NEAR AI Cloud API pricing
9 NEAR AI Cloud models. Source: https://near.ai/pricing
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU) · Jasnah Inc. d/b/a NEAR AI, a Delaware corporation (near.ai/privacy-policy); Terms governed by Delaware law. City not published.
- EU data residency
- unknown
- Residency notes
- Pricing page and docs do not publish serving regions. All listed models run in hardware TEEs with attestation; 'Private TEE' = NEAR AI's own enclaves, 'Private 3P TEE' = an attested third-party provider's enclave. Privacy policy: personal data may be transferred outside the EEA/UK/Switzerland (SCCs). OpenRouter's provider list gives no HQ or datacenters.
- Residency source
- https://near.ai/privacy-policy
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.
9models
9 of 9 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| NEAR AI Cloud Inference host | GLM 5.3 Flash | $0.08 | $0.50 | — | $0.185 | — | unknown |
| NEAR AI Cloud Inference host | Qwen3-VL-30B-A3B-Instruct | $0.15 | $0.55 | — | $0.25 | — | unknown |
| NEAR AI Cloud Inference host | Qwen 3.8 27B | $0.04 | $1.35 | — | $0.368 | — | unknown |
| NEAR AI Cloud Inference host | Qwen 3.6 35B A3B FP8 | $0.17 | $1.10 | — | $0.403 | — | unknown |
| NEAR AI Cloud Inference host | deepseek-v3.2 | $1.10 | $1.10 | — | $1.10 | — | unknown |
| NEAR AI Cloud Inference host | qwen3.5-397b-a17b | $0.50 | $3.30 | — | $1.20 | — | unknown |
| NEAR AI Cloud Inference host | Kimi K2.6 | $0.81 | $3.85 | — | $1.57 | — | unknown |
| NEAR AI Cloud Inference host | GLM 5.3 | $1.80 | $5.75 | — | $2.79 | — | unknown |
| NEAR AI Cloud Inference host | Kimi K3 | $3.30 | $16.50 | — | $6.60 | — | 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. 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.