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
Llama 4 Maverick Instruct vs Z.ai: GLM 5.3 Flash	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`z-ai/glm-5.3-flash`	41
NVIDIA: Nemotron 3 Nano 30B A3B vs Z.ai: GLM 5.3 Flash	`nvidia/nemotron-3-nano-30b-a3b`	6	`z-ai/glm-5.3-flash`	41
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Z.ai: GLM 5.3 Flash	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`z-ai/glm-5.3-flash`	41
Qwen3 Max vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-max`	5	`z-ai/glm-5.3-flash`	41
Qwen: Qwen3 VL 30B A3B Instruct vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-30b-a3b-instruct`	5	`z-ai/glm-5.3-flash`	41
Qwen: Qwen3 VL 8B Instruct vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-8b-instruct`	4	`z-ai/glm-5.3-flash`	41
Z.ai: GLM 5.3 Flash vs Z.ai: GLM 5V Turbo	`z-ai/glm-5.3-flash`	41	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Z.ai: GLM 5.3 Flash	`deepseek/deepseek-r1-0528`	6	`z-ai/glm-5.3-flash`	41
Qwen: Qwen3 Coder 30B A3B Instruct vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-coder-30b-a3b-instruct`	4	`z-ai/glm-5.3-flash`	41
Google: Gemma 3 12B vs Z.ai: GLM 5.3 Flash	`google/gemma-3-12b-it`	5	`z-ai/glm-5.3-flash`	41
Meta: Llama 3.1 70B Instruct vs Z.ai: GLM 5.3 Flash	`meta-llama/llama-3.1-70b-instruct`	5	`z-ai/glm-5.3-flash`	41
Llama 4 Scout Instruct vs Z.ai: GLM 5.3 Flash	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`z-ai/glm-5.3-flash`	41
Muse Glimmer 30B on Fireworks vs Z.ai: GLM 5.3 Flash	`meta-models/muse-glimmer-30b`	6	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4-flash-0731`	33	`moonshotai/kimi-k3`	39
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-oss-120b`	36
DeepSeek: DeepSeek V4 Flash 0731 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-flash-0731`	33	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-v4-flash`	25	`deepseek/deepseek-v4-flash-0731`	33
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4 Pro 0423	`deepseek/deepseek-v4-flash-0731`	33	`deepseek/deepseek-v4-pro`	26
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B	`deepseek/deepseek-v4-flash-0731`	33	`google/gemma-4-31b-it`	25
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v4-flash-0731`	33	`deepseek/deepseek-v4.1-flash`	23
DeepSeek: DeepSeek V4 Flash 0731 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-flash-0731`	33	`moonshotai/kimi-k2.7-code`	19
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.8-27b`	19
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax: MiniMax M3	`deepseek/deepseek-v4-flash-0731`	33	`minimax/minimax-m3`	21
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.6-35b-a3b`	17
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 5.1	`deepseek/deepseek-v4-flash-0731`	33	`z-ai/glm-5.1`	20
DeepSeek: DeepSeek V4 Flash 0731 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-3.3-70b-instruct`	18
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-oss-20b`	18
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5 397B A17B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.5-397b-a17b`	17
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v4-flash-0731`	33	`google/gemma-4-26b-a4b-it`	15
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-v3.2`	16	`deepseek/deepseek-v4-flash-0731`	33
DeepSeek: DeepSeek V4 Flash 0731 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v4-flash-0731`	33	`moonshotai/kimi-k2.5`	12
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5-122B-A10B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.5-122b-a10b`	12
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 4.7	`deepseek/deepseek-v4-flash-0731`	33	`z-ai/glm-4.7`	11
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax: MiniMax M2.5	`deepseek/deepseek-v4-flash-0731`	33	`minimax/minimax-m2.5`	13
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax: MiniMax M2.7	`deepseek/deepseek-v4-flash-0731`	33	`minimax/minimax-m2.7`	11
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 Next 80B A3B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-next-80b-a3b-instruct`	10
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5-35B-A3B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.5-35b-a3b`	10
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 5	`deepseek/deepseek-v4-flash-0731`	33	`z-ai/glm-5`	10
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 235B A22B Instruct 2507	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-235b-a22b-instruct-2507`	9
DeepSeek: DeepSeek V4 Flash 0731 vs Xiaomi: MiMo-V2.5	`deepseek/deepseek-v4-flash-0731`	33	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4 Flash Vision Exp	`deepseek/deepseek-v4-flash-0731`	33	`deepseek/deepseek-v4-flash-vision-exp`	10
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-2.5-flash`	8
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3 Ultra	`deepseek/deepseek-v4-flash-0731`	33	`nvidia/nemotron-3-ultra-550b-a55b`	9
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5-9B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.5-9b`	10
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 4.6	`deepseek/deepseek-v4-flash-0731`	33	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-v3.1`	7	`deepseek/deepseek-v4-flash-0731`	33
DeepSeek: DeepSeek V4 Flash 0731 vs Xiaomi: MiMo-V2.5-Pro	`deepseek/deepseek-v4-flash-0731`	33	`xiaomi/mimo-v2.5-pro`	8
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek V4 Pro 0423	`deepseek/deepseek-v4-flash-0731`	33	`deepseek/deepseek-v4-pro-0423`	4
