🔌 API Provider Hub
Complete reference for 13 LLM API providers — tested and benchmarked May 2026
🔌 13 Providers
📦 700+ Models
✅ 14 Working Providers
🕐 Tested May 2026
⚡ Speed:
💰 Price:
Groq
FREE · Unlimited
⚡ 212 tok/s
📦 16 models
🏆 Fastest
⭐ llama-4-maverick
⭐ gemma-3-27b
⭐ deepseek-r1-distill-70b
StepFun
$9/mo Step Plan
⚡ 93 tok/s
📦 6 models
⭐ step-2-16k
⭐ step-1.5v-7b
⭐ step-1-flash
OpenCode
$10/mo flat
⚡ 52 tok/s
📦 15 models
💰 Best Value
⭐ claude-sonnet-4
⭐ gpt-4.1
⭐ deepseek-r1
Ollama Cloud
Unlimited
⚡ 51 tok/s
📦 39 models
🔬 Exclusive
⭐ llama-4-behemoth
⭐ qwen3-235b
⭐ deepseek-r1-0528
Venice
Uncensored
⚡ 48 tok/s
📦 75 models
🔓 No Filters
⭐ deepseek-r1
⭐ qwen3-235b
⭐ llama-4-maverick
OpenRouter
33 free + paid
⚡ 46 tok/s
📦 356 models
🏆 Largest
⭐ claude-sonnet-4
⭐ gpt-4.1
⭐ deepseek-r1-0528
ZenMux
700 req/day free
⚡ 37 tok/s
📦 127 models
💎 Gemini
⭐ gemma-3-27b
⭐ llama-4-maverick
⭐ deepseek-r1
Chutes
$20/mo PRO
⚡ 28 tok/s
📦 35 models
🔒 TEE Privacy
⭐ deepseek-r1
⭐ qwen3-30b-a3b
⭐ llama-4-scout
ORBIT
2B tokens/mo free
⚡ 25 tok/s
📦 18 models
⚡ Free
⭐ claude-sonnet-4
⭐ claude-haiku-4
⭐ gpt-4o-mini
BytePlus ModelArk
$9/mo ArkCode Pro
⚡ 84 tok/s max
📦 9 verified
💻 Coding Champ
⭐ dola-seed-2.0-lite
⭐ deepseek-r1-0528
⭐ doubao-1.5-pro
Infermatic
$20/mo flat
⚡ 38 tok/s
📦 19 models
🎵 TTS
⭐ qwen3-235b
⭐ deepseek-r1
⭐ llama-4-maverick
ArliAI
From $10/mo
🐢 16 tok/s
📦 54 models
🔓 Derestricted
⭐ deepseek-r1-0528
⭐ qwen3-235b
⭐ llama-4-maverick
Featherless
Scale ×3
🐢 9 tok/s
📦 16K+ models
🌐 Largest
⭐ llama-4-maverick
⭐ deepseek-r1
⭐ qwen3-235b
⚡ Speed Comparison
212
Groq
93
StepFun
84★
BytePlus
52
OpenCode
51
Ollama
48
Venice
46
ORouter
37
ZenMux
38
Infermatic
28
Chutes
25
ORBIT
16
ArliAI
9
Featherless
tok/s avg · ★ BytePlus max = 84 for dola-seed-2.0-lite
🔍 Model Search
Search across all 700+ models from every provider. Find the right model by name, category, or use case.