Find a model

Browse the full catalog →
OpenAI compatible API · Attested · Public status

Compare AI models

Compare context, provider routes, pricing, privacy posture, and measured performance across the TrustedRouter model catalog.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Measured speed

Find the fastest routes.

Compare provider TTFT, throughput, and uptime from routed probes.

Open leaderboard → Open weights

Compare open models.

Browse DeepSeek, GLM, Gemma, Kimi, MiniMax, Qwen, and other open routes.

Browse models → Privacy

Require ZDR or confidential routes.

Separate gateway attestation from each downstream provider's privacy posture.

Review privacy →

Current comparison, preserved evidence.

Comparison pages use the current catalog and live route measurements. Monthly reports preserve the historical evidence after prices and provider performance change.

Monthly reportsRun your own eval
Model comparisons

Pick two models. Compare the routes that actually serve them.

Every comparison uses the current TrustedRouter catalog, prices, provider posture, and measured route data.

Comparison First model Routes Second model Routes
Qwen: Qwen3.5-9B vs Z.ai: GLM 4.6 qwen/qwen3.5-9b 8 z-ai/glm-4.6 7
Qwen: Qwen3.5-9B vs Z.ai: GLM 4.7 Flash qwen/qwen3.5-9b 8 z-ai/glm-4.7-flash 4
Qwen: Qwen3 14B vs Qwen: Qwen3.5-9B qwen/qwen3-14b 5 qwen/qwen3.5-9b 8
OpenAI: GPT-5.6 Luna vs Qwen: Qwen3.5-9B openai/gpt-5.6-luna 4 qwen/qwen3.5-9b 8
OpenAI: GPT-5.6 Sol vs Qwen: Qwen3.5-9B openai/gpt-5.6-sol 5 qwen/qwen3.5-9b 8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.5-9B deepseek/deepseek-v4-pro-0423 3 qwen/qwen3.5-9b 8
Google: Gemini 2.5 Pro vs Qwen: Qwen3.5-9B google/gemini-2.5-pro 4 qwen/qwen3.5-9b 8
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.5-9B google/gemini-3.1-pro-preview 5 qwen/qwen3.5-9b 8
Google: Gemini 3.8 Flash vs Qwen: Qwen3.5-9B google/gemini-3.8-flash 5 qwen/qwen3.5-9b 8
NVIDIA: Nemotron 3.5 Lightning vs Qwen: Qwen3.5-9B nvidia/nemotron-3.5-lightning 5 qwen/qwen3.5-9b 8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.5-9B nvidia/nemotron-3.5-lightning-30b-a3b 4 qwen/qwen3.5-9b 8
Qwen: Qwen3.5-9B vs Qwen: Qwen3.8-Flash-Next qwen/qwen3.5-9b 8 qwen/qwen3.8-flash-next 3
Qwen: Qwen3.5-9B vs Z.ai: GLM 5V Turbo qwen/qwen3.5-9b 8 z-ai/glm-5v-turbo 5
MiniMax: MiniMax M2.7 vs Qwen: Qwen3.5-9B minimax/minimax-m2.7 5 qwen/qwen3.5-9b 8
DeepSeek: R1 0528 vs Qwen: Qwen3.5-9B deepseek/deepseek-r1-0528 6 qwen/qwen3.5-9b 8
deepseek-ai/DeepSeek-V3.1 vs Qwen: Qwen3.5-9B deepseek/deepseek-v3.1 4 qwen/qwen3.5-9b 8
