novita

deepseek/deepseek-r1-distill-qwen-14b

Context

32K

Input

text

Output

text

Tool calling

Supported

About this model

DeepSeek-R1-Distill-Qwen-14B is a knowledge-distilled model combining DeepSeek-R1's reasoning capabilities with Qwen's multilingual strengths. Features enhanced Chinese-English performance and balanced task generalization at 14B scale with FP16 precision.

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": "2186179a80c94a46a6404fc2a84d31f8",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

novita

2186179a80c94a46a6404fc2a84d31f8

Available

Input

$0.150 / 1M

Output

$0.150 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.150 / 1M
Output tokens$0.150 / 1M

Performance

Published evaluation results associated with this model.

General Reasoning

MMLU74.8
ARC-Challenge85.3
HellaSwag85.7
Winogrande79.6

Multilingual Performance

CMMLU75.3
XTREME72.1
Flores-10168.9
MGSM78.2

Coding

HumanEval65.8
MBPP68.4
MultiPL-E61.3

Hybrid Advantages

ZH-EN Translation84.7
Cross-Cultural QA80.2
Technical Documentation87.6

Distillation Metrics

Teacher Fidelity92.7
KL Divergence0.072
Task Transfer Efficiency94.1

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "2186179a80c94a46a6404fc2a84d31f8",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'