Compare Models

Find the best model for your use case. Models sorted by average cost (input + output).

💬 Chat Models(1179 models)

ModelProviderInput/1MOutput/1MAvg CostContext
Input tokens (7)BestFREEPerplexityFREEFREEFREE-
Input tokens (8)FREEPerplexityFREEFREEFREE-
ERNIE SpeedFREEBaidu (China)FREEFREEFREE8K
ERNIE TinyFREEBaidu (China)FREEFREEFREE8K
ERNIE Speed 128KFREEBaidu (China)FREEFREEFREE128K
GLM-4V-FlashFREEZhipu AI (China)FREEFREEFREE2K
ERNIE LiteFREEBaidu (China)FREEFREEFREE8K
THUDM/glm-4-9b-chatFREESiliconflowFREEFREEFREE-
internlm/internlm2_5-7b-chatFREESiliconflowFREEFREEFREE-
BAAI/bge-large-en-v1.5FREESiliconflowFREEFREEFREE-
Qwen/Qwen1.5-7B-ChatFREESiliconflowFREEFREEFREE-
BAAI/bge-large-zh-v1.5FREESiliconflowFREEFREEFREE-
BAAI/bge-reranker-v2-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-reranker-base_v1FREESiliconflowFREEFREEFREE-
Qwen/Qwen2-7B-InstructFREESiliconflowFREEFREEFREE-

+ 1164 more models with this capability

👁️ Vision Models(230 models)

ModelProviderInput/1MOutput/1MAvg CostContext
GLM-4V-FlashBestFREEZhipu AI (China)FREEFREEFREE2K
Llama 4 Maverick Instruct (Basic)FREEFireworks AIFREEFREEFREE-
InternVL3 8BFREEFireworks AIFREEFREEFREE-
InternVL3 38BFREEFireworks AIFREEFREEFREE-
InternVL3 78BFREEFireworks AIFREEFREEFREE-
Rolm OCRFREEFireworks AIFREEFREEFREE-
GLM-4.5VFREEFireworks AIFREEFREEFREE-
NVIDIA Nemotron Nano 2 VLFREEFireworks AIFREEFREEFREE-
Ministral 3 3B Instruct 2512FREEFireworks AIFREEFREEFREE-
Ministral 3 8B Instruct 2512FREEFireworks AIFREEFREEFREE-
Ministral 3 14B Instruct 2512FREEFireworks AIFREEFREEFREE-
Mistral Large 3 675B Instruct 2512FREEFireworks AIFREEFREEFREE-
Qwen3-VL-8B-InstructFREEFireworks AIFREEFREEFREE-
Devstral Small 2 24B Instruct 2512FREEFireworks AIFREEFREEFREE-
Qwen3 Omni 30B A3B InstructFREEFireworks AIFREEFREEFREE-

+ 215 more models with this capability

💻 Code Models(26 models)

ModelProviderInput/1MOutput/1MAvg CostContext
Qwen: Qwen3 Coder 480B A35B (free)BestFREEOpenRouterFREEFREEFREE262K
CodeGeeX-4Zhipu AI (China)$0.014$0.014$0.014128K
Qwen: Qwen2.5 Coder 7B InstructOpenRouter$0.030$0.090$0.06033K
Qwen2.5 Coder 32B InstructOpenRouter$0.030$0.110$0.07033K
Qwen: Qwen3 Coder 30B A3B InstructOpenRouter$0.070$0.270$0.170160K
Qwen2.5-Coder-7B-InstructAlibaba Cloud (China)$0.137$0.411$0.274131K
Kwaipilot: KAT-Coder-Pro V1OpenRouter$0.207$0.828$0.517256K
Qwen2.5-Coder-14B-InstructAlibaba Cloud (China)$0.274$0.822$0.548131K
Qwen: Qwen3 Coder 480B A35BOpenRouter$0.220$0.950$0.585262K
Mistral: Codestral 2508OpenRouter$0.300$0.900$0.600256K
Inception: Mercury CoderOpenRouter$0.250$1.00$0.625128K
Arcee AI: Coder LargeOpenRouter$0.500$0.800$0.65033K
Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.280$1.20$0.740262K
xAI: Grok Code Fast 1OpenRouter$0.200$1.50$0.850256K
Qwen: Qwen3 Coder FlashOpenRouter$0.300$1.50$0.900128K

+ 11 more models with this capability

🧠 Reasoning Models(104 models)

