Skip to content
LLM Pulse

Lab

llmgateway-providers

297 canonical models tracked · RSS feed for this lab

ModelBest in /MBest out /MContextProvidersReleased
DeepSeek V4 Flash (Alibaba Cloud)$0.2$0.41
DeepSeek V4 Pro (Alibaba Cloud)$2.40$4.801
GLM-5 (Alibaba Cloud)$0.573$2.581
GLM-5.2 (Alibaba Cloud)$1.40$4.401
Kimi K2.5 (Alibaba Cloud)$0.574$3.011
Qwen Coder Plus (Alibaba Cloud)$0.502$11
Qwen Plus Latest (Alibaba Cloud)$0.4$1.201
Qwen3 VL Flash (Alibaba Cloud)$0.05$0.41
Qwen3.5 397B A17B (Alibaba Cloud)$0.6$3.601
Claude Fable 5 (AWS Bedrock)$10$501
Claude Haiku 4.5 (AWS Bedrock)$1$51
Claude Haiku 4.5 (2025-10-01) (AWS Bedrock)$1$51
Claude Opus 4.1 (AWS Bedrock)$15$751
Claude Opus 4.5 (AWS Bedrock)$5$251
Claude Opus 4.6 (AWS Bedrock)$5$251
Claude Opus 4.7 (AWS Bedrock)$5$251
Claude Opus 4.8 (AWS Bedrock)$5$251
Claude Opus 5 (AWS Bedrock)$5$251
Claude Sonnet 4.5 (AWS Bedrock)$3$151
Claude Sonnet 4.5 (2025-09-29) (AWS Bedrock)$3$151
Claude Sonnet 4.6 (AWS Bedrock)$3$151
Claude Sonnet 5 (AWS Bedrock)$2$101
Grok 4.3 (AWS Bedrock)$1.25$2.501
Grok 4.6 (AWS Bedrock)$2$61
Llama 3.1 70B Instruct (AWS Bedrock)$0.72$0.721
Llama 4 Maverick 17B Instruct (AWS Bedrock)$0.24$0.971
Llama 4 Scout 17B Instruct (AWS Bedrock)$0.17$0.661
GPT-5.6 Luna (AWS Mantle)$0.22$1.321
GPT-5.6 Sol (AWS Mantle)$5.50$331
GPT-5.6 Terra (AWS Mantle)$2.20$13.201
Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)$0.2$0.51
Grok 4.1 Fast Reasoning (Azure AI Foundry)$0.2$0.51
Grok 4.3 (Azure AI Foundry)$1.25$2.501
GPT-3.5 Turbo (Azure)$0.5$1.501
GPT-4 (Azure)$30$601
GPT-4 Turbo (Azure)$10$301
GPT-4.1 (Azure)$2$81
GPT-4.1 Mini (Azure)$0.4$1.601
GPT-4.1 Nano (Azure)$0.1$0.41
GPT-4o (Azure)$2.50$101
GPT-5 (Azure)$1.25$101
GPT-5 Mini (Azure)$0.25$21
GPT-5 Nano (Azure)$0.05$0.41
GPT-5.1 (Azure)$1.25$101
GPT-5.1 Codex (Azure)$1.25$101
GPT-5.1 Codex mini (Azure)$0.25$21
GPT-5.2 (Azure)$1.75$141
GPT-5.2 Codex (Azure)$1.75$141
GPT-5.2 Pro (Azure)$21$1681
GPT-5.3 Codex (Azure)$1.75$141
GPT-5.4 (Azure)$2.50$151
GPT-5.4 Mini (Azure)$0.75$4.501
GPT-5.4 Nano (Azure)$0.2$1.251
GPT-5.4 Pro (Azure)$30$1801
GPT-5.5 (Azure)$5$301
GPT-5.6 Luna (Azure)$0.2$1.201
GPT-5.6 Sol (Azure)$5$301
GPT-5.6 Terra (Azure)$2$121
GPT OSS 120B (Azure)$0.15$0.61
o1 (Azure)$15$601
o3 (Azure)$2$81
o3 Mini (Azure)$1.10$4.401
