DeepSeek V3.1

by DeepSeek

DeepSeek V3.1 on Fireworks

ToolsStructured output
Context window
164K
Max output
20K
Input price
$0.56 /1M
Output price
$1.68 /1M

Benchmarks

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

Global rank#163 of 505 LLMs
TierEfficient
Output speed0 tok/s
First token0.00s
Intelligence Index28.1
Coding Index28.4
Math Index49.7
MMLU-Pro
83%
GPQA Diamond
74%
Humanity's Last Exam
6%
LiveCodeBench
58%
SciCode
37%
AIME 2025
50%
IFBench
38%
Long-context reasoning
45%
Terminal-Bench Hard
24%
τ²-Bench Telecom
35%

Available routes

The same DeepSeek V3.1 runs on 3 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
FireworksUSDefaultNo
None for open models by default — does not log or store prompt or generation data without explicit opt-in.
PAYG$0.56$1.68
InfercomUSNo
Pending verification
PAYG$3.24$4.86
NovitaUSNone
Not published; appendix available upon request.
PAYG$0.27$1.00

Human review: No human review

Other models from DeepSeek

Start building with 300+ models

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

Get startedView Documentation
DeepSeek V3.1 by DeepSeek — pricing, benchmarks, hosting routes | Opper AI