Question 1

What is DeepSeek OCR 2?

Accepted Answer

DeepSeek OCR 2 is a model from Deepseek, released on Jan 27, 2026. DeepSeek OCR 2 is a DeepSeek model tuned for strong reasoning and coding performance at competitive cost. DeepSeek OCR 2 is a DeepSeek model tuned for strong reasoning and coding performance at competitive cost. Up to 8K context window.

Question 2

How much does DeepSeek OCR 2 cost?

Accepted Answer

On the Respan gateway, input starts at $0.03 per 1M tokens on Novita, and output starts at $0.03 per 1M tokens on Novita, after gateway discounts.

Question 3

Which providers serve DeepSeek OCR 2 on Respan?

Accepted Answer

DeepSeek OCR 2 is served by Novita.

Question 4

What is DeepSeek OCR 2's context window?

Accepted Answer

DeepSeek OCR 2 accepts up to 8K tokens of context.

Question 5

How do I use DeepSeek OCR 2 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-ocr-2". 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 OCR 2?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Novita at 53 tokens per second, and the lowest response latency was 0.4 seconds on Novita. Speed varies with request size and provider.

DeepSeek OCR 2

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

DeepSeek OCR 2 FAQ

Certified where it counts.

Works with your entire stack

Built for AI agents.
Break less.
Ship more.