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 V4 Pro 0423 vs NVIDIA: Nemotron 3 Nano 30B A3B	`deepseek/deepseek-v4-pro`	26	`nvidia/nemotron-3-nano-30b-a3b`	6
DeepSeek: DeepSeek V4 Pro 0423 vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`deepseek/deepseek-v4-pro`	26	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3 Max	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-max`	5
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3 VL 30B A3B Instruct	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-vl-30b-a3b-instruct`	5
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3 VL 8B Instruct	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-vl-8b-instruct`	4
DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5V Turbo	`deepseek/deepseek-v4-pro`	26	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs DeepSeek: DeepSeek V4 Pro 0423	`deepseek/deepseek-r1-0528`	6	`deepseek/deepseek-v4-pro`	26
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3 Coder 30B A3B Instruct	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-coder-30b-a3b-instruct`	4
DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemma 3 12B	`deepseek/deepseek-v4-pro`	26	`google/gemma-3-12b-it`	5
DeepSeek: DeepSeek V4 Pro 0423 vs Meta: Llama 3.1 70B Instruct	`deepseek/deepseek-v4-pro`	26	`meta-llama/llama-3.1-70b-instruct`	5
DeepSeek: DeepSeek V4 Pro 0423 vs Llama 4 Scout Instruct	`deepseek/deepseek-v4-pro`	26	`meta-llama/llama-4-scout-17b-16e-instruct`	5
DeepSeek: DeepSeek V4 Pro 0423 vs Muse Glimmer 30B on Fireworks	`deepseek/deepseek-v4-pro`	26	`meta-models/muse-glimmer-30b`	6
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 31B	`deepseek/deepseek-v4.1-flash`	23	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.7 Code	`google/gemma-4-31b-it`	25	`moonshotai/kimi-k2.7-code`	19
Google: Gemma 4 31B vs Qwen: Qwen3.8 27B	`google/gemma-4-31b-it`	25	`qwen/qwen3.8-27b`	19
Google: Gemma 4 31B vs MiniMax: MiniMax M3	`google/gemma-4-31b-it`	25	`minimax/minimax-m3`	21
Google: Gemma 4 31B vs Qwen: Qwen3.6 35B A3B	`google/gemma-4-31b-it`	25	`qwen/qwen3.6-35b-a3b`	17
Google: Gemma 4 31B vs Z.ai: GLM 5.1	`google/gemma-4-31b-it`	25	`z-ai/glm-5.1`	20
Google: Gemma 4 31B vs Meta: Llama 3.3 70B Instruct	`google/gemma-4-31b-it`	25	`meta-llama/llama-3.3-70b-instruct`	18
Google: Gemma 4 31B vs OpenAI: gpt-oss-20b	`google/gemma-4-31b-it`	25	`openai/gpt-oss-20b`	18
Google: Gemma 4 31B vs Qwen: Qwen3.5 397B A17B	`google/gemma-4-31b-it`	25	`qwen/qwen3.5-397b-a17b`	17
Google: Gemma 4 26B A4B vs Google: Gemma 4 31B	`google/gemma-4-26b-a4b-it`	15	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Qwen: Qwen3.6 27B	`google/gemma-4-31b-it`	25	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs Google: Gemma 4 31B	`deepseek/deepseek-v3.2`	16	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.5	`google/gemma-4-31b-it`	25	`moonshotai/kimi-k2.5`	12
Google: Gemma 4 31B vs Qwen: Qwen3.5-122B-A10B	`google/gemma-4-31b-it`	25	`qwen/qwen3.5-122b-a10b`	12
Google: Gemma 4 31B vs Z.ai: GLM 4.7	`google/gemma-4-31b-it`	25	`z-ai/glm-4.7`	11
Google: Gemma 4 31B vs MiniMax: MiniMax M2.5	`google/gemma-4-31b-it`	25	`minimax/minimax-m2.5`	13
Google: Gemma 4 31B vs MiniMax: MiniMax M2.7	`google/gemma-4-31b-it`	25	`minimax/minimax-m2.7`	11
Google: Gemma 4 31B vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemma-4-31b-it`	25	`qwen/qwen3-next-80b-a3b-instruct`	10
Google: Gemma 4 31B vs Qwen: Qwen3.5-35B-A3B	`google/gemma-4-31b-it`	25	`qwen/qwen3.5-35b-a3b`	10
Google: Gemma 4 31B vs Z.ai: GLM 5	`google/gemma-4-31b-it`	25	`z-ai/glm-5`	10