o4 Mini (Azure)$1.10$4.401
DeepSeek V4 Flash (Baidu)$0.14$0.281
DeepSeek V4 Pro (Baidu)$1.69$3.381
GLM-5 (Baidu)$1$3.201
GLM-5.1 (Baidu)$1.40$4.401
GLM-5.2 (Baidu)$1.40$4.401
Kimi K2.6 (Baidu)$0.95$41
DeepSeek V3.2 (ByteDance)$0.28$0.421
DeepSeek V4 Flash (ByteDance)$0.44$1.321
DeepSeek V4 Pro (ByteDance)$1.32$3.961
GLM-4.7 (ByteDance)$0.6$2.201
GLM-5.2 (ByteDance)$1.40$4.401
GPT OSS 120B (ByteDance)$0.1$0.51
Seed 1.6 (250615) (ByteDance)$0.25$21
Seed 1.6 (250915) (ByteDance)$0.25$21
Seed 1.6 Flash (250715) (ByteDance)$0.07$0.31
Seed 1.8 (251228) (ByteDance)$0.25$21
DeepSeek V4 Flash (CanopyWave)$0.14$0.281
DeepSeek V4 Pro (CanopyWave)$1.74$3.481
GLM-5.2 (CanopyWave)$1.40$4.401
Kimi K2.6 (CanopyWave)$0.95$41
Kimi K3 (CanopyWave)$3$151
Gemma 4 31B IT (Cerebras)$0.99$1.491
GLM-4.7 (Cerebras)$2.25$2.751
GPT OSS 120B (Cerebras)$0.35$0.751
Llama 3.3 70B Instruct (Cerebras)$0.85$1.201
Qwen3 235B A22B Instruct 2507 (Cerebras)$0.6$1.201
DeepSeek V3.2 (DeepInfra)$0.26$0.381
DeepSeek V4 Flash (DeepInfra)$0.08$0.181
DeepSeek V4 Pro (DeepInfra)$1.30$2.601
Gemma 4 26B A4B IT (DeepInfra)$0.07$0.341
Gemma 4 31B IT (DeepInfra)$0.13$0.381
GLM-5.1 (DeepInfra)$1.05$3.501
Hy3 (DeepInfra)$0.14$0.581
Kimi K2.5 (DeepInfra)$0.45$2.251
InclusionAI Ling 3.0 Flash (DeepInfra)$0.06$0.181
Nemotron 3 Ultra 550B (DeepInfra)$0.5$2.201
Qwen3 VL 235B A22B Instruct (DeepInfra)$0.2$0.881
Qwen3 VL 30B A3B Instruct (DeepInfra)$0.15$0.61
Qwen3.5 9B (DeepInfra)$0.1$0.151
GLM-4.5 (EmberCloud)$0.6$2.201
GLM-4.5 Air (EmberCloud)$0.13$0.851
GLM-4.7 (EmberCloud)$0.38$1.981
GLM-4.7 Flash (EmberCloud)$0.06$0.41
GLM-5 (EmberCloud)$0.72$2.301
GLM-5.1 (EmberCloud)$0.931$2.931
GLM-5.2 (EmberCloud)$1.26$3.961
Kimi K2.5 (EmberCloud)$0.405$1.981
Qwen3 Coder Next (EmberCloud)$0.108$0.6751
DeepSeek V4 Flash (Fireworks AI)$0.14$0.281
DeepSeek V4 Pro (Fireworks AI)$1.32$3.961
Kimi K3 (Fireworks AI)$3$151
Kimi K3 Fast (Fireworks AI)$4.50$22.501
DeepSeek V4 Flash (Gonka24)$0.075$0.1751
Kimi K2.6 (Gonka24)$0.22$1.141
MiniMax M2.7 (Gonka24)$0.08$0.321
Gemini 2.5 Flash (Google AI Studio)$0.3$2.501
Gemini 2.5 Flash Lite (Google AI Studio)$0.1$0.41
Gemini 2.5 Pro (Google AI Studio)$1.25$101
Gemini 3 Flash (Preview) (Google AI Studio)$0.5$31
Gemini 3.1 Flash Lite (Google AI Studio)$0.25$1.501