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.5-9B meta-llama/llama-3.1-8b-instruct 4 qwen/qwen3.5-9b 8
Llama 4 Scout Instruct vs Qwen: Qwen3.5-9B meta-llama/llama-4-scout-17b-16e-instruct 5 qwen/qwen3.5-9b 8
Meta: Llama 4 Maverick vs Qwen: Qwen3.5-9B meta-llama/llama-4-maverick 5 qwen/qwen3.5-9b 8
google/gemma-4-12B-it vs Qwen: Qwen3.5-9B google/gemma-4-12b-it 4 qwen/qwen3.5-9b 8
Qwen3 Embedding 8B vs Qwen: Qwen3.5-9B qwen/qwen3-embedding-8b 4 qwen/qwen3.5-9b 8
OpenAI: GPT-5.5 vs Qwen: Qwen3.5-9B openai/gpt-5.5 4 qwen/qwen3.5-9b 8
OpenAI: GPT-5.6 Terra vs Qwen: Qwen3.5-9B openai/gpt-5.6-terra 4 qwen/qwen3.5-9b 8
OpenAI: GPT-6 Astra vs Qwen: Qwen3.5-9B openai/gpt-6-astra 4 qwen/qwen3.5-9b 8
OpenAI: GPT-6 Luna vs Qwen: Qwen3.5-9B openai/gpt-6-luna 4 qwen/qwen3.5-9b 8
MiniMax: MiniMax M2.5 vs Z.ai: GLM 4.7 minimax/minimax-m2.5 8 z-ai/glm-4.7 8
Google: Gemma 3 12B vs Z.ai: GLM 4.7 google/gemma-3-12b-it 7 z-ai/glm-4.7 8
Xiaomi: MiMo-V2.6-Pro vs Z.ai: GLM 4.7 xiaomi/mimo-v2.6-pro 8 z-ai/glm-4.7 8
Google: Gemini 2.5 Flash vs Z.ai: GLM 4.7 google/gemini-2.5-flash 6 z-ai/glm-4.7 8
Google: Gemini 3.1 Flash Lite vs Z.ai: GLM 4.7 google/gemini-3.1-flash-lite 6 z-ai/glm-4.7 8
NVIDIA: Nemotron 3.5 Super VL vs Z.ai: GLM 4.7 nvidia/nemotron-3.5-super-vl 7 z-ai/glm-4.7 8
Qwen3.7 Max vs Z.ai: GLM 4.7 qwen/qwen3.7-max 7 z-ai/glm-4.7 8
Qwen3.8 Max vs Z.ai: GLM 4.7 qwen/qwen3.8-max 8 z-ai/glm-4.7 8
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 4.7 xiaomi/mimo-v2.5 5 z-ai/glm-4.7 8
Qwen/Qwen3-235B-A22B-Instruct-2507 vs Z.ai: GLM 4.7 qwen/qwen3-235b-a22b-instruct-2507 7 z-ai/glm-4.7 8
Qwen: Qwen3 Next 80B A3B Instruct vs Z.ai: GLM 4.7 qwen/qwen3-next-80b-a3b-instruct 7 z-ai/glm-4.7 8
Tencent: Hy3 vs Z.ai: GLM 4.7 tencent/hy3 8 z-ai/glm-4.7 8
Z.ai: GLM 4.6 vs Z.ai: GLM 4.7 z-ai/glm-4.6 7 z-ai/glm-4.7 8
Z.ai: GLM 4.7 vs Z.ai: GLM 4.7 Flash z-ai/glm-4.7 8 z-ai/glm-4.7-flash 4
Qwen: Qwen3 14B vs Z.ai: GLM 4.7 qwen/qwen3-14b 5 z-ai/glm-4.7 8
OpenAI: GPT-5.6 Luna vs Z.ai: GLM 4.7 openai/gpt-5.6-luna 4 z-ai/glm-4.7 8
OpenAI: GPT-5.6 Sol vs Z.ai: GLM 4.7 openai/gpt-5.6-sol 5 z-ai/glm-4.7 8
DeepSeek V4 Pro 0423 vs Z.ai: GLM 4.7 deepseek/deepseek-v4-pro-0423 3 z-ai/glm-4.7 8
Google: Gemini 2.5 Pro vs Z.ai: GLM 4.7 google/gemini-2.5-pro 4 z-ai/glm-4.7 8
Google: Gemini 3.1 Pro Preview vs Z.ai: GLM 4.7 google/gemini-3.1-pro-preview 5 z-ai/glm-4.7 8
Google: Gemini 3.8 Flash vs Z.ai: GLM 4.7 google/gemini-3.8-flash 5 z-ai/glm-4.7 8
