Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

DeepSeek OCR 2

deepseek-ocr-2by DeepSeekZDR (all rungs)
Try in Chat

DeepSeek's document recognition model. Send a page image with a short prompt (for example "Free OCR." for plain text, or "<|grounding|>Convert the document to markdown." for Markdown with layout boxes) and it returns the recognized text. Image in, text out; no tool calling.

Context

8K

Max output

8K

Price per million tokens

$0.030in$0.030cached$0.030out

Released

-

Waterfall

  1. 1
    Experiential Cloud$0.030/$0.03099.9% up--

Quickstart

I want you to route my LLM calls for "deepseek-ocr-2" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
3. Use the model id "deepseek-ocr-2" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text, image

Sampling

Temperature

Streaming

Streaming

Limits

Max output8,192Max-tokens fieldmax_tokens

Sending an unsupported field? See error reference

Providers serving this model1
Status
Experiential Cloudexperientialno datano data99.9%#1 / 18K8K$0.030$0.030$0.030-ZDRactive-
Hugging Face