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 reports Run 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 Next 80B A3B Instruct vs Qwen: Qwen3.5-9B	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.5-9b`	10
Qwen: Qwen3 Next 80B A3B Instruct vs Z.ai: GLM 4.6	`qwen/qwen3-next-80b-a3b-instruct`	10	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs Qwen: Qwen3 Next 80B A3B Instruct	`deepseek/deepseek-v3.1`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Next 80B A3B Instruct vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3-next-80b-a3b-instruct`	10	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 Next 80B A3B Instruct	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemini 2.5 Pro vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-2.5-pro`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemini 3 Flash Preview vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-3-flash-preview`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-3.1-pro-preview`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemini 3.5 Flash vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-3.5-flash`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen3.7 Max	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.7-max`	7
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen3.8 Max	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.8-max`	8
Qwen: Qwen3 Next 80B A3B Instruct vs Thinking Machines: Inkling	`qwen/qwen3-next-80b-a3b-instruct`	10	`thinkingmachines/inkling`	7
Qwen: Qwen3 Next 80B A3B Instruct vs Thinking Machines: Inkling Small	`qwen/qwen3-next-80b-a3b-instruct`	10	`thinkingmachines/inkling-small`	7
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3 Next 80B A3B Instruct	`nvidia/nemotron-3-super-120b-a12b`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Coder Next vs Qwen: Qwen3 Next 80B A3B Instruct	`qwen/qwen3-coder-next`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3 VL 235B A22B Instruct	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3-vl-235b-a22b-instruct`	7
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3.5-27B	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.5-27b`	6
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3.8 2.4T A95B	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.8-2.4t-a95b`	8
Qwen: Qwen3 Next 80B A3B Instruct vs Tencent: Hy3	`qwen/qwen3-next-80b-a3b-instruct`	10	`tencent/hy3`	8
Google: Gemma 3 27B vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemma-3-27b-it`	8	`qwen/qwen3-next-80b-a3b-instruct`	10
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-llama/llama-3.1-8b-instruct`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3 Next 80B A3B Instruct	`qwen/qwen3-235b-a22b-thinking-2507`	7	`qwen/qwen3-next-80b-a3b-instruct`	10
OpenAI: GPT-5.6 Terra vs Qwen: Qwen3 Next 80B A3B Instruct	`openai/gpt-5.6-terra`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
OpenAI: GPT-6 Astra vs Qwen: Qwen3 Next 80B A3B Instruct	`openai/gpt-6-astra`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Llama 4 Maverick Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`qwen/qwen3-next-80b-a3b-instruct`	10
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 Next 80B A3B Instruct	`nvidia/nemotron-3-nano-30b-a3b`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3 Next 80B A3B Instruct	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen3 Max vs Qwen: Qwen3 Next 80B A3B Instruct	`qwen/qwen3-max`	5	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3 VL 30B A3B Instruct	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3-vl-30b-a3b-instruct`	5
