LLMDarkbloom API pricing
17 Darkbloom models. Source: https://www.darkbloom.ai/pricing
- Provider type
- Inference host
- Server location (where inference runs)
- Decentralized network of Apple Silicon Macs (typically US) · source
- Regions
- US
- Company HQ (secondary)
- US (outside EU) · Operated by Eigen Labs, Inc., a Delaware corporation (Delaware Division of Corporations file no. 6042430, incorporated 2021-06-29; Delaware Secretary of State good-standing certificate dated 2024-01-24, authentication 202657158, verifiable at corp.delaware.gov/authver.shtml). California foreign qualification, Secretary of State entity no. 6188353 (Statement and Designation filed 2024-04-15). The latest California Statement of Information obtained (file BA20250345573, filed 2025-02-18) lists the principal office of record as 1401 21st St, Ste R, Sacramento, CA 95811, USA, which is a commercial registered-agent address (Registered Agents Inc). Earlier official CA filings (2024-04-15 and 2024-07-02) listed the principal office as 15790 Redmond Way #1176, Redmond, WA 98052, and directors remain listed at a Redmond, WA address. These are official SOS-stamped filings, retrieved as republished by bizprofile.net after the live California BizFile and Delaware ICIS portals blocked unattended access. Darkbloom Terms name Eigen Labs, Inc. but give no address. No LEI found in GLEIF. Checked 2026-11-10. · legal source
- EU data residency
- no
- Residency notes
- Darkbloom is a decentralized inference platform on independently operated Apple Silicon Macs. Terms and Privacy (updated 2026-08-28) do not offer an EU region; node location depends on volunteer operators and is typically in the US.
- Listing note
- USD per-token rates from the public pricing table. The generic fallback rate on that page is not listed as a model. Context windows are omitted because they are not published there. The models API requires authentication, so rows are verified against the public pricing page.
- Residency source
- https://www.darkbloom.ai/privacy
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Tap a box to filter by it; tap it again to remove that filter. Filters combine.
17 of 17 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Darkbloom Inference host | gpt-oss-20b | $0.018 | $0.09 | $0.009 | $0.036 | — | no |
| Darkbloom Inference host | NVIDIA Nemotron 3.5 Lightning | $0.025 | $0.12 | $0.0125 | $0.0488 | — | no |
| Darkbloom Inference host | Gemma 4 26B | $0.04 | $0.15 | $0.01 | $0.0675 | — | no |
| Darkbloom Inference host | Gemma 4 26B 8-bit | $0.04 | $0.15 | $0.01 | $0.0675 | — | no |
| Darkbloom Inference host | Gemma 4 26B QAT 4-bit | $0.04 | $0.15 | $0.01 | $0.0675 | — | no |
| Darkbloom Inference host | Ternary Bonsai 2 9B MLX 2-bit | $0.08 | $0.13 | $0.04 | $0.0925 | — | no |
| Darkbloom Inference host | Qwen3.5 9B | $0.08 | $0.13 | $0.04 | $0.0925 | — | no |
| Darkbloom Inference host | GLM 5.3 Flash | $0.065 | $0.18 | $0.012 | $0.0938 | — | no |
| Darkbloom Inference host | NVIDIA Nemotron 3.5 Super | $0.06 | $0.35 | $0.01 | $0.133 | — | no |
| Darkbloom Inference host | Flint Int4 | $0.05 | $0.40 | $0.025 | $0.138 | — | no |
| Darkbloom Inference host | MiMo V2.6 Flash MoPD | $0.10 | $0.28 | $0.05 | $0.145 | — | no |
| Darkbloom Inference host | Qwen3 VL 30B A3B Instruct | $0.09 | $0.40 | $0.045 | $0.168 | — | no |
| Darkbloom Inference host | Ternary Bonsai 2 27B | $0.075 | $0.50 | $0.0375 | $0.181 | — | no |
| Darkbloom Inference host | Qwen3.8 Flash Next | $0.13 | $0.40 | $0.065 | $0.198 | — | no |
| Darkbloom Inference host | Qwen3.6 35B A3B VL MTP MXFP8 | $0.05 | $0.70 | $0.025 | $0.212 | — | no |
| Darkbloom Inference host | Qwen3.5 35B A3B | $0.065 | $0.75 | $0.0325 | $0.236 | — | no |
| Darkbloom Inference host | Qwen3.8 27B 4-bit MTP | $0.035 | $1.50 | $0.0175 | $0.401 | — | no |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with €, CHF or ₹: those are as published and not converted. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09); sorting still uses the published ₹ amount. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. Click a header to sort.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.