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
OpenAI GPT-5.4$2.50/1MFrom$15/1M
from $12 at APIMart
±0%1.05M
OpenAI GPT-5.4 Mini$0.75/1M$4.50/1M
from $3.60 at APIMart
±0%400K
OpenAI GPT-5.4 Nano$0.20/1M$1.25/1M
from $1 at APIMart
±0%400K
OpenAI GPT-5.4 Pro$30/1MFrom$180/1M
from $144 at APIMart
±0%1.05M
OpenAI GPT-5.5$5/1MFrom$30/1M
from $24 at APIMart
±0%1.05M
OpenAI o1$15/1M$60/1M
from $48 at APIMart
±0%—
OpenAI o3$2/1M$8/1M
from $6.40 at APIMart
±0%200K
OpenAI o3 mini$1.10/1M$4.40/1M
from $3.52 at APIMart
±0%200K
Phi 4$0.12/1M$0.48/1M
from $0.14 at Deep Infra
+243%16K
Phi 4 Mini$0.12/1M$0.48/1M
from $0.30 at Azure
+60%128K
Phi 4 MultimodalOnly here$0.12/1M$0.48/1M—128K
Phi-3-medium-4k-instruct$1/1M$3/1M
from $0.68 at Azure
+341%—
Qianfan OcrOnly here$0.062/1M$0.248/1M—32K
Qianfan Ocr FastOnly here$0.664/1M$2.74/1M—32K
Qwen 2.5 VL 32B InstructOnly here$0.24/1M$0.24/1M——
Qwen Audio 3.0 TTS (Flash)Cheapest—$0.014/1K chars——
Qwen Audio 3.0 Tts PlusOnly here—$0.02/1K chars——
Qwen FlashCheapest$0.02/1MFrom$0.20/1M-7%—
Qwen Image—$0.036/img
from $0.02 at FastRouter
+80%—
Qwen Image MaxOnly here—$0.07/img——
Qwen Long$0.10/1M$0.40/1M
from $0.28 at APIYI
+43%—
Qwen Max$0.38/1M$1.52/1M
from $1.38 at Alibaba
+10%—
Qwen Max Longcontext$7/1M$21/1M
from $3.20 at LaoZhang API
+556%—
Qwen MT Plus$0.492/1M$1.48/1M
from $0.75 at Jiekou.AI
+90%16K
Qwen Plus$0.113/1MFrom$1.13/1M
from $0.23 at CrazyRouter
+292%—
Qwen Turbo$0.046/1M$0.092/1M
from $0.09 at Ofox
+2%—
Qwen-MT TurboOnly here$0.192/1M$0.535/1M—16K
Qwen2-72B-InstructOnly here$0.80/1M$0.80/1M——
Qwen2-VL-72B-InstructOnly here$2.18/1M$6.54/1M——
Qwen2-VL-7B-InstructOnly here$0.28/1M$0.70/1M——
Qwen2.5 Math 1.5b InstructOnly here$0.20/1M$0.20/1M——
Qwen2.5 Math 7B InstructOnly here$0.20/1M$0.40/1M——
Qwen2.5-32B-Instruct$0.60/1MFrom$0.60/1M
from $0.175 at SiliconFlow
+243%—
Qwen2.5-72B-Instruct$0.80/1MFrom$0.80/1M
from $0.40 at Deep Infra
+100%—
Qwen2.5-Coder-32B-InstructCheapest$0.16/1M$0.16/1M——
Qwen2.5-VL 72B InstructCheapest$0.50/1MFrom$0.50/1M——
Qwen2p5 14B$0.40/1M$1.20/1M
from $0.097 at SiliconFlow
+1134%—
Qwen2p5 Coder 1.5BOnly here$0.20/1M$0.40/1M——
Qwen2p5 Math 72B InstructOnly here$0.80/1M$2.40/1M——
Qwen3 235B A22B Instruct 2507$0.28/1MFrom$1.12/1M
from $0.10 at Requesty
+1020%262K
Qwen3 235B A22b Thinking 2507$0.28/1M$2.80/1M
from $2.30 at Hugging Face
+22%262K
Qwen3 30B A3B Thinking 2507Only here$0.12/1M$1.20/1M——
Qwen3 30B-A3B Instruct 2507$0.103/1M$0.411/1M
from $0.30 at Cortecs
+37%—
Qwen3 Embedding 8B$0.068/1MFree/1M-100%—
Qwen3 Max$0.451/1MFrom$1.80/1M
from $1.43 at Ofox
+26%262K
Qwen3 Max PreviewCheapest$0.846/1MFrom$3.38/1M——
Qwen3 Next 80B A3B Thinking$0.142/1M$1.42/1M
from $1.20 at OpenRouter
+18%256K
Qwen3 Reranker 8B$0.11/1M$0.11/1M
from $0.039 at SiliconFlow
+183%—
Qwen3 VL 235B A22B Instruct$0.274/1M$1.10/1M
from $0.88 at Deep Infra
+25%—
Qwen3-Coder-PlusCheapest$0.54/1MFrom$2.16/1M—1.05M

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