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3 VL 8B Instruct	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3-vl-8b-instruct`	4
Qwen: Qwen3 Next 80B A3B Instruct vs Z.ai: GLM 5V Turbo	`qwen/qwen3-next-80b-a3b-instruct`	10	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Qwen: Qwen3 Next 80B A3B Instruct	`deepseek/deepseek-r1-0528`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3 Coder 30B A3B Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`qwen/qwen3-coder-30b-a3b-instruct`	4	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemma 3 12B vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemma-3-12b-it`	5	`qwen/qwen3-next-80b-a3b-instruct`	10
Meta: Llama 3.1 70B Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-llama/llama-3.1-70b-instruct`	5	`qwen/qwen3-next-80b-a3b-instruct`	10
Llama 4 Scout Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`qwen/qwen3-next-80b-a3b-instruct`	10
Muse Glimmer 30B on Fireworks vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-models/muse-glimmer-30b`	6	`qwen/qwen3-next-80b-a3b-instruct`	10
Qwen: Qwen3.5-35B-A3B vs Z.ai: GLM 5	`qwen/qwen3.5-35b-a3b`	10	`z-ai/glm-5`	10
Qwen3 235B A22B Instruct 2507 vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-235b-a22b-instruct-2507`	9	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.5-35b-a3b`	10	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-v4-flash-vision-exp`	10	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 2.5 Flash vs Qwen: Qwen3.5-35B-A3B	`google/gemini-2.5-flash`	8	`qwen/qwen3.5-35b-a3b`	10
NVIDIA: Nemotron 3 Ultra vs Qwen: Qwen3.5-35B-A3B	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Qwen: Qwen3.5-9B	`qwen/qwen3.5-35b-a3b`	10	`qwen/qwen3.5-9b`	10
Qwen: Qwen3.5-35B-A3B vs Z.ai: GLM 4.6	`qwen/qwen3.5-35b-a3b`	10	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-v3.1`	7	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3.5-35b-a3b`	10	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 2.5 Pro vs Qwen: Qwen3.5-35B-A3B	`google/gemini-2.5-pro`	6	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 3 Flash Preview vs Qwen: Qwen3.5-35B-A3B	`google/gemini-3-flash-preview`	6	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3.5-35B-A3B	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.5-35B-A3B	`google/gemini-3.1-pro-preview`	7	`qwen/qwen3.5-35b-a3b`	10
Google: Gemini 3.5 Flash vs Qwen: Qwen3.5-35B-A3B	`google/gemini-3.5-flash`	7	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Qwen3.7 Max	`qwen/qwen3.5-35b-a3b`	10	`qwen/qwen3.7-max`	7
Qwen: Qwen3.5-35B-A3B vs Qwen3.8 Max	`qwen/qwen3.5-35b-a3b`	10	`qwen/qwen3.8-max`	8
Qwen: Qwen3.5-35B-A3B vs Thinking Machines: Inkling	`qwen/qwen3.5-35b-a3b`	10	`thinkingmachines/inkling`	7
Qwen: Qwen3.5-35B-A3B vs Thinking Machines: Inkling Small	`qwen/qwen3.5-35b-a3b`	10	`thinkingmachines/inkling-small`	7
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3.5-35B-A3B	`nvidia/nemotron-3-super-120b-a12b`	7	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 Coder Next vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-coder-next`	7	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 VL 235B A22B Instruct vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-vl-235b-a22b-instruct`	7	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-27B vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3.5-27b`	6	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Qwen: Qwen3.8 2.4T A95B	`qwen/qwen3.5-35b-a3b`	10	`qwen/qwen3.8-2.4t-a95b`	8
Qwen: Qwen3.5-35B-A3B vs Tencent: Hy3	`qwen/qwen3.5-35b-a3b`	10	`tencent/hy3`	8
