Skip to main content

DeepSeek R1 Distill Qwen 14B

DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Input / output price
$0.4312 / $1.12 per 1M
Context
33K tokens
Released
Jan 20, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "deepseek-r1-distill-qwen-14b".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Featherlessfeatherless/deepseek-r1-distill-qwen-14b
$0.4312/M$1.12/M

Pricing

USD per 1M tokens on Featherless, after gateway discounts.

Input
$0.4312 per 1M
Output
$1.12 per 1M
Cache read
$0.30 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.4312/MFeatherless

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

13tokens/sacross providers

Faster than 25% of the other 599 models on the gateway

Response latency

Lower is better

8.8sacross providers

Faster than 21% of the other 780 models on the gateway

Benchmarks

7 published scores from 2 sources, each linked to where it was published.

Published scores

BenchmarkScore
LiveCodeBenchhuggingface.co53.1%

Apps

Use DeepSeek R1 Distill Qwen 14B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

DeepSeek R1 Distill Qwen 14B FAQ

Short answers, built from the data on this page.

DeepSeek R1 Distill Qwen 14B is a model from Deepseek, released on Jan 20, 2025. DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

On the Respan gateway, DeepSeek R1 Distill Qwen 14B costs $0.4312 per 1M input tokens and $1.12 per 1M output tokens on Featherless, after gateway discounts.

DeepSeek R1 Distill Qwen 14B is served by Featherless.

DeepSeek R1 Distill Qwen 14B accepts up to 33K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "deepseek-r1-distill-qwen-14b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

DeepSeek R1 Distill Qwen 14B has 7 published benchmark scores, including LiveCodeBench 53.1%, GPQA Diamond 59.1%, and MATH-500 93.9%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.