Inception Labs / inception/mercury-2-free

Mercury 2 (Free) - access through LLMTR

Mercury 2 is Inception Labs' diffusion language model (dLLM). Instead of emitting tokens strictly one after another it produces several in parallel and refines them step by step, which in practice means markedly lower latency than comparable models. This row is served free from a sponsored token pool Inception granted us, and is bounded by a per-user token allowance. It has a 128,000-token context window and a single response can be at most 50,000 tokens. It supports tool/function calling (sequential; parallel calls are not available yet) and schema-enforced JSON output. It accepts text only — no image or audio input. The model reasons by default and those reasoning tokens count as output, so they draw down your allowance even on short questions; use the `:minimal` suffix for the lightest setting when you need speed or economy. The levels are `:minimal`, `:low`, `:medium` and `:high`, and the default is `medium`. When your allowance or the sponsored period runs out, requests fail with an explicit error pointing you at the metered `inception/mercury-2` row.

Technical specifications

Canonical IDinception/mercury-2-free
ProviderInception Labs
Context window128,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENSNot available
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENSNot available
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENSNot available

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"inception/mercury-2-free","messages":[{"role":"user","content":"Hello"}]}'

Related models