Featherless AI
Try Featherless AI on us. Starter credit covers your first requests, then one key reaches all 36 Featherless AI models, with the privacy posture shown on every route.
Featherless AIfeatherless
These privacy labels describe Featherless AI, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Featherless AI |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://featherless.ai/ |
| Models | 36 public models |
| Credits routes | 36 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| Policy note | Featherless's published privacy policy states that prompts and completions are neither collected nor stored. Account, payment and usage metadata, including token counts and sampler settings, may be retained. This is policy-backed ZDR, not verified confidential compute or E2EE. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
18 samplesContinuously sampled across Featherless 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 | 3143 ms |
|---|---|
| Effective throughput | 62 tok/s n=9 |
| Uptime | 88.89% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-4.7-flash | 1230 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 1449 ms | 42 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3-coder-next | 1919 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 2185 ms | 75 tok/s n=2 | 100.00% | — | 1 |
| stepfun-ai/step-5-preview | 2656 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4.1-flash | 2913 ms | — | 100.00% | — | 1 |
| z-ai/glm-5 | 3111 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 3143 ms | 62 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 3870 ms | — | 100.00% | — | 1 |
| stepfun-ai/step-3.7-flash | 4404 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3.1-flash | 5195 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-2.4t-a95b | 11299 ms | — | 100.00% | — | 1 |
| qwen/qwen-agentworld-35b-a3b | 13112 ms | — | 33.33% | — | 3 |
| qwen/qwen3.6-27b | 19203 ms | — | 100.00% | — | 2 |
| minimax/minimax-m3 | — | 31 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2.6 | — | 35 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.3 | — | 182 tok/s n=1 | — | — | 0 |
Featherless AI performance history · Full provider & model leaderboard.
Models served by Featherless 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 121#42 | 1,048,576 | $0.1477/1M | Not published | $0.2954/1M |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.1477/1M | Not published | $0.2954/1M |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 123#34 | 1,048,576 | $1.688/1M | Not published | $3.376/1M |
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#24 | 1,048,576 | $0.3165/1M | Not published | $1.266/1M |
deepseek/deepseek-v4.1-flash-1017DeepSeek: DeepSeek V4.1 Flash 1017 |
IQ 128#19 | 1,048,576 | $0.237375/1M | Not published | $0.9495/1M |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 103#111 | 196,608 | $0.311225/1M | Not published | $1.266/1M |
minimax/minimax-m2.7MiniMax: MiniMax M2.7 |
IQ 105#96 | 196,608 | $0.3165/1M | Not published | $1.266/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 114#64 | 1,048,576 | $0.58025/1M | Not published | $2.321/1M |
minimax/minimax-m3.1-flashMiniMax: MiniMax M3.1 Flash |
IQ 120#49 | 1,048,576 | $0.15825/1M | Not published | $0.633/1M |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
IQ 110#82 | 262,144 | $0.844/1M | Not published | $3.587/1M |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 114#62 | 262,144 | $0.844/1M | Not published | $3.587/1M |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 111#77 | 262,144 | $0.844/1M | Not published | $3.587/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#22 | 1,048,576 | $3.165/1M | Not published | $15.825/1M |
qwen/qwen-agentworld-35b-a3bQwen/Qwen-AgentWorld-35B-A3B |
— | 32,768 | $0.422/1M | Not published | $4.22/1M |
qwen/qwen3-coder-nextQwen: Qwen3 Coder Next |
— | 262,144 | $0.1688/1M | Not published | $1.21325/1M |
qwen/qwen3.5-27bQwen: Qwen3.5-27B |
— | 262,144 | $0.3165/1M | Not published | $2.532/1M |
qwen/qwen3.5-2bQwen/Qwen3.5-2B |
IQ 83#173 | 32,768 | $0.0844/1M | Not published | $0.422/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.58025/1M | Not published | $3.6925/1M |
qwen/qwen3.5-4bQwen/Qwen3.5-4B |
IQ 90#162 | 32,768 | $0.1055/1M | Not published | $0.211/1M |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 96#145 | 262,144 | $0.17935/1M | Not published | $0.26375/1M |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 110#83 | 262,144 | $0.3376/1M | Not published | $2.8485/1M |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 104#107 | 262,144 | $0.19623/1M | Not published | $1.175059/1M |
qwen/qwen3.8-2.4t-a95bQwen: Qwen3.8 2.4T A95B |
IQ 123#36 | 1,000,000 | $1.055/1M | Not published | $4.22/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 115#57 | 65,536 | $0.422/1M | Not published | $3.165/1M |
qwen/qwen3.8-flash-nextQwen: Qwen3.8-Flash-Next |
— | 262,144 | $0.15825/1M | Not published | $0.5275/1M |
qwen/webworld-8bQwen/WebWorld-8B |
— | 32,768 | $0.49374/1M | Not published | $1.9201/1M |
stepfun-ai/step-3.7-flashStepFun: Step-3.7-Flash |
IQ 103#113 | 256,000 | $0.211/1M | Not published | $1.21325/1M |
stepfun-ai/step-5-previewstepfun-ai/Step-5-Preview |
— | 1,048,576 | $1.055/1M | Not published | $2.8485/1M |
xiaomi/mimo-v2.5Xiaomi: MiMo-V2.5 |
IQ 108#89 | 1,050,000 | $0.157195/1M | Not published | $0.520115/1M |
xiaomi/mimo-v2.6-distill-qwen-9bXiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B |
— | 32,768 | $0.454916/1M | Not published | $1.1816/1M |
z-ai/glm-4.7-flashZ.ai: GLM 4.7 Flash |
— | 131,072 | $0.068892/1M | Not published | $0.422/1M |
z-ai/glm-5Z.ai: GLM 5 |
IQ 106#94 | 202,752 | $1.00225/1M | Not published | $3.32325/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 112#67 | 202,752 | $1.3715/1M | Not published | $4.5365/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 118#53 | 1,048,576 | $1.477/1M | Not published | $4.642/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 124#30 | 1,048,576 | $1.477/1M | Not published | $4.642/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 119#50 | 1,048,576 | $0.15825/1M | Not published | $0.5275/1M |
Questions
Does Featherless AI have zero data retention?
TrustedRouter records Featherless AI as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Featherless AI end-to-end encrypted?
TrustedRouter does not currently mark Featherless AI 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 Featherless AI models are available through TrustedRouter?
This page currently lists 36 public Featherless AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.