LLM ReferenceLLM Reference
OpenRouter

OpenRouter Models — Pricing & Benchmarks

222 models available · OpenRouter, Inc.

OpenRouter hosts 222 AI models in this catalog. The lowest listed input price is CoBuddy at Free, with 8 free-tier models. LLM Reference lets you compare these models across all 63 providers without switching tabs.

ModelInput (per 1M)Output (per 1M)Context
CoBuddyFreeFree131K
Laguna M.1FreeFree131K
Laguna XS.2FreeFree131K
Ling-2.6-1TFreeFree262K
Lyria 3 ClipFreeFree—
Lyria 3 ProFreeFree—
Nemotron 3 Nano OmniFreeFree262K
Tencent Hy3 PreviewFreeFree262K
Llama 3.1 8B Instruct$0.02$0.05128K
Mistral NeMo (2407)$0.02$0.03128K
Llama 3.2 1B Instruct$0.027$0.2128K
gpt-oss-20b$0.03$0.14131K
LFM2-24B-A2B$0.03$0.1232K
Llama 3 8B Instruct$0.03$0.048K
Nova Micro$0.035$0.14128K
gpt-oss-120b$0.039$0.18131K
Gemma 3$0.04$0.08—
Gemma 3 12B (free)$0.04$0.1333K
Gemma 3 4B IT$0.04$0.08—
Nemotron-Nano-9B-v2$0.04$0.16—
Qwen2.5-7B-Instruct$0.04$0.1128K
Trinity Mini$0.045$0.15128K
GPT-5 Nano$0.05$0.4400K
Granite 4.1 8B$0.05$0.1131K
Qwen3-8B$0.05$0.4128K
Llama 3.2 3B Instruct$0.051$0.34128K
Gemma 3n 4B (free)$0.06$0.128K
Gemma 4 26B A4B IT$0.06$0.33256k
GLM-4.7 Flash$0.06$0.4198K
MythoMax L2 13B$0.06$0.06—
Nova Lite$0.06$0.24300K
Qwen3-14B$0.06$0.2440K
Phi-4 14B$0.065$0.14—
Qwen3.5-Flash$0.07$0.261M
Gemini 2.0 Flash Lite$0.075$0.31M
GPT OSS Safeguard 20B$0.075$0.3131K
Ring-2.6-1T$0.075$0.625262K
Gemma 3 27B (free)$0.08$0.16131K
Ling-2.6-Flash$0.08$0.24262K
Llama 4 Scout 17B-16E Instruct$0.08$0.3328K
Qwen3-30B-A3B$0.08$0.28—
Qwen3-32B$0.08$0.2440K
Nemotron 3 Super-120B-A12B$0.09$0.451M
Qwen3-Next-80B-A3B$0.0975$0.78—
Gemini 2.0 Flash$0.1$0.42M
Gemini 2.5 Flash Lite$0.1$0.41M
Gemini 2.5 Flash Lite Preview 09-2025$0.1$0.41M
GLM-4 32B$0.1$0.1—
GPT-4.1 Nano$0.1$0.41M
Llama 3.3 70B Instruct (free)$0.1$0.3266K
Qwen3.5-9B$0.1$0.15262K
Reka Edge$0.1$0.164K
Seed 2.0 Mini$0.1$0.4262K
Step 3.5 Flash$0.1$0.3256K
Mistral 7B Instruct v0.1$0.11$0.198K
Qwen3-Coder-Next$0.12$0.8256K
Gemma 4 31B IT$0.13$0.38256k
GLM-4.5-Air$0.13$0.85128K
Qwen3-VL-30B-A3B$0.13$1.56—
Qwen-VL-Plus$0.1365$0.409532K
DeepSeek V4 Flash$0.14$0.281M
Hermes 2 Pro Llama 3 8B$0.14$0.14—
Command R$0.15$0.6128K
GPT-4o Mini (07-18)$0.15$0.6128K