Google: Gemma 4 31B vs Qwen3 235B A22B Instruct 2507	`google/gemma-4-31b-it`	25	`qwen/qwen3-235b-a22b-instruct-2507`	9
Google: Gemma 4 31B vs Xiaomi: MiMo-V2.5	`google/gemma-4-31b-it`	25	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs Google: Gemma 4 31B	`deepseek/deepseek-v4-flash-vision-exp`	10	`google/gemma-4-31b-it`	25
Google: Gemini 2.5 Flash vs Google: Gemma 4 31B	`google/gemini-2.5-flash`	8	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs NVIDIA: Nemotron 3 Ultra	`google/gemma-4-31b-it`	25	`nvidia/nemotron-3-ultra-550b-a55b`	9
Google: Gemma 4 31B vs Qwen: Qwen3.5-9B	`google/gemma-4-31b-it`	25	`qwen/qwen3.5-9b`	10
Google: Gemma 4 31B vs Z.ai: GLM 4.6	`google/gemma-4-31b-it`	25	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs Google: Gemma 4 31B	`deepseek/deepseek-v3.1`	7	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Xiaomi: MiMo-V2.5-Pro	`google/gemma-4-31b-it`	25	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs Google: Gemma 4 31B	`deepseek/deepseek-v4-pro-0423`	4	`google/gemma-4-31b-it`	25
Google: Gemini 2.5 Pro vs Google: Gemma 4 31B	`google/gemini-2.5-pro`	6	`google/gemma-4-31b-it`	25
Google: Gemini 3 Flash Preview vs Google: Gemma 4 31B	`google/gemini-3-flash-preview`	6	`google/gemma-4-31b-it`	25
Google: Gemini 3.1 Flash Lite vs Google: Gemma 4 31B	`google/gemini-3.1-flash-lite`	6	`google/gemma-4-31b-it`	25
Google: Gemini 3.1 Pro Preview vs Google: Gemma 4 31B	`google/gemini-3.1-pro-preview`	7	`google/gemma-4-31b-it`	25
Google: Gemini 3.5 Flash vs Google: Gemma 4 31B	`google/gemini-3.5-flash`	7	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Qwen3.7 Max	`google/gemma-4-31b-it`	25	`qwen/qwen3.7-max`	7
Google: Gemma 4 31B vs Qwen3.8 Max	`google/gemma-4-31b-it`	25	`qwen/qwen3.8-max`	8
Google: Gemma 4 31B vs Thinking Machines: Inkling	`google/gemma-4-31b-it`	25	`thinkingmachines/inkling`	7
Google: Gemma 4 31B vs Thinking Machines: Inkling Small	`google/gemma-4-31b-it`	25	`thinkingmachines/inkling-small`	7
Google: Gemma 4 31B vs NVIDIA: Nemotron 3 Super	`google/gemma-4-31b-it`	25	`nvidia/nemotron-3-super-120b-a12b`	7
Google: Gemma 4 31B vs Qwen: Qwen3 Coder Next	`google/gemma-4-31b-it`	25	`qwen/qwen3-coder-next`	7
Google: Gemma 4 31B vs Qwen: Qwen3 VL 235B A22B Instruct	`google/gemma-4-31b-it`	25	`qwen/qwen3-vl-235b-a22b-instruct`	7
Google: Gemma 4 31B vs Qwen: Qwen3.5-27B	`google/gemma-4-31b-it`	25	`qwen/qwen3.5-27b`	6
Google: Gemma 4 31B vs Qwen: Qwen3.8 2.4T A95B	`google/gemma-4-31b-it`	25	`qwen/qwen3.8-2.4t-a95b`	8
Google: Gemma 4 31B vs Tencent: Hy3	`google/gemma-4-31b-it`	25	`tencent/hy3`	8
Google: Gemma 3 27B vs Google: Gemma 4 31B	`google/gemma-3-27b-it`	8	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Meta: Llama 3.1 8B Instruct	`google/gemma-4-31b-it`	25	`meta-llama/llama-3.1-8b-instruct`	6
Google: Gemma 4 31B vs Qwen: Qwen3 235B A22B Thinking 2507	`google/gemma-4-31b-it`	25	`qwen/qwen3-235b-a22b-thinking-2507`	7
Google: Gemma 4 31B vs OpenAI: GPT-5.6 Terra	`google/gemma-4-31b-it`	25	`openai/gpt-5.6-terra`	6
Google: Gemma 4 31B vs OpenAI: GPT-6 Astra	`google/gemma-4-31b-it`	25	`openai/gpt-6-astra`	6
Google: Gemma 4 31B vs Llama 4 Maverick Instruct	`google/gemma-4-31b-it`	25	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5
Google: Gemma 4 31B vs NVIDIA: Nemotron 3 Nano 30B A3B	`google/gemma-4-31b-it`	25	`nvidia/nemotron-3-nano-30b-a3b`	6
Google: Gemma 4 31B vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`google/gemma-4-31b-it`	25	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
Google: Gemma 4 31B vs Qwen3 Max	`google/gemma-4-31b-it`	25	`qwen/qwen3-max`	5
Google: Gemma 4 31B vs Qwen: Qwen3 VL 30B A3B Instruct	`google/gemma-4-31b-it`	25	`qwen/qwen3-vl-30b-a3b-instruct`	5