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 2.5 Pro	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-2.5-pro`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3 Flash Preview	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-3-flash-preview`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.1 Flash Lite	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-3.1-flash-lite`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.1 Pro Preview	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-3.1-pro-preview`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.5 Flash	`deepseek/deepseek-v4-flash-0731`	33	`google/gemini-3.5-flash`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.7 Max	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.7-max`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.8 Max	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.8-max`	8
DeepSeek: DeepSeek V4 Flash 0731 vs Thinking Machines: Inkling	`deepseek/deepseek-v4-flash-0731`	33	`thinkingmachines/inkling`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Thinking Machines: Inkling Small	`deepseek/deepseek-v4-flash-0731`	33	`thinkingmachines/inkling-small`	7
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3 Super	`deepseek/deepseek-v4-flash-0731`	33	`nvidia/nemotron-3-super-120b-a12b`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 Coder Next	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-coder-next`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 VL 235B A22B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-vl-235b-a22b-instruct`	7
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5-27B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.5-27b`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.8 2.4T A95B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.8-2.4t-a95b`	8
DeepSeek: DeepSeek V4 Flash 0731 vs Tencent: Hy3	`deepseek/deepseek-v4-flash-0731`	33	`tencent/hy3`	8
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 3 27B	`deepseek/deepseek-v4-flash-0731`	33	`google/gemma-3-27b-it`	8
DeepSeek: DeepSeek V4 Flash 0731 vs Meta: Llama 3.1 8B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-3.1-8b-instruct`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 235B A22B Thinking 2507	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-235b-a22b-thinking-2507`	7
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-5.6 Terra	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-5.6-terra`	6
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-6 Astra	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-6-astra`	6
DeepSeek: DeepSeek V4 Flash 0731 vs Llama 4 Maverick Instruct	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3 Nano 30B A3B	`deepseek/deepseek-v4-flash-0731`	33	`nvidia/nemotron-3-nano-30b-a3b`	6
DeepSeek: DeepSeek V4 Flash 0731 vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`deepseek/deepseek-v4-flash-0731`	33	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 Max	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-max`	5
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 VL 30B A3B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-vl-30b-a3b-instruct`	5
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 VL 8B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-vl-8b-instruct`	4
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 5V Turbo	`deepseek/deepseek-v4-flash-0731`	33	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-r1-0528`	6	`deepseek/deepseek-v4-flash-0731`	33
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 Coder 30B A3B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-coder-30b-a3b-instruct`	4
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 3 12B	`deepseek/deepseek-v4-flash-0731`	33	`google/gemma-3-12b-it`	5
DeepSeek: DeepSeek V4 Flash 0731 vs Meta: Llama 3.1 70B Instruct	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-3.1-70b-instruct`	5
DeepSeek: DeepSeek V4 Flash 0731 vs Llama 4 Scout Instruct	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-4-scout-17b-16e-instruct`	5
DeepSeek: DeepSeek V4 Flash 0731 vs Muse Glimmer 30B on Fireworks	`deepseek/deepseek-v4-flash-0731`	33	`meta-models/muse-glimmer-30b`	6
MoonshotAI: Kimi K3 vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k3`	39	`openai/gpt-oss-120b`	36
MoonshotAI: Kimi K2.6 vs MoonshotAI: Kimi K3	`moonshotai/kimi-k2.6`	33	`moonshotai/kimi-k3`	39
DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4-flash`	25	`moonshotai/kimi-k3`	39
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4-pro`	26	`moonshotai/kimi-k3`	39
Google: Gemma 4 31B vs MoonshotAI: Kimi K3	`google/gemma-4-31b-it`	25	`moonshotai/kimi-k3`	39
DeepSeek: DeepSeek V4.1 Flash vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4.1-flash`	23	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K2.7 Code vs MoonshotAI: Kimi K3	`moonshotai/kimi-k2.7-code`	19	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K3 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k3`	39	`qwen/qwen3.8-27b`	19
MiniMax: MiniMax M3 vs MoonshotAI: Kimi K3	`minimax/minimax-m3`	21	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K3 vs Qwen: Qwen3.6 35B A3B	`moonshotai/kimi-k3`	39	`qwen/qwen3.6-35b-a3b`	17
MoonshotAI: Kimi K3 vs Z.ai: GLM 5.1	`moonshotai/kimi-k3`	39	`z-ai/glm-5.1`	20
Meta: Llama 3.3 70B Instruct vs MoonshotAI: Kimi K3	`meta-llama/llama-3.3-70b-instruct`	18	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K3 vs OpenAI: gpt-oss-20b	`moonshotai/kimi-k3`	39	`openai/gpt-oss-20b`	18
MoonshotAI: Kimi K3 vs Qwen: Qwen3.5 397B A17B	`moonshotai/kimi-k3`	39	`qwen/qwen3.5-397b-a17b`	17
Google: Gemma 4 26B A4B vs MoonshotAI: Kimi K3	`google/gemma-4-26b-a4b-it`	15	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K3 vs Qwen: Qwen3.6 27B	`moonshotai/kimi-k3`	39	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v3.2`	16	`moonshotai/kimi-k3`	39
MoonshotAI: Kimi K2.5 vs MoonshotAI: Kimi K3	`moonshotai/kimi-k2.5`	12	`moonshotai/kimi-k3`	39