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
DeepSeek: DeepSeek V3.2 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v3.2`	15	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 4 26B A4B vs Z.ai: GLM 5	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-5`	12
Google: Gemma 4 26B A4B vs Qwen: Qwen3.5-9B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.5-9b`	12
Google: Gemma 4 26B A4B vs Z.ai: GLM 4.7	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-4.7`	10
Google: Gemma 4 26B A4B vs Qwen: Qwen3.8 2.4T A95B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.8-2.4t-a95b`	9
Google: Gemma 4 26B A4B vs Qwen: Qwen3.5-122B-A10B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.5-122b-a10b`	10
Google: Gemma 4 26B A4B vs MiniMax: MiniMax M2.5	`google/gemma-4-26b-a4b-it`	16	`minimax/minimax-m2.5`	9
Google: Gemma 3 27B vs Google: Gemma 4 26B A4B	`google/gemma-3-27b-it`	10	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 4 26B A4B vs Z.ai: GLM 4.7 Flash	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-4.7-flash`	7
Google: Gemma 4 26B A4B vs Xiaomi: MiMo-V2.6-Flash	`google/gemma-4-26b-a4b-it`	16	`xiaomi/mimo-v2.6-flash`	9
Google: Gemma 4 26B A4B vs NVIDIA: Nemotron 3 Super	`google/gemma-4-26b-a4b-it`	16	`nvidia/nemotron-3-super-120b-a12b`	8
Google: Gemma 4 26B A4B vs NVIDIA: Nemotron 3 Ultra	`google/gemma-4-26b-a4b-it`	16	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemma 4 26B A4B vs Qwen/Qwen3-235B-A22B-Instruct-2507	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3-235b-a22b-instruct-2507`	7
Google: Gemma 4 26B A4B vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3-next-80b-a3b-instruct`	8
Google: Gemma 4 26B A4B vs Qwen: Qwen3.5-27B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.5-27b`	7
Google: Gemma 4 26B A4B vs Qwen: Qwen3.5-35B-A3B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.5-35b-a3b`	9
Google: Gemma 4 26B A4B vs Z.ai: GLM 4.6	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-4.6`	8
deepseek-ai/DeepSeek-V3.1 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v3.1`	6	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 3 12B vs Google: Gemma 4 26B A4B	`google/gemma-3-12b-it`	7	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 4 26B A4B vs Meta: Llama 3.1 8B Instruct	`google/gemma-4-26b-a4b-it`	16	`meta-llama/llama-3.1-8b-instruct`	7
Google: Gemma 4 26B A4B vs Qwen: Qwen3 14B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3-14b`	6
Google: Gemma 4 26B A4B vs Xiaomi: MiMo-V2.6-Pro	`google/gemma-4-26b-a4b-it`	16	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v4-pro-0423`	4	`google/gemma-4-26b-a4b-it`	16
Google: Gemini 2.5 Flash vs Google: Gemma 4 26B A4B	`google/gemini-2.5-flash`	6	`google/gemma-4-26b-a4b-it`	16
Google: Gemini 3.1 Flash Lite vs Google: Gemma 4 26B A4B	`google/gemini-3.1-flash-lite`	6	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 4 26B A4B vs Xiaomi: MiMo-V2.5	`google/gemma-4-26b-a4b-it`	16	`xiaomi/mimo-v2.5`	5
Google: Gemma 4 26B A4B vs Qwen3.7 Max	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.7-max`	7
Google: Gemma 4 26B A4B vs Qwen3.8 Max	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.8-max`	8
Google: Gemma 4 26B A4B vs Tencent: Hy4 preview	`google/gemma-4-26b-a4b-it`	16	`tencent/hy4-preview`	8
Google: Gemma 4 26B A4B vs Tencent: Hy3	`google/gemma-4-26b-a4b-it`	16	`tencent/hy3`	8
Google: Gemma 4 26B A4B vs MiniMax: MiniMax M2.7	`google/gemma-4-26b-a4b-it`	16	`minimax/minimax-m2.7`	7
Google: Gemma 4 26B A4B vs Qwen: Qwen3 32B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3-32b`	5