Gemini 3.1 Pro (Preview) (Google AI Studio)$2$121
Gemini 3.5 Flash (Google AI Studio)$1.50$91
Gemini 3.5 Flash Lite (Google AI Studio)$0.3$2.501
Gemini 3.6 Flash (Google AI Studio)$0.75$3.751
Gemini 3.7 Flash (Google AI Studio)$0.75$3.751
Gemini Pro Latest (Google AI Studio)$2$121
Gemini 2.5 Flash (Google Vertex AI)$0.3$2.501
Gemini 2.5 Flash Lite (Google Vertex AI)$0.1$0.41
Gemini 2.5 Pro (Google Vertex AI)$1.25$101
Gemini 3 Flash (Preview) (Google Vertex AI)$0.5$31
Gemini 3.1 Flash Lite (Google Vertex AI)$0.25$1.501
Gemini 3.1 Pro (Preview) (Google Vertex AI)$2$121
Gemini 3.5 Flash (Google Vertex AI)$1.50$91
Gemini 3.5 Flash Lite (Google Vertex AI)$0.3$2.501
Gemini 3.6 Flash (Google Vertex AI)$0.75$3.751
Gemini 3.7 Flash (Google Vertex AI)$0.75$3.751
GPT OSS 120B (Groq)$0.15$0.751
GPT OSS 20B (Groq)$0.1$0.51
Gemini 3 Flash (Preview) (Iceberg)$0.5$31
Gemini 3.1 Pro (Preview) (Iceberg)$2$121
Gemini 3.6 Flash (Iceberg)$0.75$3.751
Llama 3.2 11B Instruct (Inference.net)$0.07$0.331
MiniMax M2 (MiniMax)$0.2$11
MiniMax M2.1 (MiniMax)$0.27$1.101
MiniMax M2.1 Lightning (MiniMax)$0.12$0.481
MiniMax M2.5 (MiniMax)$0.3$1.201
MiniMax M2.5 Highspeed (MiniMax)$0.6$2.401
MiniMax M2.7 (MiniMax)$0.3$1.201
MiniMax M2.7 Highspeed (MiniMax)$0.6$2.401
MiniMax M3 (MiniMax)$0.6$2.401
MiniMax Text 01 (MiniMax)$0.2$1.101
Codestral (Mistral AI)$0.3$0.91
Ministral 14B (Mistral AI)$0.2$0.21
Ministral 3B (Mistral AI)$0.1$0.11
Ministral 8B (Mistral AI)$0.15$0.151
Kimi K2.5 (Moonshot AI)$0.6$31
Kimi K2.6 (Moonshot AI)$0.95$41
Kimi K2.7 Code (Moonshot AI)$0.95$41
Kimi K2.7 Code Highspeed (Moonshot AI)$1.90$81
Kimi K3 (Moonshot AI)$3$151
Cosmos 3 Super Reasoner (Nebius AI)$0.1$0.31
DeepSeek V4 Pro (Nebius AI)$1.75$3.501
Gemma 3 27B (Nebius AI)$0.1$0.31
GLM-5.1 (Nebius AI)$1.40$4.401
GLM-5.2 (Nebius AI)$1.40$4.401
GPT OSS 120B (Nebius AI)$0.15$0.61
Hermes 4 405B (Nebius AI)$1$31
Hermes 4 70B (Nebius AI)$0.13$0.41
Kimi K2.6 (Nebius AI)$0.95$41
Kimi K2.7 Code (Nebius AI)$0.95$41
Kimi K3 (Nebius AI)$3$151
Llama 3.1 Nemotron Ultra 253B (Nebius AI)$0.6$1.801
Llama 3.3 70B Instruct (Nebius AI)$0.13$0.41
MiniCPM-V 4.5 (Nebius AI)$0.658$1.111
MiniMax M2.5 (Nebius AI)$0.3$1.201
MiniMax M3 (Nebius AI)$0.3$1.201
Nemotron 3 Nano 30B (Nebius AI)$0.06$0.241
