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
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 5V Turbo	`moonshotai/kimi-k2.5`	14	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-r1-0528`	6	`moonshotai/kimi-k2.5`	14
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.6 27B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v3.2`	15	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 5	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-5`	12
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.5-9B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.5-9b`	12
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 4.7	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-4.7`	10
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.8 2.4T A95B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.8-2.4t-a95b`	9
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.5-122B-A10B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.5-122b-a10b`	10
Meta: Llama 3.3 70B Instruct vs MiniMax: MiniMax M2.5	`meta-llama/llama-3.3-70b-instruct`	14	`minimax/minimax-m2.5`	9
Google: Gemma 3 27B vs Meta: Llama 3.3 70B Instruct	`google/gemma-3-27b-it`	10	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 4.7 Flash	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-4.7-flash`	7
Meta: Llama 3.3 70B Instruct vs Xiaomi: MiMo-V2.6-Flash	`meta-llama/llama-3.3-70b-instruct`	14	`xiaomi/mimo-v2.6-flash`	9
Meta: Llama 3.3 70B Instruct vs NVIDIA: Nemotron 3 Super	`meta-llama/llama-3.3-70b-instruct`	14	`nvidia/nemotron-3-super-120b-a12b`	8
Meta: Llama 3.3 70B Instruct vs NVIDIA: Nemotron 3 Ultra	`meta-llama/llama-3.3-70b-instruct`	14	`nvidia/nemotron-3-ultra-550b-a55b`	9
Meta: Llama 3.3 70B Instruct vs Qwen/Qwen3-235B-A22B-Instruct-2507	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3-235b-a22b-instruct-2507`	7
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3 Next 80B A3B Instruct	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3-next-80b-a3b-instruct`	8
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.5-27B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.5-27b`	7
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.5-35B-A3B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.5-35b-a3b`	9
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 4.6	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-4.6`	8
deepseek-ai/DeepSeek-V3.1 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v3.1`	6	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemma 3 12B vs Meta: Llama 3.3 70B Instruct	`google/gemma-3-12b-it`	7	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.1 8B Instruct vs Meta: Llama 3.3 70B Instruct	`meta-llama/llama-3.1-8b-instruct`	7	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3 14B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3-14b`	6
Meta: Llama 3.3 70B Instruct vs Xiaomi: MiMo-V2.6-Pro	`meta-llama/llama-3.3-70b-instruct`	14	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v4-pro-0423`	4	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemini 2.5 Flash vs Meta: Llama 3.3 70B Instruct	`google/gemini-2.5-flash`	6	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemini 3.1 Flash Lite vs Meta: Llama 3.3 70B Instruct	`google/gemini-3.1-flash-lite`	6	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.3 70B Instruct vs Xiaomi: MiMo-V2.5	`meta-llama/llama-3.3-70b-instruct`	14	`xiaomi/mimo-v2.5`	5
Meta: Llama 3.3 70B Instruct vs Qwen3.7 Max	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.7-max`	7
Meta: Llama 3.3 70B Instruct vs Qwen3.8 Max	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.8-max`	8
