Featherless Models — Pricing & Benchmarks

28 models available

Last refreshed 2026-11-10. Next refresh: weekly.

Featherless hosts 28 AI models in this catalog. The lowest listed input price is gpt-oss-20b at $0.04/1M input tokens. LLM Reference compares these models across all 130 providers.

ModelInput (per 1M)Output (per 1M)Context
gpt-oss-20b$0.04$0.15128K
Llama 3.1 8B Instruct$0.05$0.0832K
Phi-4 14B$0.07$0.1432K
Qwen3-32B$0.102$0.49332K
Qwen3-8B$0.117$0.45532K
Qwen3-14B$0.12$0.2432K
gpt-oss-120b$0.15$0.6128K
Qwen2.5-7B-Instruct$0.17$0.232K
Qwen3.5-9B$0.17$0.2532K
Mistral Small 3.1 24B Instruct$0.217$0.40332K
DeepSeek V3.2$0.264$0.41128K
DeepSeek V3.1$0.285$1.00128K
MiniMax M2.5$0.295$1.20200K
Qwen3.5-27B$0.3$2.4032K
Qwen3.6-27B$0.32$2.7032K
Qwen2.5-72B-Instruct$0.37$0.432K
DeepSeek V3 0324$0.385$1.63128K
Gemma 2 9B Instruct$0.431$1.1216K
GLM 4.7$0.55$2.20198K
Kimi K2 Instruct$0.6$2.5032K
Gemma 2 27B Instruct$0.65$0.6532K
Llama 3.3 70B Instruct$0.65$0.7532K
Qwen2.5-32B-Instruct$0.68$1.2032K
Llama 3.1 70B Instruct$0.72$0.7232K
Apertus 1.5 70B$0.875$2.0832K
GLM-5.3$1.40$4.40256K
DeepSeek V4 Pro$1.60$3.20256K
Kimi K3$3.00$15.00256K

Where else to run this

Pricing Overview

Cheapest$0.04/1M
Most expensive$3.00/1M

About Featherless

Featherless serves catalog models through https://api.featherless.ai/v1. The public models endpoint reports exact provider IDs (HF-style), model_class, context_length, gating, and effective pricing.input/output (USD per 1M tokens). Chat is flat-rate; Developer credits bill successful requests per token; Business is dedicated/contract.

Full provider profile →