novita

deepseek/deepseek-v3-turbo

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

DeepSeek-V3 is a 671B parameter Mixture of Experts (MoE) model with 128 experts and 2.4B active parameters per token. It features 128K context length and state-of-the-art performance across reasoning, coding, mathematics, and multilingual tasks with enhanced efficiency.

Capabilities

text

Available through the unified API

Quick start

View API docs
curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "a46989f7dcc74a8fbcc84d06ca6e22d3",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

novita

a46989f7dcc74a8fbcc84d06ca6e22d3

Available

Input

$0.400 / 1M

Output

$1.300 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.400 / 1M
Output tokens$1.300 / 1M

Performance

Published evaluation results associated with this model.

General Knowledge

MMLU85.2
MMLU-Pro62.8
HellaSwag90.1
ARC-Challenge89.7

Mathematical Reasoning

GSM8K94.8
MATH65.3
AIME52.1

Coding Tasks

HumanEval88.9
MBPP85.7
LiveCodeBench72.4
DS-100078.6

Multilingual Tasks

MGSM86.3
INCLUDE75.8
XCOPA89.2

Reasoning & Understanding

BBH87.4
GPQA48.9
DROP84.2

Long Context

NeedleInAHaystack98.7
ZeroSCROLLS83.5
LongBench79.8

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "a46989f7dcc74a8fbcc84d06ca6e22d3",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'