inception

Inception: Mercury 2.5

inception/mercury-2.5

A text reasoning model tested in Jevrouter's production connectivity checks. A short response completed with a 512-token limit; the earlier 64-token check returned no final text. This is a connectivity observation, not a quality or speed benchmark.

text

Try in Playground ↗

Input / 1M tokens$0.04

Output / 1M tokens$0.15

Context window260,000

Maximum output65,536

Provider-supported parameters

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

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolsstreamdeveloper_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: cmub1179j001wr82gui6qm530:1

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.00000004",
  "completion": "0.00000015",
  "input_cache_read": "0.000000004"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Inspect finish_reason and usage before treating an empty answer as a transport failure.
Compare latency on your own workload; provider speed claims are not Jevrouter measurements.

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": "inception/mercury-2.5",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly: catalog ready"
    }
  ],
  "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.

OpenAI: GPT-5 Mini Google: Gemini 2.5 Flash

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