deepseek

DeepSeek: R1

deepseek/deepseek-r1

A reasoning-oriented text candidate. Give it a task with a verifiable outcome and account for the full reported token usage when comparing costs.

text

Try in Playground ↗

Input / 1M tokens$0.7

Output / 1M tokens$2.5

Context window64,000

Maximum output16,000

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_pstreamdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-09-22T08:51:50.371Z · Price version: cmub11cjm019wr82gbu9rto87:1

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.0000007",
  "completion": "0.0000025"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Set an output budget that covers both reasoning and final content.
Treat reasoning text as model output, not as an independently verified explanation of correctness.

Start with the example below, then test representative inputs against your own acceptance criteria.

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "deepseek/deepseek-r1",
  "messages": [
    {
      "role": "user",
      "content": "All packages with a red label require inspection. Package A has a red label. What can be concluded, and what cannot be concluded, about package B?"
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Connect with the OpenAI Python SDK →Estimate this model’s cost →Budgets, request status and safe retries →

Related models to evaluate

Use identical inputs and scoring rules. No ranking is implied by this selection.

DeepSeek: DeepSeek V3.1 OpenAI: GPT-5 Mini

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.