Google: Gemma 3 27B vs Qwen: Qwen3.5-35B-A3B	`google/gemma-3-27b-it`	8	`qwen/qwen3.5-35b-a3b`	10
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.5-35B-A3B	`meta-llama/llama-3.1-8b-instruct`	6	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-235b-a22b-thinking-2507`	7	`qwen/qwen3.5-35b-a3b`	10
OpenAI: GPT-5.6 Terra vs Qwen: Qwen3.5-35B-A3B	`openai/gpt-5.6-terra`	6	`qwen/qwen3.5-35b-a3b`	10
OpenAI: GPT-6 Astra vs Qwen: Qwen3.5-35B-A3B	`openai/gpt-6-astra`	6	`qwen/qwen3.5-35b-a3b`	10
Llama 4 Maverick Instruct vs Qwen: Qwen3.5-35B-A3B	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`qwen/qwen3.5-35b-a3b`	10
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3.5-35B-A3B	`nvidia/nemotron-3-nano-30b-a3b`	6	`qwen/qwen3.5-35b-a3b`	10
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.5-35B-A3B	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3.5-35b-a3b`	10
Qwen3 Max vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-max`	5	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 VL 30B A3B Instruct vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-vl-30b-a3b-instruct`	5	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 VL 8B Instruct vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-vl-8b-instruct`	4	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3.5-35B-A3B vs Z.ai: GLM 5V Turbo	`qwen/qwen3.5-35b-a3b`	10	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-r1-0528`	6	`qwen/qwen3.5-35b-a3b`	10
Qwen: Qwen3 Coder 30B A3B Instruct vs Qwen: Qwen3.5-35B-A3B	`qwen/qwen3-coder-30b-a3b-instruct`	4	`qwen/qwen3.5-35b-a3b`	10
Google: Gemma 3 12B vs Qwen: Qwen3.5-35B-A3B	`google/gemma-3-12b-it`	5	`qwen/qwen3.5-35b-a3b`	10
Meta: Llama 3.1 70B Instruct vs Qwen: Qwen3.5-35B-A3B	`meta-llama/llama-3.1-70b-instruct`	5	`qwen/qwen3.5-35b-a3b`	10
Llama 4 Scout Instruct vs Qwen: Qwen3.5-35B-A3B	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`qwen/qwen3.5-35b-a3b`	10
Muse Glimmer 30B on Fireworks vs Qwen: Qwen3.5-35B-A3B	`meta-models/muse-glimmer-30b`	6	`qwen/qwen3.5-35b-a3b`	10
Qwen3 235B A22B Instruct 2507 vs Z.ai: GLM 5	`qwen/qwen3-235b-a22b-instruct-2507`	9	`z-ai/glm-5`	10
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5	`xiaomi/mimo-v2.5`	8	`z-ai/glm-5`	10
DeepSeek: DeepSeek V4 Flash Vision Exp vs Z.ai: GLM 5	`deepseek/deepseek-v4-flash-vision-exp`	10	`z-ai/glm-5`	10
Google: Gemini 2.5 Flash vs Z.ai: GLM 5	`google/gemini-2.5-flash`	8	`z-ai/glm-5`	10
NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 5	`nvidia/nemotron-3-ultra-550b-a55b`	9	`z-ai/glm-5`	10
Qwen: Qwen3.5-9B vs Z.ai: GLM 5	`qwen/qwen3.5-9b`	10	`z-ai/glm-5`	10
Z.ai: GLM 4.6 vs Z.ai: GLM 5	`z-ai/glm-4.6`	8	`z-ai/glm-5`	10
DeepSeek V3.1 vs Z.ai: GLM 5	`deepseek/deepseek-v3.1`	7	`z-ai/glm-5`	10
Xiaomi: MiMo-V2.5-Pro vs Z.ai: GLM 5	`xiaomi/mimo-v2.5-pro`	8	`z-ai/glm-5`	10
DeepSeek V4 Pro 0423 vs Z.ai: GLM 5	`deepseek/deepseek-v4-pro-0423`	4	`z-ai/glm-5`	10
Google: Gemini 2.5 Pro vs Z.ai: GLM 5	`google/gemini-2.5-pro`	6	`z-ai/glm-5`	10
Google: Gemini 3 Flash Preview vs Z.ai: GLM 5	`google/gemini-3-flash-preview`	6	`z-ai/glm-5`	10
Google: Gemini 3.1 Flash Lite vs Z.ai: GLM 5	`google/gemini-3.1-flash-lite`	6	`z-ai/glm-5`	10
Google: Gemini 3.1 Pro Preview vs Z.ai: GLM 5	`google/gemini-3.1-pro-preview`	7	`z-ai/glm-5`	10
Google: Gemini 3.5 Flash vs Z.ai: GLM 5	`google/gemini-3.5-flash`	7	`z-ai/glm-5`	10
Qwen3.7 Max vs Z.ai: GLM 5	`qwen/qwen3.7-max`	7	`z-ai/glm-5`	10
Qwen3.8 Max vs Z.ai: GLM 5	`qwen/qwen3.8-max`	8	`z-ai/glm-5`	10
Thinking Machines: Inkling vs Z.ai: GLM 5	`thinkingmachines/inkling`	7	`z-ai/glm-5`	10