FriendliAI
Explore FriendliAI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
FriendliAIfriendli
No provider claim
| Provider | FriendliAI |
|---|---|
| Provider website | https://friendli.ai/ |
| Models | 7 public models |
| Prepaid routes | 7 |
| BYOK routes | 7 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. Friendli's legal/privacy terms are linked for users who need to review API data handling. Policy source |
Measured performance
44 samplesContinuously sampled across FriendliAI'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 | 1716 ms |
|---|---|
| Effective throughput | 79 tok/s n=3 |
| Uptime | 100.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-5.1 | 793 ms | 793 ms | — | 100.00% | — | 6 |
| lgai-exaone/k-exaone-2.0-750b-a37b | 1412 ms | 1411 ms | — | 100.00% | — | 7 |
| minimax/minimax-m2.5 | 1447 ms | 1447 ms | — | 100.00% | — | 5 |
| z-ai/glm-5.2 | 1716 ms | 1716 ms | 79 tok/s n=2 | 100.00% | — | 6 |
| lgai-exaone/k-exaone-236b-a23b | 2507 ms | 2507 ms | — | 100.00% | — | 6 |
| google/gemma-4-31b-it | 2826 ms | 2825 ms | 198 tok/s n=1 | 100.00% | — | 7 |
| deepseek/deepseek-v3.2 | 3198 ms | 3197 ms | — | 100.00% | — | 7 |
FriendliAI performance history · Full provider & model leaderboard.
Models served by FriendliAI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 103#57 | 163,840 | 2 | $0.525/1M | $1.575/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#66 | 262,144 | 2 | $0.147/1M | $0.42/1M | prepaid BYOK |
lgai-exaone/k-exaone-2.0-750b-a37bLGAI-EXAONE/K-EXAONE-2.0-750B-A37B |
— | 262,144 | 2 | $0.63/1M | $2.52/1M | prepaid BYOK |
lgai-exaone/k-exaone-236b-a23bLGAI-EXAONE/K-EXAONE-236B-A23B |
— | 262,144 | 2 | $0.21/1M | $0.84/1M | prepaid BYOK |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 105#56 | 204,800 | 2 | $0.315/1M | $1.26/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#32 | 204,800 | 2 | $1.47/1M | $4.62/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#16 | 1,048,576 | 2 | $1.47/1M | $4.62/1M | prepaid BYOK |
Questions
Does FriendliAI have zero data retention?
TrustedRouter does not currently mark FriendliAI 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 FriendliAI end-to-end encrypted?
TrustedRouter does not currently mark FriendliAI as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which FriendliAI models are available through TrustedRouter?
This page currently lists 7 public FriendliAI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.