Question 1

What is DeepSeek R1 Distill Qwen 14B?

Accepted Answer

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.

Question 2

How much does DeepSeek R1 Distill Qwen 14B cost?

Accepted Answer

On the Respan gateway, input starts at $0.43 per 1M tokens on Featherless, and output starts at $1.12 per 1M tokens on Featherless, after gateway discounts. Averaged across 2 providers, it costs $1.02 per 1M input tokens and $1.36 per 1M output tokens.

Question 3

Which providers serve DeepSeek R1 Distill Qwen 14B on Respan?

Accepted Answer

2 providers serve DeepSeek R1 Distill Qwen 14B: Featherless and TogetherAI. TogetherAI requires your own provider API key (BYOK).

Question 4

What is DeepSeek R1 Distill Qwen 14B's context window?

Accepted Answer

DeepSeek R1 Distill Qwen 14B accepts up to 131K tokens of context on its largest provider route.

Question 5

How do I use DeepSeek R1 Distill Qwen 14B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ 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.

Question 6

How fast is DeepSeek R1 Distill Qwen 14B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Featherless at 39 tokens per second, and the lowest response latency was 7.6 seconds on Featherless. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
Featherless`featherless_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B`	33K	$0.43/M	$1.12/M
TogetherAIBYOK only`together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B`	131K	$1.60/M	$1.60/M

DeepSeek R1 Distill Qwen 14B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps