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
Google: Gemini 2.5 Flash vs Qwen: Qwen3 Coder Next	`google/gemini-2.5-flash`	8	`qwen/qwen3-coder-next`	5
Google: Gemini 2.5 Flash vs Qwen3 Max	`google/gemini-2.5-flash`	8	`qwen/qwen3-max`	5
Google: Gemini 2.5 Flash vs Z.ai: GLM 4.7 Flash	`google/gemini-2.5-flash`	8	`z-ai/glm-4.7-flash`	5
DeepSeek: R1 0528 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-r1-0528`	6	`google/gemini-2.5-flash`	8
DeepSeek V3 0324 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v3-0324`	7	`google/gemini-2.5-flash`	8
DeepSeek: DeepSeek V3.2 Exp vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v3.2-exp`	5	`google/gemini-2.5-flash`	8
DeepSeek: DeepSeek V3.1 Terminus vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v3.1-terminus`	5	`google/gemini-2.5-flash`	8
Google: Gemini 2.5 Flash vs Google: Gemma 3 12B	`google/gemini-2.5-flash`	8	`google/gemma-3-12b-it`	5
Qwen: Qwen3.5-27B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.5-27b`	8	`xiaomi/mimo-v2.5`	8
NVIDIA: Nemotron 3 Ultra vs Xiaomi: MiMo-V2.5	`nvidia/nemotron-3-ultra-550b-a55b`	9	`xiaomi/mimo-v2.5`	8
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 4.6	`xiaomi/mimo-v2.5`	8	`z-ai/glm-4.6`	8
Google: Gemini 2.5 Pro vs Xiaomi: MiMo-V2.5	`google/gemini-2.5-pro`	6	`xiaomi/mimo-v2.5`	8
Google: Gemini 3 Flash Preview vs Xiaomi: MiMo-V2.5	`google/gemini-3-flash-preview`	6	`xiaomi/mimo-v2.5`	8
Google: Gemini 3.1 Flash Lite vs Xiaomi: MiMo-V2.5	`google/gemini-3.1-flash-lite`	6	`xiaomi/mimo-v2.5`	8
Google: Gemini 3.1 Pro Preview vs Xiaomi: MiMo-V2.5	`google/gemini-3.1-pro-preview`	7	`xiaomi/mimo-v2.5`	8
Google: Gemini 3.5 Flash vs Xiaomi: MiMo-V2.5	`google/gemini-3.5-flash`	7	`xiaomi/mimo-v2.5`	8
Xiaomi: MiMo-V2.5 vs Xiaomi: MiMo-V2.5-Pro	`xiaomi/mimo-v2.5`	8	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v4-pro-0423`	4	`xiaomi/mimo-v2.5`	8
Qwen3.7 Max vs Xiaomi: MiMo-V2.5	`qwen/qwen3.7-max`	7	`xiaomi/mimo-v2.5`	8
Qwen3.8 Max vs Xiaomi: MiMo-V2.5	`qwen/qwen3.8-max`	8	`xiaomi/mimo-v2.5`	8
Thinking Machines: Inkling vs Xiaomi: MiMo-V2.5	`thinkingmachines/inkling`	7	`xiaomi/mimo-v2.5`	8
Thinking Machines: Inkling Small vs Xiaomi: MiMo-V2.5	`thinkingmachines/inkling-small`	7	`xiaomi/mimo-v2.5`	8
NVIDIA: Nemotron 3 Super vs Xiaomi: MiMo-V2.5	`nvidia/nemotron-3-super-120b-a12b`	7	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3 VL 30B A3B Instruct vs Xiaomi: MiMo-V2.5	`qwen/qwen3-vl-30b-a3b-instruct`	6	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3.5-9B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.5-9b`	8	`xiaomi/mimo-v2.5`	8
Tencent: Hy3 vs Xiaomi: MiMo-V2.5	`tencent/hy3`	8	`xiaomi/mimo-v2.5`	8
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5V Turbo	`xiaomi/mimo-v2.5`	8	`z-ai/glm-5v-turbo`	7
DeepSeek V3.1 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v3.1`	6	`xiaomi/mimo-v2.5`	8
Google: Gemma 3 27B vs Xiaomi: MiMo-V2.5	`google/gemma-3-27b-it`	8	`xiaomi/mimo-v2.5`	8
Meta: Llama 3.1 8B Instruct vs Xiaomi: MiMo-V2.5	`meta-llama/llama-3.1-8b-instruct`	6	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3 235B A22B Thinking 2507 vs Xiaomi: MiMo-V2.5	`qwen/qwen3-235b-a22b-thinking-2507`	7	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3 VL 235B A22B Instruct vs Xiaomi: MiMo-V2.5	`qwen/qwen3-vl-235b-a22b-instruct`	7	`xiaomi/mimo-v2.5`	8
OpenAI: GPT-5.6 Terra vs Xiaomi: MiMo-V2.5	`openai/gpt-5.6-terra`	6	`xiaomi/mimo-v2.5`	8
Google: Gemini 3.7 Flash vs Xiaomi: MiMo-V2.5	`google/gemini-3.7-flash`	6	`xiaomi/mimo-v2.5`	8