Nemotron 3 Nano Omni (Nebius AI)$0.06$0.241
Nemotron 3 Super 120B (Nebius AI)$0.3$0.91
Nemotron 3 Ultra 550B (Nebius AI)$1$31
Qwen2.5 VL 72B Instruct (Nebius AI)$0.25$0.751
Qwen3 235B A22B Instruct 2507 (Nebius AI)$0.2$0.61
Qwen3 30B A3B Instruct 2507 (Nebius AI)$0.1$0.31
Qwen3 32B (Nebius AI)$0.1$0.31
Qwen3 Next 80B A3B Thinking (Nebius AI)$0.15$1.201
DeepSeek V3.2 (NovitaAI)$0.269$0.41
DeepSeek V4 Flash (NovitaAI)$0.14$0.281
ERNIE 4.5 VL 424B A47B (NovitaAI)$0.42$1.251
Gemma 4 26B A4B IT (NovitaAI)$0.13$0.41
Gemma 4 31B IT (NovitaAI)$0.14$0.41
GLM-4.5V (NovitaAI)$0.6$1.801
GLM-4.6 (NovitaAI)$0.55$2.201
GLM-4.6V (NovitaAI)$0.3$0.91
GLM-4.7 (NovitaAI)$0.6$2.201
GLM-5 (NovitaAI)$1$3.201
GLM-5.1 (NovitaAI)$1.38$4.401
GLM-5.2 (NovitaAI)$1.40$4.401
Hy3 (NovitaAI)$0.14$0.581
Kimi K2 (NovitaAI)$0.57$2.301
Kimi K2.6 (NovitaAI)$0.8$3.401
Kimi K2.7 Code (NovitaAI)$0.95$41
Kimi K3 (NovitaAI)$3$151
InclusionAI Ling 3.0 Flash (NovitaAI)$0.06$0.181
Llama 3 70B Instruct (NovitaAI)$0.51$0.741
Llama 3.2 3B Instruct (NovitaAI)$0.03$0.051
Llama 3.3 70B Instruct (NovitaAI)$0.135$0.41
Llama 4 Maverick 17B Instruct (NovitaAI)$0.27$0.851
Llama 4 Scout 17B Instruct (NovitaAI)$0.18$0.591
MiniMax M2.1 (NovitaAI)$0.3$1.201
MiniMax M2.5 (NovitaAI)$0.3$1.201
MiniMax M2.7 (NovitaAI)$0.3$1.201
Qwen3 235B A22B FP8 (NovitaAI)$0.2$0.81
Qwen3 235B A22B Instruct 2507 (NovitaAI)$0.09$0.581
Qwen3 235B A22B Thinking 2507 (NovitaAI)$0.3$31
Qwen3 Coder 30B A3B Instruct (NovitaAI)$0.07$0.271
Qwen3 Coder 480B A35B Instruct (NovitaAI)$0.38$1.551
Qwen3 Max (NovitaAI)$0.845$3.381
Qwen3 Next 80B A3B Instruct (NovitaAI)$0.15$1.501
Qwen3 VL 235B A22B Instruct (NovitaAI)$0.3$1.501
Qwen3 VL 235B A22B Thinking (NovitaAI)$0.98$3.951
Qwen3 VL 30B A3B Instruct (NovitaAI)$0.2$0.71
Qwen3.6 35B A3B (NovitaAI)$0.248$1.491
Qwen3.7 Max (NovitaAI)$1.25$3.751
Qwen3.8 Max (NovitaAI)$2$61
Qwen3.5 397B A17B (NovitaAI)$0.6$3.601
GPT-4o Mini Search Preview (OpenAI)$0.15$0.61
GPT-4o Mini Transcribe (OpenAI)$1.25$51
GPT-4o Search Preview (OpenAI)$2.50$101
GPT-4o Transcribe (OpenAI)$2.50$101
Kimi K3 (Permafrost)$3$151
Gemini 3.1 Pro (Preview) (Quartz)$2$121
DeepSeek V4 Flash (RanoAI)$0.14$0.281
DeepSeek V4 Flash (Runware)$0.076$0.1531
DeepSeek V4 Pro (Runware)$0.961$1.921
Gemma 4 31B IT (Runware)$0.102$0.2971
GLM-5.2 (Runware)$0.8$2.551
