NEAR AI
Explore NEAR AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
NEAR AInear-ai
Confidential
| Provider | NEAR AI |
|---|---|
| Routing status | Active |
| Provider website | https://near.ai/ |
| Models | 10 public models |
| Credits routes | 10 |
| Zero data retention | not claimed |
| Confidential compute | yes |
| Provider E2EE | yes |
| Policy note | TrustedRouter connects directly to the model workload and verifies the live TLS key, Intel TDX quote, NVIDIA GPUs, deployment action log, and pinned workload inside the TrustedRouter enclave before sending content. Verification fails closed. No separate ZDR claim is currently tracked. Policy source |
Measured performance
375 samplesContinuously sampled across NEAR AI's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | — |
|---|---|
| Effective throughput | 16 tok/s n=1 |
| Uptime | 0.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash | — | — | 0.00% | — | 36 |
| google/gemma-4-31b-it | — | — | 0.00% | — | 96 |
| openai/gpt-oss-120b | — | — | 0.00% | — | 39 |
| qwen/qwen3-vl-30b-a3b-instruct | — | — | 0.00% | — | 2 |
| qwen/qwen3.5-122b-a10b | — | — | 0.00% | — | 46 |
| qwen/qwen3.6-27b | — | — | 0.00% | — | 6 |
| qwen/qwen3.6-35b-a3b | — | — | 0.00% | — | 51 |
| qwen/qwen3.8-27b | — | — | 0.00% | — | 73 |
| z-ai/glm-5.1 | — | — | 0.00% | — | 2 |
| z-ai/glm-5.2 | — | 16 tok/s n=1 | 0.00% | — | 24 |
NEAR AI performance history · Full provider & model leaderboard.
Models served by NEAR AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#46 | 1,024,000 | $0.17935/1M | $0.036925/1M | $0.36925/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#80 | 262,144 | $0.13715/1M | $0.02743/1M | $0.422/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#69 | 131,072 | $0.15825/1M | $0.03165/1M | $0.58025/1M |
qwen/qwen3-vl-30b-a3b-instructQwen: Qwen3 VL 30B A3B Instruct |
— | 262,144 | $0.15825/1M | $0.03165/1M | $0.58025/1M |
qwen/qwen3.5-122b-a10bQwen: Qwen3.5-122B-A10B |
— | 262,144 | $0.422/1M | $0.0844/1M | $3.376/1M |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 111#56 | 262,144 | $0.342875/1M | $0.1688/1M | $3.42875/1M |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 100#89 | 262,144 | $0.17935/1M | $0.05908/1M | $1.1605/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 112#52 | 1,000,000 | $0.4642/1M | $0.04642/1M | $3.4815/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#43 | 200,000 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#27 | 1,048,576 | $1.477/1M | $0.3165/1M | $4.642/1M |
Questions
Does NEAR AI have zero data retention?
TrustedRouter does not currently mark NEAR AI as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is NEAR AI end-to-end encrypted?
TrustedRouter records NEAR AI as supporting provider-side confidential compute and end-to-end encrypted inference. The route-specific model page shows whether that protection applies to a particular endpoint.
Which NEAR AI models are available through TrustedRouter?
This page currently lists 10 public NEAR AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.