Mercury 3
Inception LabsReleased Oct 19, 2026Closed weightsmercury-3
- Reasoning
- yes, with effort levels
- Context
- 1M tokens
- Max output
- 131K tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode
- Inception Labs's API
- yes, as mercury-3
Read Nov 3, 11:57 UTC from the hosts' published offers and OpenRouter, spec sheet from Inception Labs
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Inception Labs−50% | $0.10 | $0.35 | $0.01 | 378 | 2.82 s | 99.2% | Nov 3 |
| OpenRouter−50% | $0.10 | $0.35 | $0.01 | 378 | 2.82 s | 99.2% | Nov 3 |
| Vercel AI Gateway | $0.10 | $0.35 | $0.01 | — | — | — | Nov 3 |
3 of 3 providers · prices per million tokens, read Nov 3, 11:57 UTC · speed: OpenRouter, median of the last 30 min, read Nov 3, 11:57 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Inception Labs | — | 1M | 128K | yes | yes | yes |
| OpenRouter | — | 1M | 128K | yes | yes | yes |
| Vercel AI Gateway | — | 1M | 128K | — | — | — |
As served by each host and declared to OpenRouter; not verified by us · weights: the precision the host declares
Mercury 3 spec sheet, field by field, with sources
Mercury 3 spec sheetmaker-declared
What Inception Labs declares, from its own weights and docs. What each host serves is in the offers: both can be true.
- Context window
- 1,000,000 tokens
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- not applicable — no weights publishedcurated · read 2026-10-25
- License
- Proprietary — API onlycurated · read 2026-10-25Scope: the license of the published weights only — not the maker's acceptable-use policy, nor the terms of the host you call.
- Knowledge cutoff
- not published by the maker
- Modalities
- text → text
- Max output (official)
- 131,072 tokens
- Release date
- October 19, 2026maker's docs · read 2026-10-25
- Maker lifecycle status
- General availabilitymaker's docs · read 2026-10-25
docs.inceptionlabs.ai · maker's documentation · read 2026-10-25 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Inception Labs | $0.28 | $0.97 | $0.75 |
| OpenRouter | $0.28 | $0.97 | $0.75 |
| Vercel AI Gateway | $0.28 | $0.97 | $0.75 |
What each host bills for 1,000 requests of a representative job