GPT-4o-mini$0.15$0.6128K
GPT-4o-mini Search Preview$0.15$0.6128K
Llama 4 Maverick 17B Instruct FP8$0.15$0.61M
MiniMax M2.5$0.15$1.15197K
Mistral Small 4$0.15$0.6256K
Perceptron Mk1$0.15$1.5033K
Qwen3.6-35B-A3B$0.15$1262K
Trinity-Large-Preview$0.15$0.45128K
Qwen3.5-35B-A3B$0.1625$1.3262K
Llama Guard 4 12B$0.18$0.18164K
Qwen3.5-27B$0.195$1.56262K
GPT-5.4 Nano$0.2$1.25400K
Grok 4.1 Fast$0.2$0.51M
Grok Code Fast 1$0.2$1.5262K
Nemotron-Nano-12B-v2-VL$0.2$0.6—
DeepSeek V3.1 Terminus$0.21$0.79164K
Trinity-Large-Thinking$0.22$0.85256K
Llama 3.2 11B Vision Instruct$0.245$0.245128K
Claude 3 Haiku$0.25$1.25200K
Gemini 3.1 Flash Lite Preview$0.25$1.51M
Gemini 3.1 Flash-Lite$0.25$1.501M
GPT-5 Mini$0.25$2400K
Mercury 2$0.25$0.75131K
Qwen3.6-Flash$0.25$1.51M
Seed 2.0 Lite$0.25$2262K
DeepSeek V3$0.252$0.37864k
DeepSeek V3.2$0.252$0.378160K
MiniMax M2$0.255$1197K
Qwen3-VL-235B-A22B$0.26$2.6—
Qwen3.5-122B-A10B$0.26$2.08262K
DeepSeek V3.2 Exp$0.27$0.41164K
DeepSeek R1 Distill Qwen-32B$0.29$0.29128K
MiniMax M2.1$0.29$0.95200k
Gemini 2.5 Flash$0.3$2.51M
Grok 3 Mini$0.3$0.5131k
KAT Coder Pro V2$0.3$1.2256K
MiniMax M2.7$0.3$1.2205K
Nano Banana (Gemini 2.5 Flash Image)$0.3$2.533K
Qwen3.6-27B$0.32$3.2262K
Qwen3.6-Plus$0.33$1.951M
Mistral Small 3.1 24B Instruct$0.35$0.56128K
Qwen2.5-72B-Instruct$0.36$0.4128K
GLM-4.7$0.38$1.74—
GLM-4.6$0.39$1.9198K
Qwen3.5-397B-A17B$0.39$2.34262K
DeepSeek V3.2 Speciale$0.4$1.2164K
GPT-4.1 Mini$0.4$1.61M
Llama 3.1 70B Instruct$0.4$0.4128K
MiMo-V2-Omni$0.4$2262K
Mistral Medium$0.4$232K
Qwen3.5-Plus$0.4$2.41M
Xiaomi MiMo-V2.5$0.4$21M
DeepSeek V4 Pro$0.44$0.871M
Kimi K2.5$0.44$2256K
ReMM SLERP L2 13B$0.45$0.65—
Qwen3-235B-A22B$0.455$1.82128K
Llama Guard 3 8B$0.48$0.038K
DeepSeek R1 0528$0.5$2.15160K
Gemini 3 Flash Preview$0.5$31M
GPT-3.5 Turbo$0.5$1.516K
Mistral Large 2$0.5$1.5128K
Nano Banana 2 (Gemini 3.1 Flash Image Preview)$0.5$366K
Llama 3 70B Instruct$0.51$0.748K
Qwen-VL-Max$0.52$2.08—
Kimi K2$0.57$2.3262K
GLM-4.5$0.6$2.2128K
GLM-5$0.6$2.08200k
GPT Audio Mini$0.6$2.4128K
Kimi K2 Thinking$0.6$2.5256K
WizardLM-2 8x22B$0.62$0.62—
Gemma 2 27B Instruct$0.65$0.658K
Qwen2.5-Coder-32B-Instruct$0.66$1—
Qianfan-OCR-Fast$0.68$2.8166K
DeepSeek R1$0.7$2.5128K
DeepSeek R1 Distill Llama 70B$0.7$0.8128K
