Choose a model to open its comparison page.
DeepSeek V4 Pro benchmark, API pricing, and provider data cover 357 API providers, with prices starting at $0.0015/request. DeepSeek V4 Pro free API options are available from 9 providers. The page also shows measured API speed and first-token latency.
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
2 metrics
2 metrics
19 metrics · Rated
13 metrics · Rated
7 metrics · Rated
10 metrics · Provisional
5 metrics · Estimated
0 metrics · No data
1 metric · No data
1 metric · Provisional
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Alibaba alibaba/fp8 | $1.42/M | $2.83/M | 99.7% | — | — | 1M tokens / 393.2K tokens |
DeepSeek deepseek | $0.435/M | $0.870/M | 99.7% | — | — | 1.0M tokens / 384K tokens |
BaseTen baseten/fp4 | $1.74/M | $3.48/M | 99.7% | — | — | 262.1K tokens / 262.1K tokens |
CoreWeave coreweave/fp8 | $1.15/M | $2.55/M | 99.6% | — | — | 1.0M tokens / 1.0M tokens |
Baidu baidu/fp8 | $0.338/M | $0.676/M | 99.6% | — | — | 1.0M tokens / 393.2K tokens |
Cloudflare cloudflare | $1.17/M | $2.34/M | 99.5% | — | — | 393.2K tokens / 393.2K tokens |
Novita novita/fp8 | $0.600/M | $1.20/M | 99.5% | — | — | 1.0M tokens / 393.2K tokens |
DeepInfra deepinfra/fp4 | $1.30/M | $2.60/M | 99.0% | — | — | 1.0M tokens / 16.4K tokens |
AtlasCloud atlas-cloud/fp4 | $1.68/M | $3.38/M | 98.7% | — | — | 1.0M tokens / 393.2K tokens |
DigitalOcean digitalocean | $0.870/M | $1.74/M | 98.6% | — | — | 1.0M tokens / — |
GMICloud gmicloud/fp8 | $0.661/M | $1.32/M | 98.5% | — | — | 1.0M tokens / — |
SiliconFlow siliconflow/fp8 | $1.50/M | $3.14/M | 97.7% | — | — | 1.0M tokens / 393.2K tokens |
Ionstream ionstream/fp4 | $1.13/M | $2.26/M | 97.7% | — | — | 1.0M tokens / 393.2K tokens |
StreamLake streamlake/fp8 | $0.348/M | $0.696/M | 96.9% | — | — | 1.0M tokens / 384K tokens |
Parasail parasail/fp8 | $1.74/M | $3.48/M | 95.6% | — | — | 1.0M tokens / 1.0M tokens |
Together together | $1.74/M | $3.48/M | 93.0% | — | — | 512K tokens / — |
Venice venice | $1.65/M | $3.30/M | 74.2% | — | — | 1M tokens / 32.8K tokens |
Fireworks fireworks | $1.74/M | $3.48/M | 0% | — | — | 1.0M tokens / — |
Compare DeepSeek V4 Pro API pricing across 348 providers. Prices range from $0.0015/request to $4345.65/M. VSLLM offers the lowest rate at $0.0015/request. 9 providers offer free API credits or a free tier.
