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: Qwen3.8 27B vs Z.ai: GLM 5.1	`qwen/qwen3.8-27b`	19	`z-ai/glm-5.1`	20
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-3.3-70b-instruct`	18	`qwen/qwen3.8-27b`	19
OpenAI: gpt-oss-20b vs Qwen: Qwen3.8 27B	`openai/gpt-oss-20b`	18	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.5 397B A17B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-397b-a17b`	17	`qwen/qwen3.8-27b`	19
Google: Gemma 4 26B A4B vs Qwen: Qwen3.8 27B	`google/gemma-4-26b-a4b-it`	15	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.6 27B vs Qwen: Qwen3.8 27B	`qwen/qwen3.6-27b`	14	`qwen/qwen3.8-27b`	19
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v3.2`	16	`qwen/qwen3.8-27b`	19
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2.5`	12	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.5-122B-A10B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-122b-a10b`	12	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Z.ai: GLM 4.7	`qwen/qwen3.8-27b`	19	`z-ai/glm-4.7`	11
MiniMax: MiniMax M2.5 vs Qwen: Qwen3.8 27B	`minimax/minimax-m2.5`	13	`qwen/qwen3.8-27b`	19
MiniMax: MiniMax M2.7 vs Qwen: Qwen3.8 27B	`minimax/minimax-m2.7`	11	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-next-80b-a3b-instruct`	10	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.5-35B-A3B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-35b-a3b`	10	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Z.ai: GLM 5	`qwen/qwen3.8-27b`	19	`z-ai/glm-5`	10
Qwen3 235B A22B Instruct 2507 vs Qwen: Qwen3.8 27B	`qwen/qwen3-235b-a22b-instruct-2507`	9	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.8-27b`	19	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-flash-vision-exp`	10	`qwen/qwen3.8-27b`	19
Google: Gemini 2.5 Flash vs Qwen: Qwen3.8 27B	`google/gemini-2.5-flash`	8	`qwen/qwen3.8-27b`	19
NVIDIA: Nemotron 3 Ultra vs Qwen: Qwen3.8 27B	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.5-9B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-9b`	10	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Z.ai: GLM 4.6	`qwen/qwen3.8-27b`	19	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v3.1`	7	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3.8-27b`	19	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3.8-27b`	19
Google: Gemini 2.5 Pro vs Qwen: Qwen3.8 27B	`google/gemini-2.5-pro`	6	`qwen/qwen3.8-27b`	19
Google: Gemini 3 Flash Preview vs Qwen: Qwen3.8 27B	`google/gemini-3-flash-preview`	6	`qwen/qwen3.8-27b`	19
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3.8 27B	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.8-27b`	19
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.8 27B	`google/gemini-3.1-pro-preview`	7	`qwen/qwen3.8-27b`	19
Google: Gemini 3.5 Flash vs Qwen: Qwen3.8 27B	`google/gemini-3.5-flash`	7	`qwen/qwen3.8-27b`	19
Qwen3.7 Max vs Qwen: Qwen3.8 27B	`qwen/qwen3.7-max`	7	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Qwen3.8 Max	`qwen/qwen3.8-27b`	19	`qwen/qwen3.8-max`	8
Qwen: Qwen3.8 27B vs Thinking Machines: Inkling	`qwen/qwen3.8-27b`	19	`thinkingmachines/inkling`	7
Qwen: Qwen3.8 27B vs Thinking Machines: Inkling Small	`qwen/qwen3.8-27b`	19	`thinkingmachines/inkling-small`	7
