Compare Models

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

💬 Chat Models(1597 models)

ModelProviderInput/1MOutput/1MAvg CostContext
FreeBestFREEMistral AIFREEFREEFREE-
BAAI/bge-large-en-v1.5FREESiliconflowFREEFREEFREE-
BAAI/bge-large-zh-v1.5FREESiliconflowFREEFREEFREE-
Qwen/Qwen2-7B-InstructFREESiliconflowFREEFREEFREE-
THUDM/glm-4-9b-chatFREESiliconflowFREEFREEFREE-
internlm/internlm2_5-7b-chatFREESiliconflowFREEFREEFREE-
Qwen/Qwen1.5-7B-ChatFREESiliconflowFREEFREEFREE-
BAAI/bge-reranker-v2-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-reranker-base_v1FREESiliconflowFREEFREEFREE-
BAAI/bge-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-embedding-base_v1FREESiliconflowFREEFREEFREE-
01-ai/Yi-1.5-9B-Chat-16KFREESiliconflowFREEFREEFREE-
01-ai/Yi-1.5-6B-ChatFREESiliconflowFREEFREEFREE-
THUDM/GLM-4-9B-0414FREESiliconflowFREEFREEFREE-
Qwen/Qwen2.5-Coder-7B-InstructFREESiliconflowFREEFREEFREE-

+ 1582 more models with this capability

👁️ Vision Models(389 models)

ModelProviderInput/1MOutput/1MAvg CostContext
FreeBestFREEMistral AIFREEFREEFREE-
GLM-4.6V-FlashFREEZhipu AI (China)FREEFREEFREE32K
qwen3.7-plusFREEAlibaba Cloud (China)FREEFREEFREE-
Mistral Large 3 675B Instruct 2512FREEFireworks AIFREEFREEFREE-
Ministral 3 14B Instruct 2512FREEFireworks AIFREEFREEFREE-
Ministral 3 8B Instruct 2512FREEFireworks AIFREEFREEFREE-
Ministral 3 3B Instruct 2512FREEFireworks AIFREEFREEFREE-
NVIDIA Nemotron Nano 2 VLFREEFireworks AIFREEFREEFREE-
GLM-4.5VFREEFireworks AIFREEFREEFREE-
Rolm OCRFREEFireworks AIFREEFREEFREE-
InternVL3 78BFREEFireworks AIFREEFREEFREE-
InternVL3 38BFREEFireworks AIFREEFREEFREE-
InternVL3 8BFREEFireworks AIFREEFREEFREE-
Phi-3.5 Vision InstructFREEFireworks AIFREEFREEFREE-
Llama 3.2 90B Vision InstructFREEFireworks AIFREEFREEFREE-

+ 374 more models with this capability

💻 Code Models(51 models)

ModelProviderInput/1MOutput/1MAvg CostContext
PrismML Ternary Bonsai 27BBestFREETogether AIFREEFREEFREE-
Cohere: North Mini Code (free)FREEOpenRouterFREEFREEFREE256K
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-Air V2.5OpenRouter$0.150$0.600$0.375256K
Qwen: Qwen3 Coder NextOpenRouter$0.120$0.800$0.460262K
Qwen2.5-Coder-14B-InstructAlibaba Cloud (China)$0.274$0.822$0.548131K
qwen-coder-turboAlibaba Cloud (International)$0.287$0.861$0.574-
Qwen: Qwen3 Coder FlashOpenRouter$0.195$0.975$0.585128K
Mistral: Codestral 2508OpenRouter$0.300$0.900$0.600256K
Qwen: Qwen3 Coder 480B A35BOpenRouter$0.300$1.00$0.650262K
Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.300$1.00$0.650262K
Kwaipilot: KAT-Coder-Pro V2OpenRouter$0.300$1.20$0.750262K
qwen-coder-plusAlibaba Cloud (International)$0.502$1.00$0.753-
Qwen2.5 Coder 32B InstructOpenRouter$0.660$1.00$0.83033K

+ 36 more models with this capability

🧠 Reasoning Models(235 models)

ModelProviderInput/1MOutput/1MAvg CostContext
FreeBestFREEMistral AIFREEFREEFREE-
Macaron V1 TallFREENovita AIFREEFREEFREE262K
Qwen3.6-PlusFREENovita AIFREEFREEFREE1.0M
Nex-N2-ProFREENovita AIFREEFREEFREE262K
Qwen3.5-PlusFREENovita AIFREEFREEFREE1.0M
Macaron V1 VentiFREENovita AIFREEFREEFREE1.0M
Ling-3.0-flashFREENovita AIFREEFREEFREE262K
Sao10K: Llama 3 8B LunarisOpenRouter$0.040$0.050$0.0458K
gpt-oss-20bDeepInfra$0.030$0.140$0.085131K
gemini-1.5-flash-8bDeepInfra$0.037$0.150$0.0941.0M
gpt-oss-120bDeepInfra$0.037$0.170$0.104131K
Qwen VL OCRAlibaba Cloud (International)$0.070$0.160$0.1151.0M
Qwen Doc TurboAlibaba Cloud (International)$0.087$0.144$0.1151.0M
Qwen3.5-9BDeepInfra$0.100$0.150$0.125262K
GLM-4.1V-Thinking-FlashXZhipu AI (China)$0.274FREE$0.137-