Google: Gemma 4 31B vs Qwen: Qwen3 VL 8B Instruct	`google/gemma-4-31b-it`	25	`qwen/qwen3-vl-8b-instruct`	4
Google: Gemma 4 31B vs Z.ai: GLM 5V Turbo	`google/gemma-4-31b-it`	25	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Google: Gemma 4 31B	`deepseek/deepseek-r1-0528`	6	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Qwen: Qwen3 Coder 30B A3B Instruct	`google/gemma-4-31b-it`	25	`qwen/qwen3-coder-30b-a3b-instruct`	4
Google: Gemma 3 12B vs Google: Gemma 4 31B	`google/gemma-3-12b-it`	5	`google/gemma-4-31b-it`	25
Google: Gemma 4 31B vs Meta: Llama 3.1 70B Instruct	`google/gemma-4-31b-it`	25	`meta-llama/llama-3.1-70b-instruct`	5
Google: Gemma 4 31B vs Llama 4 Scout Instruct	`google/gemma-4-31b-it`	25	`meta-llama/llama-4-scout-17b-16e-instruct`	5
Google: Gemma 4 31B vs Muse Glimmer 30B on Fireworks	`google/gemma-4-31b-it`	25	`meta-models/muse-glimmer-30b`	6
DeepSeek: DeepSeek V4.1 Flash vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4.1-flash`	23	`moonshotai/kimi-k2.7-code`	19
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.8-27b`	19
DeepSeek: DeepSeek V4.1 Flash vs MiniMax: MiniMax M3	`deepseek/deepseek-v4.1-flash`	23	`minimax/minimax-m3`	21
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.6-35b-a3b`	17
DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5.1	`deepseek/deepseek-v4.1-flash`	23	`z-ai/glm-5.1`	20
DeepSeek: DeepSeek V4.1 Flash vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v4.1-flash`	23	`meta-llama/llama-3.3-70b-instruct`	18
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v4.1-flash`	23	`openai/gpt-oss-20b`	18
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.5 397B A17B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.5-397b-a17b`	17
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v4.1-flash`	23	`google/gemma-4-26b-a4b-it`	15
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v3.2`	16	`deepseek/deepseek-v4.1-flash`	23
DeepSeek: DeepSeek V4.1 Flash vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v4.1-flash`	23	`moonshotai/kimi-k2.5`	12
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.5-122B-A10B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.5-122b-a10b`	12
DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 4.7	`deepseek/deepseek-v4.1-flash`	23	`z-ai/glm-4.7`	11
DeepSeek: DeepSeek V4.1 Flash vs MiniMax: MiniMax M2.5	`deepseek/deepseek-v4.1-flash`	23	`minimax/minimax-m2.5`	13
DeepSeek: DeepSeek V4.1 Flash vs MiniMax: MiniMax M2.7	`deepseek/deepseek-v4.1-flash`	23	`minimax/minimax-m2.7`	11
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3 Next 80B A3B Instruct	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3-next-80b-a3b-instruct`	10
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.5-35b-a3b`	10
DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5	`deepseek/deepseek-v4.1-flash`	23	`z-ai/glm-5`	10
DeepSeek: DeepSeek V4.1 Flash vs Qwen3 235B A22B Instruct 2507	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3-235b-a22b-instruct-2507`	9
DeepSeek: DeepSeek V4.1 Flash vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v4.1-flash`	23	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v4-flash-vision-exp`	10	`deepseek/deepseek-v4.1-flash`	23
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v4.1-flash`	23	`google/gemini-2.5-flash`	8
DeepSeek: DeepSeek V4.1 Flash vs NVIDIA: Nemotron 3 Ultra	`deepseek/deepseek-v4.1-flash`	23	`nvidia/nemotron-3-ultra-550b-a55b`	9
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.5-9B	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3.5-9b`	10