Llama 4 Maverick Instruct vs Xiaomi: MiMo-V2.5	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`xiaomi/mimo-v2.5`	8
DeepSeek V4 Pro 0813 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v4-pro-0813`	3	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3.8 2.4T A95B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.8-2.4t-a95b`	6	`xiaomi/mimo-v2.5`	8
NVIDIA: Nemotron 3 Nano 30B A3B vs Xiaomi: MiMo-V2.5	`nvidia/nemotron-3-nano-30b-a3b`	6	`xiaomi/mimo-v2.5`	8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Xiaomi: MiMo-V2.5	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3 Coder 30B A3B Instruct vs Xiaomi: MiMo-V2.5	`qwen/qwen3-coder-30b-a3b-instruct`	4	`xiaomi/mimo-v2.5`	8
Qwen: Qwen3 Coder Next vs Xiaomi: MiMo-V2.5	`qwen/qwen3-coder-next`	5	`xiaomi/mimo-v2.5`	8
Qwen3 Max vs Xiaomi: MiMo-V2.5	`qwen/qwen3-max`	5	`xiaomi/mimo-v2.5`	8
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 4.7 Flash	`xiaomi/mimo-v2.5`	8	`z-ai/glm-4.7-flash`	5
DeepSeek: R1 0528 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-r1-0528`	6	`xiaomi/mimo-v2.5`	8
DeepSeek V3 0324 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v3-0324`	7	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V3.2 Exp vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v3.2-exp`	5	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V3.1 Terminus vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v3.1-terminus`	5	`xiaomi/mimo-v2.5`	8
Google: Gemma 3 12B vs Xiaomi: MiMo-V2.5	`google/gemma-3-12b-it`	5	`xiaomi/mimo-v2.5`	8
NVIDIA: Nemotron 3 Ultra vs Qwen: Qwen3.5-27B	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Z.ai: GLM 4.6	`qwen/qwen3.5-27b`	8	`z-ai/glm-4.6`	8
Google: Gemini 2.5 Pro vs Qwen: Qwen3.5-27B	`google/gemini-2.5-pro`	6	`qwen/qwen3.5-27b`	8
Google: Gemini 3 Flash Preview vs Qwen: Qwen3.5-27B	`google/gemini-3-flash-preview`	6	`qwen/qwen3.5-27b`	8
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3.5-27B	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.5-27b`	8
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.5-27B	`google/gemini-3.1-pro-preview`	7	`qwen/qwen3.5-27b`	8
Google: Gemini 3.5 Flash vs Qwen: Qwen3.5-27B	`google/gemini-3.5-flash`	7	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3.5-27b`	8	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Qwen3.7 Max	`qwen/qwen3.5-27b`	8	`qwen/qwen3.7-max`	7
Qwen: Qwen3.5-27B vs Qwen3.8 Max	`qwen/qwen3.5-27b`	8	`qwen/qwen3.8-max`	8
Qwen: Qwen3.5-27B vs Thinking Machines: Inkling	`qwen/qwen3.5-27b`	8	`thinkingmachines/inkling`	7
Qwen: Qwen3.5-27B vs Thinking Machines: Inkling Small	`qwen/qwen3.5-27b`	8	`thinkingmachines/inkling-small`	7
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3.5-27B	`nvidia/nemotron-3-super-120b-a12b`	7	`qwen/qwen3.5-27b`	8
Qwen: Qwen3 VL 30B A3B Instruct vs Qwen: Qwen3.5-27B	`qwen/qwen3-vl-30b-a3b-instruct`	6	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Qwen: Qwen3.5-9B	`qwen/qwen3.5-27b`	8	`qwen/qwen3.5-9b`	8
Qwen: Qwen3.5-27B vs Tencent: Hy3	`qwen/qwen3.5-27b`	8	`tencent/hy3`	8
Qwen: Qwen3.5-27B vs Z.ai: GLM 5V Turbo	`qwen/qwen3.5-27b`	8	`z-ai/glm-5v-turbo`	7
DeepSeek V3.1 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v3.1`	6	`qwen/qwen3.5-27b`	8
Google: Gemma 3 27B vs Qwen: Qwen3.5-27B	`google/gemma-3-27b-it`	8	`qwen/qwen3.5-27b`	8
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.5-27B	`meta-llama/llama-3.1-8b-instruct`	6	`qwen/qwen3.5-27b`	8
