Question 1

What is DeepSeek R1?

Accepted Answer

DeepSeek R1 is a model from Deepseek, released on Jan 20, 2025. DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. $0.70 per million input tokens, $2.50 per million output tokens. 163,840 token context window, maximum output of 16,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does DeepSeek R1 cost?

Accepted Answer

On the Respan gateway, input starts at $0.50 per 1M tokens on DeepInfra and OpenRouter, and output starts at $2.15 per 1M tokens on DeepInfra, after gateway discounts. Averaged across 9 providers, it costs $1.84 per 1M input tokens and $4.12 per 1M output tokens.

Question 3

Which providers serve DeepSeek R1 on Respan?

Accepted Answer

9 providers serve DeepSeek R1: DeepInfra, OpenRouter, IO.net, Novita, Tera, Google Vertex AI, and 2 more. Tera, Google Vertex AI, TogetherAI, and Azure DeepSeek require your own provider API key (BYOK).

Question 4

What is DeepSeek R1's context window?

Accepted Answer

DeepSeek R1 accepts up to 164K tokens of context on its largest provider route.

Question 5

How do I use DeepSeek R1 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". 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?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was DeepInfra at 19 tokens per second, and the lowest response latency was 3.2 seconds on DeepInfra. Speed varies with request size and provider.

Question 7

Where does DeepSeek R1 rank on the Respan Index?

Accepted Answer

DeepSeek R1 scores 17.9 out of 100 on the Respan Index v1.1, ranking #107 of 138 models. By category: Coding 5.2, Agents 17.8, Reasoning 13.4, Knowledge & language 17.1, and Human preference 47.2. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does DeepSeek R1 score on benchmarks?

Accepted Answer

DeepSeek R1 has 12 published benchmark scores, including SWE-bench Verified 49.2%, BALROG 34.9%, and GPQA Diamond 76.3%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
DeepInfra`deepinfra/deepseek-ai/DeepSeek-R1-0528`	164K	$0.50/M	$2.15/M
OpenRouter`openrouter/deepseek/deepseek-r1-0528`	164K	$0.50/M	$2.15/M
IO.net`ionet/deepseek-ai/DeepSeek-R1-0528`	128K	$0.53/M	$2.19/M
NovitaSave 10%`novita/deepseek/deepseek-r1-0528`	164K	$0.63/M	$2.25/M
OpenRouter`openrouter/deepseek/deepseek-r1`	64K	$0.70/M	$2.50/M
TeraBYOK only`tera/deepseek-ai/DeepSeek-R1-0528`	164K	$1.35/M	$5.40/M
Google Vertex AIBYOK only`vertex_ai/deepseek-ai/deepseek-r1-0528-maas`	164K	$1.35/M	$5.40/M
TogetherAIBYOK only`together_ai/deepseek-ai/DeepSeek-R1-0528`	164K	$3.00/M	$7.00/M
Azure DeepSeekBYOK only`azure_deepseek/deepseek-r1`	64K	$8.00/M	$8.00/M	—

DeepSeek R1

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding2

Agents

Apps

DeepSeek R1 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Reasoning3

Math3

Knowledge2

Arena1