Skip to main content

OpenRouter

Aggregator

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

PricingDocsStatus
Visit openrouter.ai
Models323
Cheapest for
71 models
Serves
3 model types
Visits in September 202621.3M−3.4%Unique visitors 4.9M
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on OpenRouter

ModelInputOutputvs officialContext
GPT-4o (2024-11-20)$2.50/1MFrom$10/1M
from $8 at APIMart
±0%128K
GPT OSS 20BCheapest$0.018/1MFrom$0.09/1M—131K
GPT-3.5 Turbo 16k$3/1MFrom$4/1M
from $3.90 at APIYI
+3%16K
Mercury 2.5Cheapest$0.04/1MFrom$0.15/1M±0%260K
Qwen3.6 35B-A3B$0.10/1MFrom$0.95/1M-58%262K
Gemini 2.5 Flash$0.30/1MFrom$2.50/1M
from $2 at APIMart
±0%1.05M
Solar Pro 4$0.15/1MFrom$0.60/1M
from $0.127 at AI/ML API
+373%524K
Kimi K2.6$0.65/1MFrom$3.41/1M
from $2.40 at APIYI
-9%262K
Qwen3 Coder Flash$0.195/1MFrom$0.975/1M
from $0.544 at AIHubMix
-35%1M
MiMo-V2.5$0.119/1MFrom$0.238/1M
from $0.224 at CometAPI
+6%1.05M
Qwen3.8 Omni Flash$0.15/1MFrom$0.47/1M
from $0.38 at AIHubMix
+23%1M
Aion-2.0Cheapest$0.80/1MFrom$1.60/1M—131K
Mercury 3Cheapest$0.10/1MFrom$0.35/1M±0%1M
MiniMax M2.5$0.30/1MFrom$1.20/1M
from $0.95 at Venice AI
+26%205K
Llama 4 Maverick$0.188/1MFrom$0.652/1M
from $0.20 at AIHubMix
+226%524K
Qwen3-Coder-Next$0.12/1MFrom$0.80/1M
from $0.548 at AIHubMix
+46%262K
Llama 4 Scout 17B Instruct$0.10/1MFrom$0.30/1M
from $0.20 at AIHubMix
+50%1.31M
GLM-4.7-Flash$0.06/1MFrom$0.40/1M±0%200K
GLM-5.1$1.40/1MFrom$4.40/1M
from $1.44 at APIMart
±0%205K
Solar Mini 4Cheapest$0.05/1MFrom$0.20/1M—524K
Ling 3.0 Flash (free)Cheapest$0.021/1MFrom$0.063/1M±0%262K
GLM-4.7$0.54/1MFrom$1.98/1M
from $1.10 at AIHubMix
-10%205K
GLM-4.5$0.60/1MFrom$2.20/1M
from $1.16 at ZenMux
±0%131K
GLM-4.6$0.55/1MFrom$2.20/1M
from $1.10 at AIHubMix
±0%205K
Gemma 4$0.20/1MFrom$0.40/1M
from $0.30 at FastRouter
+33%262K
Qwen3-VL-8B-Instruct$0.25/1MFrom$0.75/1M
from $0.278 at SiliconFlow
+170%262K
Kimi K2.7 Code HighSpeed$0.671/1MFrom$3.35/1M
from $2.76 at Kenari
-11%262K
LFM2.5-24B-A2BCheapest$0.05/1MFrom$0.70/1M±0%128K
Hermes 3 405B InstructCheapest$1/1MFrom$1/1M—131K
MiMo-V2.5-ProCheapest$0.304/1MFrom$0.609/1M±0%1.05M
Qwen3 30B A3B$0.12/1MFrom$0.50/1M
from $0.29 at Helicone
+72%41K
GLM 5.3 Prime$2.80/1MFrom$8.80/1M
from $8.23 at AIHubMix
+7%1M
Nemotron 3.5 Lightning 30B A3B$0.07/1MFrom$0.20/1M
from $0.16 at Deep Infra
—262K
Llama-3.3-70B-Instruct$0.10/1MFrom$0.32/1M±0%131K
Qwen3.6 27BCheapest$0.25/1MFrom$2/1M-44%262K
Mistral Nemo$0.029/1MFrom$0.03/1M±0%131K
Gemma 3 4B ITCheapest$0.04/1MFrom$0.05/1M—131K
DeepSeek V4 Flash 0731Cheapest$0.044/1MFrom$0.133/1M—1.05M
LongCat-2.0$0.30/1MFrom$1.20/1M—1.05M
Grok 4.5$2/1MFrom$6/1M
from $3.20 at APIMart
±0%500K
Laguna S 2.1Cheapest$0.09/1MFrom$0.18/1M±0%1.05M
Mistral Medium 3.5$1.50/1MFrom$7.50/1M±0%262K
Qwen3 14B$0.12/1MFrom$0.24/1M
from $0.20 at Hugging Face
+20%41K
Qwen3.5 397B-A17B$0.50/1MFrom$3.60/1M
from $0.986 at AIHubMix
+249%262K
Qwen2.5-7B-Instruct$0.10/1MFrom$0.20/1M
from $0.05 at SiliconFlow
+300%33K
Mercury 2Cheapest$0.25/1MFrom$0.75/1M±0%128K
Qwen3 Coder 480B A35B Instruct$0.30/1MFrom$1/1M
from $0.95 at Helicone
+5%262K
Llama 3.1 8B Instruct$0.05/1MFrom$0.08/1M
from $0.05 at Helicone
+60%131K
Qwen3.7 Max$1.48/1MFrom$4.42/1M
from $3.75 at DevPass (LLM Gateway)
-11%1M
Qwen3-Coder 30B-A3B Instruct$0.07/1MFrom$0.28/1M
from $0.27 at DevPass (LLM Gateway)
+4%262K

OpenRouter at a glance

323 models in total: 312 text, 8 image, 3 moderation. The cheapest is Mistral Nemo at $0.03 /1M. Llama 4 Scout 17B Instruct has the largest context window, 1.31M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.

Cheapest

  1. Mistral Nemo$0.03/1M
  2. Gemma 3 4B IT$0.05/1M
  3. SLlama 3 8B Lunaris$0.05/1M
  4. Ling 3.0 Flash (free)$0.063/1M
  5. Llama 3.1 8B Instruct$0.08/1M

Largest context

  1. Llama 4 Scout 17B Instruct1.31M
  2. GPT-6 Astra1.05M
  3. GPT-6.1 Sol1.05M
  4. GPT-6 Sol1.05M
  5. GPT-6 Luna1.05M

Most searched

  1. Gemini 4 Argon2M
  2. Kimi K3658K
  3. GPT-6 Astra580K
  4. Muse Wonder569K
  5. Claude Opus 5.5405K

Newest

  1. Kimi K3.1 Pro HighspeedOct 23, 2026
  2. RFlint 40B FreeOct 21, 2026
  3. Mercury 3Oct 19, 2026
  4. DeepSeek V4 Flash Vision ExpOct 17, 2026
  5. MiniMax-M3.1-FlashOct 17, 2026