Featherless

Researched 7d agoInference PlatformTier 3

Featherless

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useapi

Featherless offers 28 tracked models (28 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 28 tracked models; last verified 2026-11-10.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

28

Models available through this provider

Priced output routes

28

Models with output token pricing tracked

Cheapest output

$0.080

Llama 3.1 8B Instruct on this route

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-08-14

95d since newest release

Freshness

2026-11-10

Researched 7d ago

fresh

Information

TypeInference Platform
TierTier 3
Models28
CompanyFeatherless

Featherless is a serverless inference provider for a large catalog of third-party open text-generation models (40,000+). Its OpenAI-compatible API exposes public model discovery, chat/completions, subscription and prepaid-credit plans, and per-token request billing by model class.

Where this host wins

  • Coding: 14 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 24 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 13 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 25 tracked models with context-token or InfiniteBench-class signal.

Getting started

Verify: quotas and regions in the linked vendor documentation.

Platform Overview

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.

Available Models(28)

View all →

All models available as Serverless

ModelInput (per 1M)Output (per 1M)
GLM-5.3$1.4$4.4
Apertus 1.5 70B$0.875$2.075
Kimi K3$3$15
Qwen3.6-27B$0.32$2.7
DeepSeek V4 Pro$1.6$3.2
Qwen3.5-9B$0.17$0.25
GLM 4.7$0.55$2.2
Qwen3.5-27B$0.3$2.4
Mistral Small 3.1 24B Instruct$0.21675$0.4025
DeepSeek V3.2$0.264$0.41
View full catalog →

Where else to run this