DeepSeek V4 Pro
View website
Released April 2026, DeepSeek's flagship 1.6T-parameter MoE (49B active) under MIT license, trained on 32T+ tokens with hybrid sparse attention. Scores 90.1 on GPQA Diamond and 93.5 on LiveCodeBench in its highest reasoning mode.
At a glance
- Context window
- 1M tokens
- Max output
- 384K tokens
- Modalities
- Text Text → Text Text
Capabilities
Function calling
Connect to external tools, APIs, and systems.
Structured output
Return responses in structured formats like JSON.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
GPUhub
|
$0.42 | $0.83 | View |
|
DeepSeek
|
$0.44 | $0.87 | View |
Novita
|
$1.60 | $3.20 | View |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.