DeepSeek logo

DeepSeek R1 Distill Qwen 14B

Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek R1 Distill Qwen 14B is DeepSeek's language model with a 131K context window and up to 16K output tokens, available from 5 providers, starting at $0.07 / 1M input and $0.07 / 1M output. A 14B Qwen-based model distilled from DeepSeek R1, balancing strong reasoning performance with moderate computational requirements.
Specifications
Canonical IDdeepseek-r1-distill-qwen-14b
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters14B
Benchmarks
Intelligence Index
9.8
#298
Math Index
55.7
#122
MMLU-Pro
0.7
#175
GPQA
0.5
#345
HLE
0.0
#364
LiveCodeBench
0.4
#179
AIME
0.7
#40
IFBench
0.2
#387
Time to First Token
0.00s
#74
SciCode
0.2
#325
MATH-500
0.9
#35
AIME 2025
0.6
#122
LCR
0.1
#323
Output TPS
0.0
#330

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning✓
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
deepseek-r1-distill-qwen-14b
$0.144$0.431$0.072$0.215
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b
$0.2$0.2——
Hugging Face logo
Hugging Face
nscale:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
$0.2$0.2——
Novita logo
Novita
novita/deepseek/deepseek-r1-distill-qwen-14b
$0.15$0.15——
Nscale logo
Nscale
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
$0.07$0.07——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek R1 Distill Qwen 14B, ranked by cheapest on-demand price. The model needs about 34 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hrwestus2
g6e.xlargeAWSL40S45 GB$1.86/hrus-east-1
Standard_NV32as_v4AzureAMD Radeon Instinct MI2564 GB$1.86/hrwestus2
7 more instances can run DeepSeek R1 Distill Qwen 14B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek R1T2 Chimera164K——Available
DeepSeek R1 528164K$0.200$0.250Available
DeepSeek R1 Distill Qwen 32B131K$0.150$0.150Available
DeepSeek R1 Distill Llama 70B131K$0.200$0.375Deprecated
DeepSeek R1164K$0.280$0.400Available
DeepSeek R1 Distill Qwen 14B—131K$0.070$0.070Current
DeepSeek R1 Distill Llama 8B—131K$0.025$0.025Available
DeepSeek R1 Distill Qwen 1.5B—131K$0.090$0.090Available
DeepSeek R1 528 Turbo—33K$1.00$3.00Available
DeepSeek R1 528B—128K$0.550$2.19Available
DeepSeek R1 671B—131K$0.800$0.800Available

Model IDs

accounts/fireworks/models/deepseek-r1-distill-qwen-14b
deepseek-llm-r1-distill-qwen-14b
deepseek-r1-distill-qwen-14b
deepseek/deepseek-r1-distill-qwen-14b
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b
novita/deepseek/deepseek-r1-distill-qwen-14b
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B