LLMRelace API pricing
10 Relace models. Source: https://docs.relace.ai/docs/open-models/quickstart
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU) · Operated by Squack, Inc. (brand Relace), 130 Bush Street, San Francisco, CA 94104, USA (Privacy Policy, effective 2026-09-21); Terms of Use governed by California law. Checked 2026-10-26. · legal source
- EU data residency
- unknown
- Residency notes
- Docs do not publish serving regions; careers page says Relace runs requests 'on our own GPU fleet around the world'. OpenRouter's provider list gives no HQ or datacenters.
- Residency source
- https://relace.ai/careers
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.
10 of 10 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Relace Inference host | DeepSeek V4 Flash 0731 | $0.07 | $0.14 | $0.014 | $0.0875 | 1M | unknown |
| Relace Inference host | GLM 5.3 Flash | $0.075 | $0.50 | $0.0075 | $0.181 | 1M | unknown |
| Relace Inference host | DeepSeek V4.1 Flash | $0.20 | $0.60 | $0.008 | $0.30 | 1M | unknown |
| Relace Inference host | DeepSeek V4.1 Flash 1017 | $0.20 | $0.60 | $0.008 | $0.30 | 1M | unknown |
| Relace Inference host | DeepSeek V4 Flash 0423 | $0.0277 | $1.28 | $0.0277 | $0.341 | 1M | unknown |
| Relace Inference host | DeepSeek V4 Pro 0813 | $0.50 | $2.00 | $0.05 | $0.875 | 1M | unknown |
| Relace Inference host | DeepSeek V4 Pro 0423 (Preview) | $0.45 | $3.00 | $0.09 | $1.09 | 1M | unknown |
| Relace Inference host | GLM 5.3 | $0.75 | $2.40 | $0.075 | $1.16 | 1M | unknown |
| Relace Inference host | GLM 5.2 | $0.40 | $4.00 | $0.08 | $1.30 | 1M | unknown |
| Relace Inference host | Kimi K3 | $2.00 | $14.00 | $0.30 | $5.00 | 1M | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. 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.