Start typing to search.
Ranks providers by estimated cost using a 1,000-input/500-output token ratio, shown per 1 million total tokens.
DeepSeek currently ranks first at $0.58 / 1M tokens via deepseek.
| Rank | Provider / route | Estimated cost / 1M tokens | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route DeepSeek deepseek | Estimated cost / 1M tokens$0.58 / 1M tokens | Speed measurements
| Endpoint details
|
| #2 | Provider / route StreamLake streamlake/fp8 | Estimated cost / 1M tokens$0.9512 / 1M tokens | Speed measurements
| Endpoint details
|
| #3 | Provider / route Baidu Qianfan baidu/fp8 | Estimated cost / 1M tokens$0.99372 / 1M tokens | Speed measurements
| Endpoint details
|
| #4 | Provider / route GMICloud gmicloud/fp8 | Estimated cost / 1M tokens$1.508 / 1M tokens | Speed measurements
| Endpoint details
|
| #5 | Provider / route NovitaAI novita/fp8 | Estimated cost / 1M tokens$1.557333 / 1M tokens | Speed measurements
| Endpoint details
|
| #6 | Provider / route DeepInfra deepinfra/fp4 | Estimated cost / 1M tokens$1.733333 / 1M tokens | Speed measurements
| Endpoint details
|
| #7 | Provider / route DigitalOcean digitalocean | Estimated cost / 1M tokens$1.856 / 1M tokens | Speed measurements
| Endpoint details
|
| #8 | Provider / route Alibaba Cloud Int. alibaba | Estimated cost / 1M tokens$1.888 / 1M tokens | Speed measurements
| Endpoint details
|
| #9 | Provider / route SiliconFlow siliconflow/fp8 | Estimated cost / 1M tokens$2.04608 / 1M tokens | Speed measurements
| Endpoint details
|
| #10 | Provider / route Venice venice | Estimated cost / 1M tokens$2.200333 / 1M tokens | Speed measurements
| Endpoint details
|
| #11 | Provider / route AtlasCloud atlas-cloud/fp4 | Estimated cost / 1M tokens$2.246667 / 1M tokens | Speed measurements
| Endpoint details
|
| #12 | Provider / route Baseten baseten/fp4 | Estimated cost / 1M tokens$2.32 / 1M tokens | Speed measurements
| Endpoint details
|
| #13 | Provider / route Parasail parasail/fp8 | Estimated cost / 1M tokens$2.32 / 1M tokens | Speed measurements
| Endpoint details
|
| #14 | Provider / route Weights & Biases wandb/fp8 | Estimated cost / 1M tokens$2.32 / 1M tokens | Speed measurements
| Endpoint details
|
| #15 | Provider / route Together together | Estimated cost / 1M tokens$2.32 / 1M tokens | Speed measurements
| Endpoint details
|
| #16 | Provider / route Fireworks fireworks | Estimated cost / 1M tokens$2.32 / 1M tokens | Speed measurements
| Endpoint details
|
Endpoint data fetched .
DeepSeek V4 Pro endpoint guide
16 of 16 DeepSeek V4 Pro endpoints currently have the published data required for this ranking. DeepSeek leads at $0.58 / 1M tokens via deepseek. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The cheapest ranking uses a 1,000-input/500-output-token ratio and reports the blended result per 1 million total tokens. Because providers can price input and output differently, a workload with a different token ratio may produce a different order.
StreamLake currently ranks second at $0.9512 / 1M tokens. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.
DeepSeek V4 Pro has 16 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.