GPT OSS 120B (Runware)$0.032$0.141
Kimi K2.6 (Runware)$0.6$3.051
GLM-5.2 (SCX.ai)$0.55$1.781
GLM-5.2 Turbo (SCX.ai)$1.99$6.161
Qwen3.8 Max (SCX.ai)$1.81$5.451
Gemma 4 31B IT (SCX.ai (Turbo))$0.3$0.911
GPT OSS 120B (SCX.ai (Turbo))$0.17$0.551
Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))$0.53$1.621
MiniMax M2.7 (SCX.ai (Turbo))$0.48$1.791
Qwen3 32B (SCX.ai (Turbo))$0.36$0.871
DeepSeek V4 Flash (Together AI)$0.14$0.281
DeepSeek V4 Pro (Together AI)$1.32$3.961
Gemma 4 31B IT (Together AI)$0.39$0.971
GLM-4.7 (Together AI)$0.45$21
GPT OSS 120B (Together AI)$0.15$0.61
GPT OSS 20B (Together AI)$0.05$0.21
Kimi K3 (Together AI)$3$151
MiniMax M3 (Together AI)$0.3$1.201
Kimi K2.6 (Tundra)$0.4$2.201
Claude Haiku 4.5 (Vertex AI (Anthropic))$1$51
Claude Opus 4.5 (Vertex AI (Anthropic))$5$251
Claude Opus 4.6 (Vertex AI (Anthropic))$5$251
Claude Opus 4.7 (Vertex AI (Anthropic))$5$251
Claude Sonnet 4.5 (Vertex AI (Anthropic))$3$151
Claude Sonnet 4.6 (Vertex AI (Anthropic))$3$151
Claude Sonnet 5 (Vertex AI (Anthropic))$2$101
DeepSeek V3.2 (Vertex AI (OpenAI-compatible))$0.56$1.681
GLM-4.7 (Vertex AI (OpenAI-compatible))$0.6$2.201
GLM-5 (Vertex AI (OpenAI-compatible))$1$3.201
Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))$1.25$2.501
Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))$1.25$2.501
Kimi K2 Thinking (Vertex AI (OpenAI-compatible))$0.6$2.501
Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))$0.22$0.881
Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))$0.22$1.801
Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))$0.15$1.201
Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))$0.15$1.201
Grok 4 (xAI)$3$151
Grok 4.20 Beta Non-Reasoning (0309) (xAI)$2$61
Grok 4.20 Beta Reasoning (0309) (xAI)$2$61
Grok 4.3 (xAI)$1.25$2.501
Grok 4.5 (xAI)$2$61
Grok 4.6 (xAI)$2$61
Grok Build 0.1 (xAI)$1$21
GLM-4 32B (0414-128k) (Z AI)$0.1$0.11
GLM-4.5 (Z AI)$0.6$2.201
GLM-4.5 Air (Z AI)$0.2$1.101
GLM-4.5 AirX (Z AI)$1.10$4.501
GLM-4.5 X (Z AI)$2.20$8.901
GLM-4.5V (Z AI)$0.6$1.801
GLM-4.6 (Z AI)$0.6$2.201
GLM-4.6V (Z AI)$0.3$0.91
GLM-4.6V FlashX (Z AI)$0.04$0.41
GLM-4.7 (Z AI)$0.6$2.201
GLM-4.7 FlashX (Z AI)$0.07$0.41
GLM-5 (Z AI)$1$3.201
GLM-5.1 (Z AI)$1.40$4.401
GLM-5.2 (Z AI)$1.40$4.401
GLM-5.3 (Z AI)$1.40$4.401