Home › Frontier and closed › inception

Mercury 3 inception

Closed weights API only listed on OpenRouter 2026-10-16 (9d ago) · source Last verified 2026-10-25 06:51 UTC Docs ↗ OpenRouter ↗

Release timeline

Stages observed by the nightly radar: announced → API only → weights public → served by third parties. Each entry carries the source it was seen at.

  1. 2026-10-16 · API only source
    seeded from the earliest dated observation when first seen · observed 2026-10-23 18:57 UTC

Description

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

via OpenRouter listing · observed 2026-10-24 21:26 UTC. The listing text is the provider's own description, not an assessment.

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Mercury 3, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.10/M.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
Inception
openrouter
inception/mercury-3 977K unknown $0.10 $0.35 — — yes live 2026-10-24

No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.01/M (source, observed 2026-10-24).

Facts

Context length1,000,000 tokens (977K) · OpenRouter listing
Modalitiestext → text
Max completion tokens131,072
Supported parametersinclude_reasoning, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools
OpennessClosed weights · closed lab
StageAPI only
Confidencemedium
Pricing (USD per M tokens) in $0.10 · out $0.35 · cache read $0.01
OpenRouter list price (cheapest live endpoint) · source · observed 2026-10-24 21:26 UTC

Open alternatives 5

Nearest open-weights models by modality, context and price on this watch list. Not a quality ranking.

ModelOrgParamsContext$/M inLicenseWhy it is here
GLM-5.3 zai-org 753B 1M $0.07 other similar context (1.05M), cheaper input price ($0.075/M vs $0.1/M)
Meta-Llama-3-8B-Instruct meta-llama 8.03B — — llama3 closest by rank, context and price
DeepSeek-V4-Flash-0731 deepseek-ai 304B 1M $0.04 mit similar context (1.05M), cheaper input price ($0.0422/M vs $0.1/M)
DeepSeek-V4-Pro deepseek-ai 1.60T 1M $0.21 mit similar context (1.05M)
GLM-5.2 zai-org 753B 1M $0.03 mit similar context (1.05M), cheaper input price ($0.0341/M vs $0.1/M)

Get alerts

Watch the release radar

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.

Sources

Radar run: 2026-10-25 06:51 UTC · Last verified 2026-10-25 06:51 UTC