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3.8 27B	`nvidia/nemotron-3-super-120b-a12b`	7	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 Coder Next vs Qwen: Qwen3.8 27B	`qwen/qwen3-coder-next`	7	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 VL 235B A22B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-vl-235b-a22b-instruct`	7	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.5-27B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-27b`	6	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 2.4T A95B vs Qwen: Qwen3.8 27B	`qwen/qwen3.8-2.4t-a95b`	8	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Tencent: Hy3	`qwen/qwen3.8-27b`	19	`tencent/hy3`	8
Google: Gemma 3 27B vs Qwen: Qwen3.8 27B	`google/gemma-3-27b-it`	8	`qwen/qwen3.8-27b`	19
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-3.1-8b-instruct`	6	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.8 27B	`qwen/qwen3-235b-a22b-thinking-2507`	7	`qwen/qwen3.8-27b`	19
OpenAI: GPT-5.6 Terra vs Qwen: Qwen3.8 27B	`openai/gpt-5.6-terra`	6	`qwen/qwen3.8-27b`	19
OpenAI: GPT-6 Astra vs Qwen: Qwen3.8 27B	`openai/gpt-6-astra`	6	`qwen/qwen3.8-27b`	19
Llama 4 Maverick Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`qwen/qwen3.8-27b`	19
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3.8 27B	`nvidia/nemotron-3-nano-30b-a3b`	6	`qwen/qwen3.8-27b`	19
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.8 27B	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3.8-27b`	19
Qwen3 Max vs Qwen: Qwen3.8 27B	`qwen/qwen3-max`	5	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 VL 30B A3B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-vl-30b-a3b-instruct`	5	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 VL 8B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-vl-8b-instruct`	4	`qwen/qwen3.8-27b`	19
Qwen: Qwen3.8 27B vs Z.ai: GLM 5V Turbo	`qwen/qwen3.8-27b`	19	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-r1-0528`	6	`qwen/qwen3.8-27b`	19
Qwen: Qwen3 Coder 30B A3B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-coder-30b-a3b-instruct`	4	`qwen/qwen3.8-27b`	19
Google: Gemma 3 12B vs Qwen: Qwen3.8 27B	`google/gemma-3-12b-it`	5	`qwen/qwen3.8-27b`	19
Meta: Llama 3.1 70B Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-3.1-70b-instruct`	5	`qwen/qwen3.8-27b`	19
Llama 4 Scout Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`qwen/qwen3.8-27b`	19
Muse Glimmer 30B on Fireworks vs Qwen: Qwen3.8 27B	`meta-models/muse-glimmer-30b`	6	`qwen/qwen3.8-27b`	19
MiniMax: MiniMax M3 vs Qwen: Qwen3.6 35B A3B	`minimax/minimax-m3`	21	`qwen/qwen3.6-35b-a3b`	17
MiniMax: MiniMax M3 vs Z.ai: GLM 5.1	`minimax/minimax-m3`	21	`z-ai/glm-5.1`	20
Meta: Llama 3.3 70B Instruct vs MiniMax: MiniMax M3	`meta-llama/llama-3.3-70b-instruct`	18	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs OpenAI: gpt-oss-20b	`minimax/minimax-m3`	21	`openai/gpt-oss-20b`	18
MiniMax: MiniMax M3 vs Qwen: Qwen3.5 397B A17B	`minimax/minimax-m3`	21	`qwen/qwen3.5-397b-a17b`	17
Google: Gemma 4 26B A4B vs MiniMax: MiniMax M3	`google/gemma-4-26b-a4b-it`	15	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs Qwen: Qwen3.6 27B	`minimax/minimax-m3`	21	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs MiniMax: MiniMax M3	`deepseek/deepseek-v3.2`	16	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs MoonshotAI: Kimi K2.5	`minimax/minimax-m3`	21	`moonshotai/kimi-k2.5`	12