NVIDIA: Nemotron 3.5 Lightning vs Z.ai: GLM 4.7 nvidia/nemotron-3.5-lightning 5 z-ai/glm-4.7 8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Z.ai: GLM 4.7 nvidia/nemotron-3.5-lightning-30b-a3b 4 z-ai/glm-4.7 8
Qwen: Qwen3.8-Flash-Next vs Z.ai: GLM 4.7 qwen/qwen3.8-flash-next 3 z-ai/glm-4.7 8
Z.ai: GLM 4.7 vs Z.ai: GLM 5V Turbo z-ai/glm-4.7 8 z-ai/glm-5v-turbo 5
MiniMax: MiniMax M2.7 vs Z.ai: GLM 4.7 minimax/minimax-m2.7 5 z-ai/glm-4.7 8
DeepSeek: R1 0528 vs Z.ai: GLM 4.7 deepseek/deepseek-r1-0528 6 z-ai/glm-4.7 8
deepseek-ai/DeepSeek-V3.1 vs Z.ai: GLM 4.7 deepseek/deepseek-v3.1 4 z-ai/glm-4.7 8
Meta: Llama 3.1 8B Instruct vs Z.ai: GLM 4.7 meta-llama/llama-3.1-8b-instruct 4 z-ai/glm-4.7 8
Llama 4 Scout Instruct vs Z.ai: GLM 4.7 meta-llama/llama-4-scout-17b-16e-instruct 5 z-ai/glm-4.7 8
Meta: Llama 4 Maverick vs Z.ai: GLM 4.7 meta-llama/llama-4-maverick 5 z-ai/glm-4.7 8
google/gemma-4-12B-it vs Z.ai: GLM 4.7 google/gemma-4-12b-it 4 z-ai/glm-4.7 8
Qwen3 Embedding 8B vs Z.ai: GLM 4.7 qwen/qwen3-embedding-8b 4 z-ai/glm-4.7 8
OpenAI: GPT-5.5 vs Z.ai: GLM 4.7 openai/gpt-5.5 4 z-ai/glm-4.7 8
OpenAI: GPT-5.6 Terra vs Z.ai: GLM 4.7 openai/gpt-5.6-terra 4 z-ai/glm-4.7 8
OpenAI: GPT-6 Astra vs Z.ai: GLM 4.7 openai/gpt-6-astra 4 z-ai/glm-4.7 8
OpenAI: GPT-6 Luna vs Z.ai: GLM 4.7 openai/gpt-6-luna 4 z-ai/glm-4.7 8
Google: Gemma 3 12B vs MiniMax: MiniMax M2.5 google/gemma-3-12b-it 7 minimax/minimax-m2.5 8
MiniMax: MiniMax M2.5 vs Xiaomi: MiMo-V2.6-Pro minimax/minimax-m2.5 8 xiaomi/mimo-v2.6-pro 8
Google: Gemini 2.5 Flash vs MiniMax: MiniMax M2.5 google/gemini-2.5-flash 6 minimax/minimax-m2.5 8
Google: Gemini 3.1 Flash Lite vs MiniMax: MiniMax M2.5 google/gemini-3.1-flash-lite 6 minimax/minimax-m2.5 8
MiniMax: MiniMax M2.5 vs NVIDIA: Nemotron 3.5 Super VL minimax/minimax-m2.5 8 nvidia/nemotron-3.5-super-vl 7
MiniMax: MiniMax M2.5 vs Qwen3.7 Max minimax/minimax-m2.5 8 qwen/qwen3.7-max 7
MiniMax: MiniMax M2.5 vs Qwen3.8 Max minimax/minimax-m2.5 8 qwen/qwen3.8-max 8
MiniMax: MiniMax M2.5 vs Xiaomi: MiMo-V2.5 minimax/minimax-m2.5 8 xiaomi/mimo-v2.5 5
MiniMax: MiniMax M2.5 vs Qwen/Qwen3-235B-A22B-Instruct-2507 minimax/minimax-m2.5 8 qwen/qwen3-235b-a22b-instruct-2507 7
MiniMax: MiniMax M2.5 vs Qwen: Qwen3 Next 80B A3B Instruct minimax/minimax-m2.5 8 qwen/qwen3-next-80b-a3b-instruct 7
MiniMax: MiniMax M2.5 vs Tencent: Hy3 minimax/minimax-m2.5 8 tencent/hy3 8
MiniMax: MiniMax M2.5 vs Z.ai: GLM 4.6 minimax/minimax-m2.5 8 z-ai/glm-4.6 7
MiniMax: MiniMax M2.5 vs Z.ai: GLM 4.7 Flash minimax/minimax-m2.5 8 z-ai/glm-4.7-flash 4