ModelProviderInput/1MOutput/1MAvg CostContext
Qwen3 Omni 30B A3B ThinkingBestFREENovita AIFREEFREEFREE66K
TNG: DeepSeek R1T2 Chimera (free)FREEOpenRouterFREEFREEFREE164K
DeepSeek: R1 0528 (free)FREEOpenRouterFREEFREEFREE164K
TNG: R1T Chimera (free)FREEOpenRouterFREEFREEFREE164K
TNG: DeepSeek R1T Chimera (free)FREEOpenRouterFREEFREEFREE164K
Sao10K: Llama 3 8B LunarisOpenRouter$0.040$0.050$0.0458K
DeepSeek: R1 Distill Llama 70BOpenRouter$0.030$0.110$0.070131K
gpt-oss-20bDeepInfra$0.030$0.140$0.085131K
gemini-1.5-flash-8bDeepInfra$0.037$0.150$0.0941.0M
gpt-oss-120bDeepInfra$0.039$0.190$0.115131K
Qwen3-14BDeepInfra$0.080$0.240$0.16041K
Qwen3-32BDeepInfra$0.080$0.280$0.18041K
Qwen3-30B-A3BDeepInfra$0.080$0.290$0.18541K
gemini-1.5-flashDeepInfra$0.075$0.300$0.1881.0M
Reasoning tokens (73997)Perplexity$0.222$0.222$0.222-

+ 89 more models with this capability

📊 Embedding Models(15 models)

ModelProviderInput/1MOutput/1MAvg CostContext
Mistral EmbedBestMistral AI$0.010FREE$0.00508K
text-embedding-3-smallOpenAI$0.020FREE$0.0108K
text-embedding-3-smallAzure OpenAI$0.020FREE$0.0108K
Embedding-V1Baidu (China)$0.027FREE$0.014384
Embedding-2Zhipu AI (China)$0.069FREE$0.034-
Embedding-3Zhipu AI (China)$0.069FREE$0.034-
MiniMax Embo-01MiniMax (China)$0.069FREE$0.034-
Text-Embedding-V3Alibaba Cloud (China)$0.096FREE$0.0488K
Text-Embedding-V2Alibaba Cloud (China)$0.096FREE$0.0482K
Embed v3 EnglishCohere$0.100FREE$0.050512
Embed v3 MultilingualCohere$0.100FREE$0.050512
Embed 4Cohere$0.120FREE$0.060512
text-embedding-3-largeAzure OpenAI$0.130FREE$0.0658K
text-embedding-3-largeOpenAI$0.130FREE$0.0658K
text-embedding-004Google$0.150FREE$0.0752K

📚 Long Context (100K+)(483 models)

ModelProviderInput/1MOutput/1MAvg CostContext
ERNIE Speed 128KBestFREEBaidu (China)FREEFREEFREE128K
Mistral: Mistral Small 3.1 24B (free)FREEOpenRouterFREEFREEFREE128K
Meta: Llama 3.2 3B Instruct (free)FREEOpenRouterFREEFREEFREE131K
Meta: Llama 3.1 405B Instruct (free)FREEOpenRouterFREEFREEFREE131K
Nous: Hermes 3 405B Instruct (free)FREEOpenRouterFREEFREEFREE131K
StepFun: Step 3.5 Flash (free)FREEOpenRouterFREEFREEFREE256K
Arcee AI: Trinity Large Preview (free)FREEOpenRouterFREEFREEFREE131K
Upstage: Solar Pro 3 (free)FREEOpenRouterFREEFREEFREE128K
NVIDIA: Nemotron 3 Nano 30B A3B (free)FREEOpenRouterFREEFREEFREE256K
Arcee AI: Trinity Mini (free)FREEOpenRouterFREEFREEFREE131K
NVIDIA: Nemotron Nano 12B 2 VL (free)FREEOpenRouterFREEFREEFREE128K
NVIDIA: Nemotron Nano 9B V2 (free)FREEOpenRouterFREEFREEFREE128K
TNG: DeepSeek R1T2 Chimera (free)FREEOpenRouterFREEFREEFREE164K
DeepSeek: R1 0528 (free)FREEOpenRouterFREEFREEFREE164K
TNG: R1T Chimera (free)FREEOpenRouterFREEFREEFREE164K

+ 468 more models with this capability

🆓 Free Models(303 models)

ModelProviderInput/1MOutput/1MAvg CostContext
Input tokens (7)BestFREEPerplexityFREEFREEFREE-
Input tokens (8)FREEPerplexityFREEFREEFREE-
ERNIE SpeedFREEBaidu (China)FREEFREEFREE8K
ERNIE TinyFREEBaidu (China)FREEFREEFREE8K
ERNIE Speed 128KFREEBaidu (China)FREEFREEFREE128K
GLM-4V-FlashFREEZhipu AI (China)FREEFREEFREE2K
ERNIE LiteFREEBaidu (China)FREEFREEFREE8K
THUDM/glm-4-9b-chatFREESiliconflowFREEFREEFREE-
internlm/internlm2_5-7b-chatFREESiliconflowFREEFREEFREE-
BAAI/bge-large-en-v1.5FREESiliconflowFREEFREEFREE-
Qwen/Qwen1.5-7B-ChatFREESiliconflowFREEFREEFREE-
BAAI/bge-large-zh-v1.5FREESiliconflowFREEFREEFREE-
BAAI/bge-reranker-v2-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-reranker-base_v1FREESiliconflowFREEFREEFREE-
Qwen/Qwen2-7B-InstructFREESiliconflowFREEFREEFREE-

+ 288 more models with this capability

Quick Links

🆓 Free Models💬 Chat Models👁️ Vision Models💻 Code Models🧠 Reasoning Models📊 Embedding Models📚 Long Context (100K+)