Skip to main content

AIHubMix

Aggregator

AIHubMix routes one API key to many upstream providers, so you can switch models without new accounts.

PricingDocsStatus
Visit aihubmix.com
Models495
Cheapest for
62 models
Serves
6 model types
Visits in September 2026284K+12.1%Unique visitors 113K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on AIHubMix

ModelInputOutputvs officialContext
Gemma 4$0.20/1M$0.40/1M
from $0.30 at FastRouter
+33%262K
Kimi K2.7 Code HighSpeed$0.95/1M$4/1M
from $2.76 at Kenari
+7%262K
Llama 3.1 405B (reasoning)Only here$4/1M$4/1M——
Qwen2.5-Coder-7B$0.20/1M$0.40/1M
from $0.03 at Hugging Face
+1233%—
Qwen3 30B A3B$1/1MFrom$1/1M
from $0.29 at Helicone
+245%—
GLM 5.3 PrimeCheapest$2.35/1M$8.23/1M——
Qwen 3 Embedding 4B$0.068/1M$0.068/1M
from $0.019 at SiliconFlow
+250%—
Seedream 5.0 Flash—$0.019/img
from $0.014 at APIMart
+3%—
Veo 3.1 Lite—$0.05/sec
from $0.03 at Vercel AI Gateway
+67%—
Llama-3.3-70B-Instruct$0.60/1MFrom$1.20/1M
from $0.32 at Deep Infra
+275%131K
kling 3.0 omni—$0.113/sec
from $0.067 at APIMart
+68%—
Qwen3.6 27B$0.422/1M$2.53/1M
from $2 at OpenRouter
-30%262K
Gemma 3 4B IT$0.20/1M$0.20/1M
from $0.05 at OpenRouter
+300%—
DeepSeek V4 Flash 0731$0.142/1MFrom$0.284/1M
from $0.133 at OpenRouter
+113%1M
Qwen2 57B A14B InstructOnly here$0.24/1M$0.24/1M——
Sora-2-Pro—$0.30/sec——
LongCat-2.0$0.775/1M$3.10/1M
from $1.20 at Atlas Cloud
+158%1M
Qwen3 0.6BOnly here$0.046/1M$0.46/1M——
Qwen Image 3.0 Pro—From$0.071/img
from $0.003 at Kie.ai
——
Grok 4.5$2/1MFrom$6/1M
from $3.20 at APIMart
±0%500K
Laguna S 2.1$0.10/1M$0.20/1M
from $0.18 at OpenRouter
+11%1.05M
Qwen3 14B$0.50/1MFrom$0.50/1M
from $0.20 at Hugging Face
+150%—
Qwen3.5 397B-A17BCheapest$0.164/1MFrom$0.986/1M-4%262K
Veo 3.1 Fast—$0.10/sec
from $0.08 at APIMart
+25%—
Qwen2.5-7B-Instruct$0.40/1MFrom$0.40/1M
from $0.05 at SiliconFlow
+700%—
Qwen3 Coder 480B A35B Instruct$0.82/1MFrom$3.28/1M
from $0.95 at Helicone
+245%262K
GPT Image 1$5/1M$40/1M
from $12.50 at Helicone
+220%—
Llama 3.1 8B Instruct$0.033/1MFrom$0.055/1M
from $0.05 at Helicone
+10%—
Qwen3.7 Max$1.69/1M$5.07/1M
from $3.75 at DevPass (LLM Gateway)
+2%1M
Qwen2.5 72B Instruct 128K$0.80/1M$0.80/1M
from $0.574 at SiliconFlow
+39%—
Qwen3-Coder 30B-A3B Instruct$0.20/1MFrom$0.80/1M
from $0.27 at DevPass (LLM Gateway)
+196%262K
Qwen3.5 35B-A3BCheapest$0.056/1MFrom$0.451/1M-77%262K
Gemma 3 27B$0.20/1MFrom$0.20/1M
from $0.16 at Deep Infra
+25%—
GLM-4.5-Air$0.14/1M$0.84/1M
from $0.291 at ZenMux
-24%131K
Seedance 2.0 Fast—$0.113/sec
from $0.024 at APIMart
+88%—
DeepSeek R1 Distill Qwen 7BCheapest$0.01/1M$0.01/1M——
Grok Code Fast 1$1/1MFrom$2/1M
from $1.43 at Jiekou.AI
+40%256K
Gemma 3 1B ItOnly here$0.20/1M$0.20/1M——
Gemma 4 26B A4B IT$0.14/1MFrom$0.40/1M
from $0.225 at OpenRouter
-33%262K
Qwen2.5 3B InstructOnly here$0.40/1M$0.80/1M——
Qwen3 32B$0.16/1MFrom$0.64/1M
from $0.25 at Hugging Face
+156%—
Qwen3.7 Plus$0.282/1MFrom$1.13/1M
from $0.30 at CrazyRouter
+2%1M
Qwen3.5 27BCheapest$0.085/1MFrom$0.677/1M-72%262K
GLM-Image—$0.015/img
from $0.01 at FastRouter
±0%—
Qwen3 Embedding 0.6B$0.068/1MFree/1M-100%—
FLUX 1.1 Pro—$0.04/img——
DeepSeek R1 Distill Qwen 32BOnly here$0.20/1M$0.20/1M——
DeepSeek Coder V2 InstructOnly here$0.16/1M$0.32/1M——
GLM 4 FlashOnly here$0.10/1M$0.10/1M——
Gemma 3 12B IT$0.20/1MFrom$0.20/1M
from $0.10 at Helicone
+100%—

AIHubMix at a glance

495 models in total: 389 text, 42 image, 30 video, 14 audio, 13 embedding, 7 reranking. The cheapest is Llama3 Groq 8B 8192 Tool Use Preview at $0.00019 /1M. Grok 4.1 Fast has the largest context window, 2M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed (Moonshot AI), released Oct 23, 2026.

Cheapest

  1. Llama3 Groq 8B 8192 Tool Use Preview$0.00019/1M
  2. Llama3 Groq 70B 8192 Tool Use Preview$0.00089/1M
  3. DeepSeek R1 Distill Qwen 7B$0.01/1M
  4. DeepSeek R1 Distill Llama 8B$0.01/1M
  5. DeepSeek R1 Distill Qwen 1.5B$0.01/1M

Largest context

  1. Grok 4.1 Fast2M
  2. Grok 4.1 Fast (Reasoning)2M
  3. Llama 4 Scout 17B Instruct1.31M
  4. GPT-6 Astra1.05M
  5. GPT-6.1 Sol1.05M

Most searched

  1. Gemini 4 Argon2M
  2. Seedance 2.0703K
  3. Kimi K3658K
  4. MiniMax H3582K
  5. GPT-6 Astra580K

Newest

  1. Kimi K3.1 Pro Highspeed (Moonshot AI)Oct 23, 2026
  2. Kimi K3.1 Pro HighspeedOct 23, 2026
  3. Cohere Rerank 5 FastOct 21, 2026
  4. Cohere Rerank 5 ProOct 21, 2026
  5. DeepSeek V4 Flash Vision ExpOct 17, 2026