api-featherless-ai
Measured metrics
- Overall score
- 9.3 / 10 ★★★★⯨
- Stability band
- Very stable
- Uptime
- 100% （Measured here）
- Response latency
- 1195 ms
- Model count
- 60
- Backend engine
- —
- Verification
- Verified
- Last checked
- 2026-10-19
- Outbound clicks
- 64 clicks
Uptime basis: Measured here, from 61 valid checks over the last 30 days, per-day reachability (not per request). The resolution is one day — 1% means roughly 0 unreachable days out of 30.
Published rates & minimums
The figures below are published by the service itself on public channels. We only log them, and they are not our measurements — always confirm on the service's own billing page.
Billing model: Pay-as-you-go
A rate of 1.0 means official list price; 0.3 means you pay 30% of it. Not sure how the maths works out? Run the rate calculator →
About this service
A globally hosted relay that fronts a range of AI model APIs. It exposes a standard /v1/models endpoint. Its site is at api.featherless.ai. An overseas payment method is required — check that the host is reachable from your network before signing up.
Strengths
- Overseas-hosted, so no China-specific network restrictions
- Exposes a standard /v1/models endpoint (confirmed by our own probe)
- Marked as verified by this site
Watch out for
- Check reachability from your own network before committing
Model families supported
This service has not published a list of model families, and no endpoint probe has completed yet.
Show the 60 models the endpoint probe detected (first 40)
recursal/EagleX_1-7Trecursal/EagleX_1-7T_ChatRWKV/EagleX-7B-Chat-V0.5-pthRWKV/v6-Finch-14B-HFmeta-llama/Llama-3.3-70B-Instructunsloth/Llama-3.3-70B-InstructSao10K/L3.3-70B-Euryale-v2.3EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0recursal/QRWKV6-32B-Instruct-Preview-v0.1KaraKaraWitch/Llama-MiraiFanfare-3.3-70Bhuihui-ai/Llama-3.3-70B-Instruct-abliteratedEVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1pankajmathur/orca_mini_v8_0_70bNaniDAO/Llama-3.3-70B-Instruct-ablatedTheDrummer/Anubis-70B-v1pankajmathur/orca_mini_v8_1_70bPaxwellPaxwell/Llama-3.3-70B-Memo-law-Instruct-v2Nohobby/L3.3-Prikol-70B-v0.1anitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1Saxo/Linkbricks-Horizon-AI-Llama-3.3-Korean-70B-sft-dpoPaxwellPaxwell/Llama-3.3-70B-Memo-law-Instruct-v1Sao10K/70B-L3.3-mhnnn-x1Sao10K/70B-L3.3-Cirrus-x1rombodawg/Rombos-LLM-70b-Llama-3.3SicariusSicariiStuff/Negative_LLAMA_70Bknifeayumu/Negative-Anubis-70B-v1Steelskull/L3.3-MS-Nevoria-70bpankajmathur/orca_mini_v9_3_70BDaemontatox/Llama3.3-70B-CogniLinksophosympatheia/Nova-Tempus-70B-v0.1finis-est/L3.3-Faust-70B-exp.001KaraKaraWitch/Llama-3.X-Workout-70BDebateLabKIT/Llama-3.3-Argunaut-1-70B-SFTdeepseek-ai/DeepSeek-R1-Distill-Llama-70Bcodelion/Llama-3.3-70B-o1ProdeusUnity/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123Steelskull/L3.3-Nevoria-R1-70brobust-rlhf/Llama-3.3-70B-Instruct_ftjob-1e99f7048485-mergedTarek07/Progenitor-V1.1-LLaMa-70BSteelskull/L3.3-Damascus-R1 Daily monitoring log
| Date | Uptime | Avg latency | Samples | Status |
|---|---|---|---|---|
| 2026-10-27 | 100.00% | 1195 ms | 1 | 200 |
| 2026-10-26 | 100.00% | 1188 ms | 2 | 200 |
| 2026-10-25 | 100.00% | 1204 ms | 2 | 200 |
| 2026-10-24 | 100.00% | 1312 ms | 2 | 200 |
| 2026-10-23 | 100.00% | 2312 ms | 2 | 200 |
| 2026-10-22 | 100.00% | 1241 ms | 2 | 200 |
| 2026-10-21 | 100.00% | 1580 ms | 2 | 200 |
| 2026-10-20 | 100.00% | 1198 ms | 2 | 200 |
| 2026-10-19 | 100.00% | 1319 ms | 2 | 200 |
| 2026-10-18 | 100.00% | 1468 ms | 2 | 200 |
| 2026-10-17 | 100.00% | 1292 ms | 2 | 200 |
| 2026-10-16 | 100.00% | 1124 ms | 2 | 200 |
| 2026-10-15 | 100.00% | 2003 ms | 2 | 200 |
| 2026-10-14 | 100.00% | 1315 ms | 2 | 200 |
Data sources
awesome-ai-api public dataset (daily automated probing of /v1/models and host reachability)
We are not affiliated with api-featherless-ai and do not act as its agent, and we do not vouch for its service or the safety of your funds. Figures may lag or contain errors — if you spot one, please report it.
Similar services
api-gptgod-work
An overseas AI API relay and aggregation service. Probing its endpoint returned 322 models. It e…
Tokencloud.ai
Tokencloud.ai aggregates AI model APIs from outside mainland China. Top-ups can be paid with WeC…
ChatAnywhere (api.chatanywhere.tech)
A globally hosted relay that fronts a range of AI model APIs. It exposes a standard /v1/models e…
KKSJ API
A globally hosted relay that fronts a range of AI model APIs. The stack is built on new-api. It…
Nio API
A globally hosted relay that fronts a range of AI model APIs. Backend engine: new-api. It expose…
OneToken
OneToken aggregates AI model APIs from outside mainland China. Backend engine: new-api. It expos…