+ 220 more models with this capability

📊 Embedding Models(29 models)

ModelProviderInput/1MOutput/1MAvg CostContext
FreeBestFREEMistral AIFREEFREEFREE-
text-embedding-v4FREEAlibaba Cloud (China)FREEFREEFREE-
Embedding-V1Baidu (China)$0.0001FREE$0.0000384
tao-8kBaidu (China)$0.0001FREE$0.0000-
Qwen3-Embedding-4BBaidu (China)$0.0001FREE$0.0000-
bge-large-zhBaidu (China)$0.0001FREE$0.0000-
Qwen3-Embedding-8BBaidu (China)$0.0001FREE$0.0000-
Qwen3-Embedding-0.6BBaidu (China)$0.0001FREE$0.0000-
bge-large-enBaidu (China)$0.0001FREE$0.0000-
Mistral EmbedMistral AI$0.010FREE$0.00508K
text-embedding-3-smallOpenAI$0.020FREE$0.0108K
Text-Embedding-V2Alibaba Cloud (China)$0.096FREE$0.0482K
Text-Embedding-V3Alibaba Cloud (China)$0.096FREE$0.0488K
Text Embedding Ada 002OpenAI$0.100FREE$0.050-
text-embedding-3-largeOpenAI$0.130FREE$0.0658K

+ 14 more models with this capability

📚 Long Context (100K+)(790 models)

ModelProviderInput/1MOutput/1MAvg CostContext
GLM-5.2BestFREEZhipu AI (China)FREEFREEFREE1.0M
NVIDIA: Nemotron 3 Super (free)FREEOpenRouterFREEFREEFREE262K
Google: Lyria 3 Clip PreviewFREEOpenRouterFREEFREEFREE1.0M
Google: Gemma 4 26B A4B (free)FREEOpenRouterFREEFREEFREE262K
NVIDIA: Nemotron 3 Nano Omni (free)FREEOpenRouterFREEFREEFREE256K
Free Models RouterFREEOpenRouterFREEFREEFREE200K
Google: Lyria 3 Pro PreviewFREEOpenRouterFREEFREEFREE1.0M
Google: Gemma 4 31B (free)FREEOpenRouterFREEFREEFREE262K
Poolside: Laguna M.1 (free)FREEOpenRouterFREEFREEFREE262K
NVIDIA: Nemotron 3 Ultra (free)FREEOpenRouterFREEFREEFREE1.0M
Poolside: Laguna XS 2.1 (free)FREEOpenRouterFREEFREEFREE262K
Poolside: Laguna S 2.1 (free)FREEOpenRouterFREEFREEFREE262K
NVIDIA: Nemotron 3.5 Content Safety (free)FREEOpenRouterFREEFREEFREE128K
Cohere: North Mini Code (free)FREEOpenRouterFREEFREEFREE256K
Ling-3.0-flash (free)FREEOpenRouterFREEFREEFREE262K

+ 775 more models with this capability

🆓 Free Models(391 models)

ModelProviderInput/1MOutput/1MAvg CostContext
FreeBestFREEMistral AIFREEFREEFREE-
Omni Moderation LatestFREEOpenAIFREEFREEFREE-
Music-2.6-freeFREEMiniMax (China)FREEFREEFREE-
Music-3.0-freeFREEMiniMax (China)FREEFREEFREE-
BAAI/bge-large-en-v1.5FREESiliconflowFREEFREEFREE-
BAAI/bge-large-zh-v1.5FREESiliconflowFREEFREEFREE-
Qwen/Qwen2-7B-InstructFREESiliconflowFREEFREEFREE-
THUDM/glm-4-9b-chatFREESiliconflowFREEFREEFREE-
internlm/internlm2_5-7b-chatFREESiliconflowFREEFREEFREE-
Qwen/Qwen1.5-7B-ChatFREESiliconflowFREEFREEFREE-
BAAI/bge-reranker-v2-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-reranker-base_v1FREESiliconflowFREEFREEFREE-
BAAI/bge-m3FREESiliconflowFREEFREEFREE-
netease-youdao/bce-embedding-base_v1FREESiliconflowFREEFREEFREE-
01-ai/Yi-1.5-9B-Chat-16KFREESiliconflowFREEFREEFREE-

+ 376 more models with this capability

Quick Links

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