MiniMax: MiniMax M2.5 vs Qwen: Qwen3 14B minimax/minimax-m2.5 8 qwen/qwen3-14b 5
MiniMax: MiniMax M2.5 vs OpenAI: GPT-5.6 Luna minimax/minimax-m2.5 8 openai/gpt-5.6-luna 4
MiniMax: MiniMax M2.5 vs OpenAI: GPT-5.6 Sol minimax/minimax-m2.5 8 openai/gpt-5.6-sol 5
DeepSeek V4 Pro 0423 vs MiniMax: MiniMax M2.5 deepseek/deepseek-v4-pro-0423 3 minimax/minimax-m2.5 8
Google: Gemini 2.5 Pro vs MiniMax: MiniMax M2.5 google/gemini-2.5-pro 4 minimax/minimax-m2.5 8
Google: Gemini 3.1 Pro Preview vs MiniMax: MiniMax M2.5 google/gemini-3.1-pro-preview 5 minimax/minimax-m2.5 8
Google: Gemini 3.8 Flash vs MiniMax: MiniMax M2.5 google/gemini-3.8-flash 5 minimax/minimax-m2.5 8
MiniMax: MiniMax M2.5 vs NVIDIA: Nemotron 3.5 Lightning minimax/minimax-m2.5 8 nvidia/nemotron-3.5-lightning 5
MiniMax: MiniMax M2.5 vs nvidia/Nemotron-3.5-Lightning-30B-A3B minimax/minimax-m2.5 8 nvidia/nemotron-3.5-lightning-30b-a3b 4
MiniMax: MiniMax M2.5 vs Qwen: Qwen3.8-Flash-Next minimax/minimax-m2.5 8 qwen/qwen3.8-flash-next 3
MiniMax: MiniMax M2.5 vs Z.ai: GLM 5V Turbo minimax/minimax-m2.5 8 z-ai/glm-5v-turbo 5
MiniMax: MiniMax M2.5 vs MiniMax: MiniMax M2.7 minimax/minimax-m2.5 8 minimax/minimax-m2.7 5
DeepSeek: R1 0528 vs MiniMax: MiniMax M2.5 deepseek/deepseek-r1-0528 6 minimax/minimax-m2.5 8
deepseek-ai/DeepSeek-V3.1 vs MiniMax: MiniMax M2.5 deepseek/deepseek-v3.1 4 minimax/minimax-m2.5 8
Meta: Llama 3.1 8B Instruct vs MiniMax: MiniMax M2.5 meta-llama/llama-3.1-8b-instruct 4 minimax/minimax-m2.5 8
Llama 4 Scout Instruct vs MiniMax: MiniMax M2.5 meta-llama/llama-4-scout-17b-16e-instruct 5 minimax/minimax-m2.5 8
Meta: Llama 4 Maverick vs MiniMax: MiniMax M2.5 meta-llama/llama-4-maverick 5 minimax/minimax-m2.5 8
google/gemma-4-12B-it vs MiniMax: MiniMax M2.5 google/gemma-4-12b-it 4 minimax/minimax-m2.5 8
MiniMax: MiniMax M2.5 vs Qwen3 Embedding 8B minimax/minimax-m2.5 8 qwen/qwen3-embedding-8b 4
MiniMax: MiniMax M2.5 vs OpenAI: GPT-5.5 minimax/minimax-m2.5 8 openai/gpt-5.5 4
MiniMax: MiniMax M2.5 vs OpenAI: GPT-5.6 Terra minimax/minimax-m2.5 8 openai/gpt-5.6-terra 4
MiniMax: MiniMax M2.5 vs OpenAI: GPT-6 Astra minimax/minimax-m2.5 8 openai/gpt-6-astra 4
MiniMax: MiniMax M2.5 vs OpenAI: GPT-6 Luna minimax/minimax-m2.5 8 openai/gpt-6-luna 4
Google: Gemma 3 12B vs Xiaomi: MiMo-V2.6-Pro google/gemma-3-12b-it 7 xiaomi/mimo-v2.6-pro 8
Google: Gemini 2.5 Flash vs Google: Gemma 3 12B google/gemini-2.5-flash 6 google/gemma-3-12b-it 7
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

By continuing you agree to the terms of service and privacy policy.