GPT-5.4 Mini$0.75$4.5400K
Kimi K2.6$0.75$3.50262K
Qwen3-Max$0.78$3.9128K
Aion 2.0$0.8$1.6128K
Claude 3.5 Haiku$0.8$4200k
Nova Pro$0.8$3.2300K
Claude Haiku 4.5$1$5200k
MiMo-V2-Pro$1$31M
Sonar$1$1127K
Xiaomi MiMo-V2.5-Pro$1$31M
Qwen-Max$1.04$4.16128K
Qwen3.6 Max Preview$1.04$6.24256K
GLM-5.1$1.05$3.5200k
o3 Mini$1.1$4.4200K
o4-mini$1.1$4.4—
GLM-5 Turbo$1.2$4200k
GLM-5V-Turbo$1.2$4200k
Gemini 2.5 Pro$1.25$101M
Gemini 2.5 Pro Preview 05-06$1.25$101M
Gemini 2.5 Pro Preview 06-05$1.25$101M
GPT-5$1.25$10400K
GPT-5.1$1.25$10262K
GPT-5.1 Codex Max$1.25$10—
Grok 4.20$1.25$2.52M
Grok 4.3$1.25$2.51M
GPT-3.5 Turbo (Instruct)$1.5$24K
Mistral Medium 3.5$1.50$7.50256K
GPT-5.2$1.75$14400K
GPT-5.3-Codex$1.75$14400K
Gemini 3.1 Pro Preview$2$121M
Gemini 3.1 Pro Preview Custom Tools$2$121M
GPT-4.1$2$81M
Grok 4.20 Multi-Agent$2$62M
Mistral Large$2$632k
Mixtral 8x22B Instruct v0.1$2$664K
Nano Banana Pro (Gemini 3 Pro Image Preview)$2$1266K
o3$2$8200K
o4 Mini Deep Research$2$8200K
Pixtral Large$2$6128K
Sonar Deep Research$2$8128K
Sonar Reasoning Pro$2$8128K
Command$2.5$104K
Command R+$2.5$10128K
GPT Audio$2.5$10128K
GPT-4o$2.5$10128K
GPT-4o (08-06)$2.5$10128K
GPT-4o (2024-11-20)$2.5$10128K
GPT-4o Audio$2.5$10128K
GPT-4o Search Preview$2.5$10128K
GPT-5.4$2.5$151.1M
Nova Premier (upcoming)$2.5$12.5—
Claude 3.7 Sonnet$3$15200K
Claude Sonnet 4$3$151M
Claude Sonnet 4.5$3$15200K
Claude Sonnet 4.6$3$151M
GPT-3.5 Turbo 16k$3$416K
Grok 4$3$15256k
Grok-3$3$151M
Sonar Pro$3$15200K
Sonar Pro Search$3$15200K
Claude Opus 4.5$5$25200K
Claude Opus 4.6$5.00$25.001M
Claude Opus 4.7$5$251M
GPT-4o (05-13)$5$15128K
GPT-5.5$5$301.1M
GPT-5.4 Image 2$8$15256K
GPT-4 Turbo$10$30128K
GPT-4 Turbo (older v1106)$10$30128K
GPT-4 Turbo Preview$10$30128K
Claude 4 Opus$15$75200k
Claude Opus 4.1$15$75200k
OLMo 1B$15$60—
o3-pro$20$80—
Claude Opus 4.6$30$1501M
Claude Opus 4.7$30.00$150.001M
GPT-4$30$608K
GPT-5.4 Pro$30$1801.1M
GPT-5.5 Pro$30$1801.1M
o1-pro$150$600200K
Claude 3.5 Sonnet——200K
Gemma 2 9B Instruct——8K
Qwen2.5-Coder-7B-Instruct———
QwQ 32B——128K

Pricing Overview

Cheapest$0.02/1M
Most expensive$150.00/1M
8 free tier models

About OpenRouter

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

Full provider profile →

Links

Dashboard Documentation Pricing