Home › Frontier and closed › inception
Mercury 2.5 inception
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.
- 2026-09-08 · API only source seeded from the earliest dated observation when first seen · observed 2026-10-07 20:20 UTC
- next · Next expected: additional third-party providers (closed weights; none expected on Hugging Face)
Description
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
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 2.5, 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: $0.04/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Inception openrouter | inception/mercury-2.5 | 254K | unknown | $0.04 | $0.15 | — | — | yes | live | 2026-10-24 |
No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.0040/M (source, observed 2026-10-24).
Facts
| Context length | 260,000 tokens (254K) · OpenRouter listing |
|---|---|
| Modalities | text → text |
| Max completion tokens | 65,536 |
| Supported parameters | include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools |
| Openness | Closed weights · closed lab |
| Stage | API only |
| Confidence | medium |
| Pricing (USD per M tokens) |
in $0.04 · out $0.15 · cache read $0.0040 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.
| Model | Org | Params | Context | $/M in | License | Why it is here |
|---|---|---|---|---|---|---|
| Meta-Llama-3-8B-Instruct | meta-llama | 8.03B | — | — | llama3 | closest by rank, context and price |
| gpt-oss-120b | openai | 117B | 128K | $0.03 | apache-2.0 | cheaper input price ($0.0296/M vs $0.04/M) |
| GLM-4.7-Flash | zai-org | 31.2B | 198K | $0.06 | mit | similar context (203K) |
| Llama-3.2-3B-Instruct | meta-llama | 3.21B | 128K | $0.05 | llama3.2 | closest by rank, context and price |
| gpt-oss-20b | openai | 20.9B | 128K | $0.02 | apache-2.0 | cheaper input price ($0.018/M vs $0.04/M) |
Get alerts
Watch the release radar
- /feeds/upcoming.xml(RSS 2.0) · upcoming and just-released models, one item per entry
- /feeds/upcoming.json(JSON Feed 1.1) · same, JSON Feed 1.1
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
Sources
- openrouter inception/mercury-2.5 · observed 2026-10-24 21:26 UTC
Radar run: 2026-10-25 06:51 UTC · Last verified 2026-10-25 06:51 UTC