🪶 Featherless
Massive model catalog — 16,000+ models but very slow inference
Featherless
Avg Speed
9 tok/s
Models
16K+
Price
Scale ×3
Best For
Obscure Models
💰 Plan & Pricing
Scale ×3 Pricing — Very Slow
Scale ×3 pricing means costs multiply quickly. Very slow at 9 tok/s with queue times of 30-50s common. Best as last resort for models not available elsewhere.
Scale ×3 pricing means costs multiply quickly. Very slow at 9 tok/s with queue times of 30-50s common. Best as last resort for models not available elsewhere.
🔑 API Key
🌐 Endpoint
https://api.featherless.ai/v1/chat/completions
📦 Models (16K+ — Key Models)
| Model | Speed | Category | Notes |
|---|---|---|---|
| llama-4-maverick | ⚡ 10 tok/s | Chat | Llama 4 Maverick |
| deepseek-r1 | ⚡ 8 tok/s | Reasoning | DeepSeek R1 |
| qwen3-235b | ⚡ 9 tok/s | Chat/Coding | Qwen3 235B |
| deepseek-v3 | ⚡ 8 tok/s | Chat | DeepSeek V3 |
| llama-3.1-70b-instruct | ⚡ 10 tok/s | Chat | Llama 3.1 70B |
| llama-3.1-8b-instruct | ⚡ 12 tok/s | Chat | Llama 3.1 8B |
| mistral-7b-instruct | ⚡ 11 tok/s | Chat | Mistral 7B |
| qwen2.5-coder-32b-instruct | ⚡ 9 tok/s | Coding | Qwen Coder |
| various 16K+ models | ⚡ ~9 avg | All | Chat, Coding, Vision, Reasoning, Image Gen, Audio |
⚠️ Very slow (9 tok/s avg, 30-50s queue). Best as fallback for obscure models. Categories: Chat, Coding, Vision, Reasoning, Image Gen, Audio.
💻 cURL Example
curl -X POST https://api.featherless.ai/v1/chat/completions \
-H "Authorization: Bearer rc_96ff...c073b" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/llama-3-70b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'
🐍 Python Example
from openai import OpenAI
client = OpenAI(
api_key="rc_96ff...c073b",
base_url="https://api.featherless.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/llama-3-70b-instruct",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
⚠️ Pitfalls & Notes
Very Slow — 9 tok/s avg with 30-50 second queue times. Expect long waits before responses begin.
Scale ×3 Pricing — Costs multiply quickly. Scale ×3 pricing means you pay 3× the base model cost.
Largest Model Catalog — 16,000+ models is the largest catalog of any provider.
Fallback for Obscure Models — Useful as fallback for obscure/niche models not available elsewhere.
🏷️ Categories
Chat
Long-tail Models
Research