Meta: Llama 3.3 70B Instruct vs Tencent: Hy4 preview	`meta-llama/llama-3.3-70b-instruct`	14	`tencent/hy4-preview`	8
Meta: Llama 3.3 70B Instruct vs Tencent: Hy3	`meta-llama/llama-3.3-70b-instruct`	14	`tencent/hy3`	8
Meta: Llama 3.3 70B Instruct vs MiniMax: MiniMax M2.7	`meta-llama/llama-3.3-70b-instruct`	14	`minimax/minimax-m2.7`	7
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3 32B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3-32b`	5
Meta: Llama 3.3 70B Instruct vs OpenAI: GPT-5.6 Luna	`meta-llama/llama-3.3-70b-instruct`	14	`openai/gpt-5.6-luna`	4
Meta: Llama 3.3 70B Instruct vs OpenAI: GPT-5.6 Sol	`meta-llama/llama-3.3-70b-instruct`	14	`openai/gpt-5.6-sol`	5
DeepSeek: DeepSeek V4 Flash Vision Exp vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v4-flash-vision-exp`	6	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemini 2.5 Pro vs Meta: Llama 3.3 70B Instruct	`google/gemini-2.5-pro`	4	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemini 3.1 Pro Preview vs Meta: Llama 3.3 70B Instruct	`google/gemini-3.1-pro-preview`	5	`meta-llama/llama-3.3-70b-instruct`	14
Google: Gemini 3.8 Flash vs Meta: Llama 3.3 70B Instruct	`google/gemini-3.8-flash`	5	`meta-llama/llama-3.3-70b-instruct`	14
Meta: Llama 3.3 70B Instruct vs stepfun-ai/Step-5-Preview	`meta-llama/llama-3.3-70b-instruct`	14	`stepfun-ai/step-5-preview`	5
Meta: Llama 3.3 70B Instruct vs Xiaomi: MiMo-V2.5-Pro	`meta-llama/llama-3.3-70b-instruct`	14	`xiaomi/mimo-v2.5-pro`	5
Meta: Llama 3.3 70B Instruct vs Qwen3.8 Flash	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.8-flash`	6
Meta: Llama 3.3 70B Instruct vs Thinking Machines: Inkling	`meta-llama/llama-3.3-70b-instruct`	14	`thinkingmachines/inkling`	5
Meta: Llama 3.3 70B Instruct vs MoonshotAI: Kimi K2 Thinking	`meta-llama/llama-3.3-70b-instruct`	14	`moonshotai/kimi-k2-thinking`	5
Meta: Llama 3.3 70B Instruct vs NVIDIA: Nemotron 3 Nano 30B A3B	`meta-llama/llama-3.3-70b-instruct`	14	`nvidia/nemotron-3-nano-30b-a3b`	5
Meta: Llama 3.3 70B Instruct vs NVIDIA: Nemotron 3.5 Lightning	`meta-llama/llama-3.3-70b-instruct`	14	`nvidia/nemotron-3.5-lightning`	5
Meta: Llama 3.3 70B Instruct vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`meta-llama/llama-3.3-70b-instruct`	14	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3 Coder Next	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3-coder-next`	4
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.8-Flash-Next	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.8-flash-next`	3
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 5V Turbo	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-r1-0528`	6	`meta-llama/llama-3.3-70b-instruct`	14
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v3.2`	15	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Z.ai: GLM 5	`qwen/qwen3.6-27b`	14	`z-ai/glm-5`	12
Qwen: Qwen3.5-9B vs Qwen: Qwen3.6 27B	`qwen/qwen3.5-9b`	12	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Z.ai: GLM 4.7	`qwen/qwen3.6-27b`	14	`z-ai/glm-4.7`	10
Qwen: Qwen3.6 27B vs Qwen: Qwen3.8 2.4T A95B	`qwen/qwen3.6-27b`	14	`qwen/qwen3.8-2.4t-a95b`	9
Qwen: Qwen3.5-122B-A10B vs Qwen: Qwen3.6 27B	`qwen/qwen3.5-122b-a10b`	10	`qwen/qwen3.6-27b`	14
MiniMax: MiniMax M2.5 vs Qwen: Qwen3.6 27B	`minimax/minimax-m2.5`	9	`qwen/qwen3.6-27b`	14
Google: Gemma 3 27B vs Qwen: Qwen3.6 27B	`google/gemma-3-27b-it`	10	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Z.ai: GLM 4.7 Flash	`qwen/qwen3.6-27b`	14	`z-ai/glm-4.7-flash`	7
Qwen: Qwen3.6 27B vs Xiaomi: MiMo-V2.6-Flash	`qwen/qwen3.6-27b`	14	`xiaomi/mimo-v2.6-flash`	9
