DeepSeek V4 Pro

by DeepSeek

DeepSeek V4 Pro MoE (1.6T params, 49B active) on DeepInfra

ReasoningToolsStructured output
Context window
1.0M
Max output
66K
Input price
$1.74 /1M
Output price
$3.48 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#16 of 505 LLMs
TierFrontier
Output speed35 tok/s
First token1.15s
Intelligence Index51.5
Coding Index47.5
GPQA Diamond
89%
Humanity's Last Exam
36%
SciCode
50%
IFBench
77%
Long-context reasoning
66%
Terminal-Bench Hard
46%
τ²-Bench Telecom
96%

Available routes

The same DeepSeek V4 Pro runs on 3 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
DeepInfraUSNo
Pending verification
PAYG$1.74$3.48
FireworksUSDefaultNo
None for open models by default — does not log or store prompt or generation data without explicit opt-in.
PAYG$1.74$3.48
NovitaUSNone
Not published; appendix available upon request.
PAYG$1.74$3.48

Human review: Abuse-flagged only

Other models from DeepSeek

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
DeepSeek V4 Pro by DeepSeek — pricing, benchmarks, hosting routes | Opper AI