Featherless Models — Pricing & Benchmarks
27 models available
Last refreshed 2026-09-24. Next refresh: weekly.
Featherless hosts 27 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 96 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| gpt-oss-20b | $0.04 | $0.15 | 131k | |
| Llama 3.1 8B Instruct | $0.05 | $0.08 | 128k | |
| Phi-4 14B | $0.07 | $0.14 | 16k | |
| Qwen3-32B | $0.102 | $0.493 | 40k | |
| Qwen3-8B | $0.117 | $0.455 | 128k | |
| Qwen3-14B | $0.12 | $0.24 | 40k | |
| gpt-oss-120b | $0.15 | $0.6 | 131k | |
| Qwen2.5-7B-Instruct | $0.17 | $0.2 | 128k | |
| Qwen3.5-9B | $0.17 | $0.25 | 262k | |
| Mistral Small 3.1 24B Instruct | $0.217 | $0.403 | 128k | |
| DeepSeek V3.2 | $0.264 | $0.41 | 160k | |
| DeepSeek V3.1 | $0.285 | $1.00 | 64k | |
| MiniMax M2.5 | $0.295 | $1.20 | 197k | |
| Qwen3.5-27B | $0.3 | $2.40 | 262k | |
| Qwen3.6-27B | $0.32 | $2.70 | 262k | |
| Qwen2.5-72B-Instruct | $0.37 | $0.4 | 128k | |
| DeepSeek V3 0324 | $0.385 | $1.63 | 160k | |
| Gemma 2 9B Instruct | $0.431 | $1.12 | 8k | |
| GLM 4.7 | $0.55 | $2.20 | 200k | |
| Kimi K2 Instruct | $0.6 | $2.50 | 131k | |
| Gemma 2 27B Instruct | $0.65 | $0.65 | 8k | |
| Llama 3.3 70B Instruct (free) | $0.65 | $0.75 | 66k | |
| Qwen2.5-32B-Instruct | $0.68 | $1.20 | 128k | |
| Llama 3.1 70B Instruct | $0.72 | $0.72 | 128k | |
| GLM-5.3 | $1.40 | $4.40 | 1m | |
| DeepSeek V4 Pro | $1.60 | $3.20 | 1m | |
| Kimi K3 | $3.00 | $15.00 | 1.05m |
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 →