MiniMax: MiniMax M3 vs Qwen: Qwen3.5-122B-A10B	`minimax/minimax-m3`	21	`qwen/qwen3.5-122b-a10b`	12
MiniMax: MiniMax M3 vs Z.ai: GLM 4.7	`minimax/minimax-m3`	21	`z-ai/glm-4.7`	11
MiniMax: MiniMax M2.5 vs MiniMax: MiniMax M3	`minimax/minimax-m2.5`	13	`minimax/minimax-m3`	21
MiniMax: MiniMax M2.7 vs MiniMax: MiniMax M3	`minimax/minimax-m2.7`	11	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs Qwen: Qwen3 Next 80B A3B Instruct	`minimax/minimax-m3`	21	`qwen/qwen3-next-80b-a3b-instruct`	10
MiniMax: MiniMax M3 vs Qwen: Qwen3.5-35B-A3B	`minimax/minimax-m3`	21	`qwen/qwen3.5-35b-a3b`	10
MiniMax: MiniMax M3 vs Z.ai: GLM 5	`minimax/minimax-m3`	21	`z-ai/glm-5`	10
MiniMax: MiniMax M3 vs Qwen3 235B A22B Instruct 2507	`minimax/minimax-m3`	21	`qwen/qwen3-235b-a22b-instruct-2507`	9
MiniMax: MiniMax M3 vs Xiaomi: MiMo-V2.5	`minimax/minimax-m3`	21	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs MiniMax: MiniMax M3	`deepseek/deepseek-v4-flash-vision-exp`	10	`minimax/minimax-m3`	21
Google: Gemini 2.5 Flash vs MiniMax: MiniMax M3	`google/gemini-2.5-flash`	8	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs NVIDIA: Nemotron 3 Ultra	`minimax/minimax-m3`	21	`nvidia/nemotron-3-ultra-550b-a55b`	9
MiniMax: MiniMax M3 vs Qwen: Qwen3.5-9B	`minimax/minimax-m3`	21	`qwen/qwen3.5-9b`	10
MiniMax: MiniMax M3 vs Z.ai: GLM 4.6	`minimax/minimax-m3`	21	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs MiniMax: MiniMax M3	`deepseek/deepseek-v3.1`	7	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs Xiaomi: MiMo-V2.5-Pro	`minimax/minimax-m3`	21	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs MiniMax: MiniMax M3	`deepseek/deepseek-v4-pro-0423`	4	`minimax/minimax-m3`	21
Google: Gemini 2.5 Pro vs MiniMax: MiniMax M3	`google/gemini-2.5-pro`	6	`minimax/minimax-m3`	21
Google: Gemini 3 Flash Preview vs MiniMax: MiniMax M3	`google/gemini-3-flash-preview`	6	`minimax/minimax-m3`	21
Google: Gemini 3.1 Flash Lite vs MiniMax: MiniMax M3	`google/gemini-3.1-flash-lite`	6	`minimax/minimax-m3`	21
Google: Gemini 3.1 Pro Preview vs MiniMax: MiniMax M3	`google/gemini-3.1-pro-preview`	7	`minimax/minimax-m3`	21
Google: Gemini 3.5 Flash vs MiniMax: MiniMax M3	`google/gemini-3.5-flash`	7	`minimax/minimax-m3`	21
MiniMax: MiniMax M3 vs Qwen3.7 Max	`minimax/minimax-m3`	21	`qwen/qwen3.7-max`	7
MiniMax: MiniMax M3 vs Qwen3.8 Max	`minimax/minimax-m3`	21	`qwen/qwen3.8-max`	8
MiniMax: MiniMax M3 vs Thinking Machines: Inkling	`minimax/minimax-m3`	21	`thinkingmachines/inkling`	7
MiniMax: MiniMax M3 vs Thinking Machines: Inkling Small	`minimax/minimax-m3`	21	`thinkingmachines/inkling-small`	7
MiniMax: MiniMax M3 vs NVIDIA: Nemotron 3 Super	`minimax/minimax-m3`	21	`nvidia/nemotron-3-super-120b-a12b`	7
MiniMax: MiniMax M3 vs Qwen: Qwen3 Coder Next	`minimax/minimax-m3`	21	`qwen/qwen3-coder-next`	7
MiniMax: MiniMax M3 vs Qwen: Qwen3 VL 235B A22B Instruct	`minimax/minimax-m3`	21	`qwen/qwen3-vl-235b-a22b-instruct`	7
MiniMax: MiniMax M3 vs Qwen: Qwen3.5-27B	`minimax/minimax-m3`	21	`qwen/qwen3.5-27b`	6
MiniMax: MiniMax M3 vs Qwen: Qwen3.8 2.4T A95B	`minimax/minimax-m3`	21	`qwen/qwen3.8-2.4t-a95b`	8
MiniMax: MiniMax M3 vs Tencent: Hy3	`minimax/minimax-m3`	21	`tencent/hy3`	8
Google: Gemma 3 27B vs MiniMax: MiniMax M3	`google/gemma-3-27b-it`	8	`minimax/minimax-m3`	21