Google: Gemma 4 26B A4B vs OpenAI: GPT-5.6 Luna	`google/gemma-4-26b-a4b-it`	16	`openai/gpt-5.6-luna`	4
Google: Gemma 4 26B A4B vs OpenAI: GPT-5.6 Sol	`google/gemma-4-26b-a4b-it`	16	`openai/gpt-5.6-sol`	5
DeepSeek: DeepSeek V4 Flash Vision Exp vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v4-flash-vision-exp`	6	`google/gemma-4-26b-a4b-it`	16
Google: Gemini 2.5 Pro vs Google: Gemma 4 26B A4B	`google/gemini-2.5-pro`	4	`google/gemma-4-26b-a4b-it`	16
Google: Gemini 3.1 Pro Preview vs Google: Gemma 4 26B A4B	`google/gemini-3.1-pro-preview`	5	`google/gemma-4-26b-a4b-it`	16
Google: Gemini 3.8 Flash vs Google: Gemma 4 26B A4B	`google/gemini-3.8-flash`	5	`google/gemma-4-26b-a4b-it`	16
Google: Gemma 4 26B A4B vs stepfun-ai/Step-5-Preview	`google/gemma-4-26b-a4b-it`	16	`stepfun-ai/step-5-preview`	5
Google: Gemma 4 26B A4B vs Xiaomi: MiMo-V2.5-Pro	`google/gemma-4-26b-a4b-it`	16	`xiaomi/mimo-v2.5-pro`	5
Google: Gemma 4 26B A4B vs Qwen3.8 Flash	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.8-flash`	6
Google: Gemma 4 26B A4B vs Thinking Machines: Inkling	`google/gemma-4-26b-a4b-it`	16	`thinkingmachines/inkling`	5
Google: Gemma 4 26B A4B vs MoonshotAI: Kimi K2 Thinking	`google/gemma-4-26b-a4b-it`	16	`moonshotai/kimi-k2-thinking`	5
Google: Gemma 4 26B A4B vs NVIDIA: Nemotron 3 Nano 30B A3B	`google/gemma-4-26b-a4b-it`	16	`nvidia/nemotron-3-nano-30b-a3b`	5
Google: Gemma 4 26B A4B vs NVIDIA: Nemotron 3.5 Lightning	`google/gemma-4-26b-a4b-it`	16	`nvidia/nemotron-3.5-lightning`	5
Google: Gemma 4 26B A4B vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`google/gemma-4-26b-a4b-it`	16	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
Google: Gemma 4 26B A4B vs Qwen: Qwen3 Coder Next	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3-coder-next`	4
Google: Gemma 4 26B A4B vs Qwen: Qwen3.8-Flash-Next	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.8-flash-next`	3
Google: Gemma 4 26B A4B vs Z.ai: GLM 5V Turbo	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-r1-0528`	6	`google/gemma-4-26b-a4b-it`	16
Meta: Llama 3.3 70B Instruct vs MoonshotAI: Kimi K2.5	`meta-llama/llama-3.3-70b-instruct`	14	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.6 27B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v3.2`	15	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 5	`moonshotai/kimi-k2.5`	14	`z-ai/glm-5`	12
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.5-9B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.5-9b`	12
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 4.7	`moonshotai/kimi-k2.5`	14	`z-ai/glm-4.7`	10
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.8 2.4T A95B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.8-2.4t-a95b`	9
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.5-122B-A10B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.5-122b-a10b`	10
MiniMax: MiniMax M2.5 vs MoonshotAI: Kimi K2.5	`minimax/minimax-m2.5`	9	`moonshotai/kimi-k2.5`	14
Google: Gemma 3 27B vs MoonshotAI: Kimi K2.5	`google/gemma-3-27b-it`	10	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 4.7 Flash	`moonshotai/kimi-k2.5`	14	`z-ai/glm-4.7-flash`	7
MoonshotAI: Kimi K2.5 vs Xiaomi: MiMo-V2.6-Flash	`moonshotai/kimi-k2.5`	14	`xiaomi/mimo-v2.6-flash`	9
MoonshotAI: Kimi K2.5 vs NVIDIA: Nemotron 3 Super	`moonshotai/kimi-k2.5`	14	`nvidia/nemotron-3-super-120b-a12b`	8
MoonshotAI: Kimi K2.5 vs NVIDIA: Nemotron 3 Ultra	`moonshotai/kimi-k2.5`	14	`nvidia/nemotron-3-ultra-550b-a55b`	9
MoonshotAI: Kimi K2.5 vs Qwen/Qwen3-235B-A22B-Instruct-2507	`moonshotai/kimi-k2.5`	14	`qwen/qwen3-235b-a22b-instruct-2507`	7
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3 Next 80B A3B Instruct	`moonshotai/kimi-k2.5`	14	`qwen/qwen3-next-80b-a3b-instruct`	8
