US) ernd partner | $0.111 | $4.44 | $1.19 | $0.106 | 1.05M | MXFP4 | 0.28 s | 86 tok/s | $1.07after 10% cash back |
| Wafer ernd partner | $0.285 | $4.30 | $1.29 | $0.284 | 1.05M | MXFP4 | 0.27 s | 79 tok/s | $1.16after 10% cash back |
| Phala | $0.957 | $2.88 | $1.44 | $0.099 | 1.05M | Not listed | 2.71 s | 52 tok/s | – |
| NovitaAI | $0.99 | $2.97 | $1.48 | $0.033 | 1.05M | FP8 | 1.62 s | 45 tok/s | – |
| GMICloud | $1.06 | $3.17 | $1.58 | $0.0352 | 1.05M | FP8 | 2.47 s | 45 tok/s | – |
| Sail Research | $1.35 | $2.40 | $1.61 | $0.195 | 1.05M | FP4 | 0.40 s | 65 tok/s | – |
| Sail Research (US) | $1.35 | $2.40 | $1.61 | $0.195 | 1.05M | FP4 | 0.41 s | 66 tok/s | – |
| DeepInfra | $1.30 | $2.60 | $1.63 | $0.10 | 1.05M | FP8 | 1.08 s | 41 tok/s | – |
| CoreWeave | $1.31 | $3.96 | $1.97 | $0.044 | 1.05M | FP8 | 0.59 s | 104 tok/s | – |
| AtlasCloud | $1.32 | $3.96 | $1.98 | $0.132 | 1.05M | FP8 | 1.38 s | 28 tok/s | – |
| Baseten | $1.32 | $3.96 | $1.98 | $0.132 | 1.05M | FP4 | 0.77 s | 45 tok/s | – |
| Cloudflare | $1.32 | $3.96 | $1.98 | $0.044 | 1.05M | Not listed | 0.80 s | 32 tok/s | – |
| DigitalOcean | $1.32 | $3.96 | $1.98 | $0.044 | 1.05M | Not listed | 1.02 s | 83 tok/s | – |
| Nebius Token Factory | $1.32 | $3.96 | $1.98 | $0.04 | 1.05M | FP8 | 0.48 s | 66 tok/s | – |
| Parasail | $1.32 | $3.96 | $1.98 | $0.044 | 1.05M | FP8 | 0.59 s | 35 tok/s | – |
| SiliconFlow | $1.32 | $3.96 | $1.98 | $0.044 | 1.05M | FP8 | 1.28 s | 25 tok/s | – |
| Together | $1.32 | $3.96 | $1.98 | $0.13 | 1.05M | Not listed | 0.52 s | 89 tok/s | – |
| Relace | $0.0999 | $8.00 | $2.07 | $0.0999 | 1.05M | FP4 | 0.67 s | 20 tok/s | – |
| Venice | $1.65 | $4.95 | $2.47 | $0.165 | 1M | Not listed | 1.21 s | 26 tok/s | – |
| Parasail (Fast) | $1.98 | $5.94 | $2.97 | $0.066 | 1.05M | FP8 | 0.39 s | 67 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 Pro 0813 API provider?
Alibaba Cloud Int., at $0.871 per million tokens blended ($0.581 input, $1.74 output), in OpenRouter's listings on November 7, 2026.
How much does DeepSeek V4 Pro 0813 cost per million tokens?
Input runs from $0.0999 to $1.98 per million tokens across 25 listings, and output from $1.74 to $8.00. The middle listing comes to $1.63 blended.
Which DeepSeek V4 Pro 0813 provider is fastest?
CoreWeave had the most throughput over the last 7 days, about 104 tokens per second. Wafer was quickest to the first token at 0.27 s.
How do I pay for DeepSeek V4 Pro 0813 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.
More models
- DeepSeek V4.1 Flash 1017 from $0.0813 blended
- DeepSeek V4.1 Flash from $0.0887 blended
- GLM 5.3 Flash from $0.0459 blended
- Hy4 preview from $1.13 blended
- MiniMax M3.1 Flash from $0.131 blended
- DeepSeek V4 Flash 0731 from $0.0667 blended
- GLM 5.3 from $0.402 blended
- Kimi K3.1 Pro from $2.27 blended
- Nemotron 3 Ultra from $0.74 blended
- Hy3 from $0.144 blended
- Nemotron 3.5 Super VL from $0.133 blended
- MiMo-V2.6-Flash from $0.14 blended
- DeepSeek V4 Flash 0423 from $0.0544 blended
- Kimi K3 from $2.61 blended
- Nemotron 3.5 Lightning from $0.0488 blended
- MiMo-V2.6-Pro from $0.486 blended
- GLM 5.2 from $0.29 blended
- Qwen3.8 27B from $0.342 blended
- gpt-oss-120b from $0.025 blended
Source
Checked . Providers change prices often, so OpenRouter's page is the final word. ernd is run by Provenance Research Inc.