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3.6 27B	`nvidia/nemotron-3-super-120b-a12b`	8	`qwen/qwen3.6-27b`	14
NVIDIA: Nemotron 3 Ultra vs Qwen: Qwen3.6 27B	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.6-27b`	14
Qwen/Qwen3-235B-A22B-Instruct-2507 vs Qwen: Qwen3.6 27B	`qwen/qwen3-235b-a22b-instruct-2507`	7	`qwen/qwen3.6-27b`	14
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3.6 27B	`qwen/qwen3-next-80b-a3b-instruct`	8	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.5-27B vs Qwen: Qwen3.6 27B	`qwen/qwen3.5-27b`	7	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.5-35B-A3B vs Qwen: Qwen3.6 27B	`qwen/qwen3.5-35b-a3b`	9	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Z.ai: GLM 4.6	`qwen/qwen3.6-27b`	14	`z-ai/glm-4.6`	8
deepseek-ai/DeepSeek-V3.1 vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v3.1`	6	`qwen/qwen3.6-27b`	14
Google: Gemma 3 12B vs Qwen: Qwen3.6 27B	`google/gemma-3-12b-it`	7	`qwen/qwen3.6-27b`	14
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.6 27B	`meta-llama/llama-3.1-8b-instruct`	7	`qwen/qwen3.6-27b`	14
Qwen: Qwen3 14B vs Qwen: Qwen3.6 27B	`qwen/qwen3-14b`	6	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3.6-27b`	14	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3.6-27b`	14
Google: Gemini 2.5 Flash vs Qwen: Qwen3.6 27B	`google/gemini-2.5-flash`	6	`qwen/qwen3.6-27b`	14
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3.6 27B	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.6-27b`	14	`xiaomi/mimo-v2.5`	5
Qwen: Qwen3.6 27B vs Qwen3.7 Max	`qwen/qwen3.6-27b`	14	`qwen/qwen3.7-max`	7
Qwen: Qwen3.6 27B vs Qwen3.8 Max	`qwen/qwen3.6-27b`	14	`qwen/qwen3.8-max`	8
Qwen: Qwen3.6 27B vs Tencent: Hy4 preview	`qwen/qwen3.6-27b`	14	`tencent/hy4-preview`	8
Qwen: Qwen3.6 27B vs Tencent: Hy3	`qwen/qwen3.6-27b`	14	`tencent/hy3`	8
MiniMax: MiniMax M2.7 vs Qwen: Qwen3.6 27B	`minimax/minimax-m2.7`	7	`qwen/qwen3.6-27b`	14
Qwen: Qwen3 32B vs Qwen: Qwen3.6 27B	`qwen/qwen3-32b`	5	`qwen/qwen3.6-27b`	14
OpenAI: GPT-5.6 Luna vs Qwen: Qwen3.6 27B	`openai/gpt-5.6-luna`	4	`qwen/qwen3.6-27b`	14
OpenAI: GPT-5.6 Sol vs Qwen: Qwen3.6 27B	`openai/gpt-5.6-sol`	5	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V4 Flash Vision Exp vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v4-flash-vision-exp`	6	`qwen/qwen3.6-27b`	14
Google: Gemini 2.5 Pro vs Qwen: Qwen3.6 27B	`google/gemini-2.5-pro`	4	`qwen/qwen3.6-27b`	14
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.6 27B	`google/gemini-3.1-pro-preview`	5	`qwen/qwen3.6-27b`	14
Google: Gemini 3.8 Flash vs Qwen: Qwen3.6 27B	`google/gemini-3.8-flash`	5	`qwen/qwen3.6-27b`	14
Qwen: Qwen3.6 27B vs stepfun-ai/Step-5-Preview	`qwen/qwen3.6-27b`	14	`stepfun-ai/step-5-preview`	5
Qwen: Qwen3.6 27B vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3.6-27b`	14	`xiaomi/mimo-v2.5-pro`	5
Qwen: Qwen3.6 27B vs Qwen3.8 Flash	`qwen/qwen3.6-27b`	14	`qwen/qwen3.8-flash`	6
Qwen: Qwen3.6 27B vs Thinking Machines: Inkling	`qwen/qwen3.6-27b`	14	`thinkingmachines/inkling`	5
MoonshotAI: Kimi K2 Thinking vs Qwen: Qwen3.6 27B	`moonshotai/kimi-k2-thinking`	5	`qwen/qwen3.6-27b`	14
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3.6 27B	`nvidia/nemotron-3-nano-30b-a3b`	5	`qwen/qwen3.6-27b`	14
NVIDIA: Nemotron 3.5 Lightning vs Qwen: Qwen3.6 27B	`nvidia/nemotron-3.5-lightning`	5	`qwen/qwen3.6-27b`	14
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.6 27B	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3.6-27b`	14
Qwen: Qwen3 Coder Next vs Qwen: Qwen3.6 27B	`qwen/qwen3-coder-next`	4	`qwen/qwen3.6-27b`	14