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.5-27B	`qwen/qwen3-235b-a22b-thinking-2507`	7	`qwen/qwen3.5-27b`	8
Qwen: Qwen3 VL 235B A22B Instruct vs Qwen: Qwen3.5-27B	`qwen/qwen3-vl-235b-a22b-instruct`	7	`qwen/qwen3.5-27b`	8
OpenAI: GPT-5.6 Terra vs Qwen: Qwen3.5-27B	`openai/gpt-5.6-terra`	6	`qwen/qwen3.5-27b`	8
Google: Gemini 3.7 Flash vs Qwen: Qwen3.5-27B	`google/gemini-3.7-flash`	6	`qwen/qwen3.5-27b`	8
Llama 4 Maverick Instruct vs Qwen: Qwen3.5-27B	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`qwen/qwen3.5-27b`	8
DeepSeek V4 Pro 0813 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v4-pro-0813`	3	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Qwen: Qwen3.8 2.4T A95B	`qwen/qwen3.5-27b`	8	`qwen/qwen3.8-2.4t-a95b`	6
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3.5-27B	`nvidia/nemotron-3-nano-30b-a3b`	6	`qwen/qwen3.5-27b`	8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.5-27B	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3.5-27b`	8
Qwen: Qwen3 Coder 30B A3B Instruct vs Qwen: Qwen3.5-27B	`qwen/qwen3-coder-30b-a3b-instruct`	4	`qwen/qwen3.5-27b`	8
Qwen: Qwen3 Coder Next vs Qwen: Qwen3.5-27B	`qwen/qwen3-coder-next`	5	`qwen/qwen3.5-27b`	8
Qwen3 Max vs Qwen: Qwen3.5-27B	`qwen/qwen3-max`	5	`qwen/qwen3.5-27b`	8
Qwen: Qwen3.5-27B vs Z.ai: GLM 4.7 Flash	`qwen/qwen3.5-27b`	8	`z-ai/glm-4.7-flash`	5
DeepSeek: R1 0528 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-r1-0528`	6	`qwen/qwen3.5-27b`	8
DeepSeek V3 0324 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v3-0324`	7	`qwen/qwen3.5-27b`	8
DeepSeek: DeepSeek V3.2 Exp vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v3.2-exp`	5	`qwen/qwen3.5-27b`	8
DeepSeek: DeepSeek V3.1 Terminus vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v3.1-terminus`	5	`qwen/qwen3.5-27b`	8
Google: Gemma 3 12B vs Qwen: Qwen3.5-27B	`google/gemma-3-12b-it`	5	`qwen/qwen3.5-27b`	8
NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 4.6	`nvidia/nemotron-3-ultra-550b-a55b`	9	`z-ai/glm-4.6`	8
Google: Gemini 2.5 Pro vs NVIDIA: Nemotron 3 Ultra	`google/gemini-2.5-pro`	6	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemini 3 Flash Preview vs NVIDIA: Nemotron 3 Ultra	`google/gemini-3-flash-preview`	6	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemini 3.1 Flash Lite vs NVIDIA: Nemotron 3 Ultra	`google/gemini-3.1-flash-lite`	6	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemini 3.1 Pro Preview vs NVIDIA: Nemotron 3 Ultra	`google/gemini-3.1-pro-preview`	7	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemini 3.5 Flash vs NVIDIA: Nemotron 3 Ultra	`google/gemini-3.5-flash`	7	`nvidia/nemotron-3-ultra-550b-a55b`	9
NVIDIA: Nemotron 3 Ultra vs Xiaomi: MiMo-V2.5-Pro	`nvidia/nemotron-3-ultra-550b-a55b`	9	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs NVIDIA: Nemotron 3 Ultra	`deepseek/deepseek-v4-pro-0423`	4	`nvidia/nemotron-3-ultra-550b-a55b`	9
NVIDIA: Nemotron 3 Ultra vs Qwen3.7 Max	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.7-max`	7
NVIDIA: Nemotron 3 Ultra vs Qwen3.8 Max	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.8-max`	8
NVIDIA: Nemotron 3 Ultra vs Thinking Machines: Inkling	`nvidia/nemotron-3-ultra-550b-a55b`	9	`thinkingmachines/inkling`	7
NVIDIA: Nemotron 3 Ultra vs Thinking Machines: Inkling Small	`nvidia/nemotron-3-ultra-550b-a55b`	9	`thinkingmachines/inkling-small`	7
NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3 Ultra	`nvidia/nemotron-3-super-120b-a12b`	7	`nvidia/nemotron-3-ultra-550b-a55b`	9