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.5-27B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.5-27b`	7
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.5-35B-A3B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.5-35b-a3b`	9
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 4.6	`moonshotai/kimi-k2.5`	14	`z-ai/glm-4.6`	8
deepseek-ai/DeepSeek-V3.1 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v3.1`	6	`moonshotai/kimi-k2.5`	14
Google: Gemma 3 12B vs MoonshotAI: Kimi K2.5	`google/gemma-3-12b-it`	7	`moonshotai/kimi-k2.5`	14
Meta: Llama 3.1 8B Instruct vs MoonshotAI: Kimi K2.5	`meta-llama/llama-3.1-8b-instruct`	7	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3 14B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3-14b`	6
MoonshotAI: Kimi K2.5 vs Xiaomi: MiMo-V2.6-Pro	`moonshotai/kimi-k2.5`	14	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v4-pro-0423`	4	`moonshotai/kimi-k2.5`	14
Google: Gemini 2.5 Flash vs MoonshotAI: Kimi K2.5	`google/gemini-2.5-flash`	6	`moonshotai/kimi-k2.5`	14
Google: Gemini 3.1 Flash Lite vs MoonshotAI: Kimi K2.5	`google/gemini-3.1-flash-lite`	6	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Xiaomi: MiMo-V2.5	`moonshotai/kimi-k2.5`	14	`xiaomi/mimo-v2.5`	5
MoonshotAI: Kimi K2.5 vs Qwen3.7 Max	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.7-max`	7
MoonshotAI: Kimi K2.5 vs Qwen3.8 Max	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.8-max`	8
MoonshotAI: Kimi K2.5 vs Tencent: Hy4 preview	`moonshotai/kimi-k2.5`	14	`tencent/hy4-preview`	8
MoonshotAI: Kimi K2.5 vs Tencent: Hy3	`moonshotai/kimi-k2.5`	14	`tencent/hy3`	8
MiniMax: MiniMax M2.7 vs MoonshotAI: Kimi K2.5	`minimax/minimax-m2.7`	7	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3 32B	`moonshotai/kimi-k2.5`	14	`qwen/qwen3-32b`	5
MoonshotAI: Kimi K2.5 vs OpenAI: GPT-5.6 Luna	`moonshotai/kimi-k2.5`	14	`openai/gpt-5.6-luna`	4
MoonshotAI: Kimi K2.5 vs OpenAI: GPT-5.6 Sol	`moonshotai/kimi-k2.5`	14	`openai/gpt-5.6-sol`	5
DeepSeek: DeepSeek V4 Flash Vision Exp vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v4-flash-vision-exp`	6	`moonshotai/kimi-k2.5`	14
Google: Gemini 2.5 Pro vs MoonshotAI: Kimi K2.5	`google/gemini-2.5-pro`	4	`moonshotai/kimi-k2.5`	14
Google: Gemini 3.1 Pro Preview vs MoonshotAI: Kimi K2.5	`google/gemini-3.1-pro-preview`	5	`moonshotai/kimi-k2.5`	14
Google: Gemini 3.8 Flash vs MoonshotAI: Kimi K2.5	`google/gemini-3.8-flash`	5	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs stepfun-ai/Step-5-Preview	`moonshotai/kimi-k2.5`	14	`stepfun-ai/step-5-preview`	5
MoonshotAI: Kimi K2.5 vs Xiaomi: MiMo-V2.5-Pro	`moonshotai/kimi-k2.5`	14	`xiaomi/mimo-v2.5-pro`	5
MoonshotAI: Kimi K2.5 vs Qwen3.8 Flash	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.8-flash`	6
MoonshotAI: Kimi K2.5 vs Thinking Machines: Inkling	`moonshotai/kimi-k2.5`	14	`thinkingmachines/inkling`	5
MoonshotAI: Kimi K2 Thinking vs MoonshotAI: Kimi K2.5	`moonshotai/kimi-k2-thinking`	5	`moonshotai/kimi-k2.5`	14
MoonshotAI: Kimi K2.5 vs NVIDIA: Nemotron 3 Nano 30B A3B	`moonshotai/kimi-k2.5`	14	`nvidia/nemotron-3-nano-30b-a3b`	5
MoonshotAI: Kimi K2.5 vs NVIDIA: Nemotron 3.5 Lightning	`moonshotai/kimi-k2.5`	14	`nvidia/nemotron-3.5-lightning`	5
MoonshotAI: Kimi K2.5 vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`moonshotai/kimi-k2.5`	14	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3 Coder Next	`moonshotai/kimi-k2.5`	14	`qwen/qwen3-coder-next`	4
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.8-Flash-Next	`moonshotai/kimi-k2.5`	14	`qwen/qwen3.8-flash-next`	3