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
Claude Opus 4 20250514 Coding vs Z.ai: GLM 5.2	`anthropic/claude-opus-4-20250514-coding`	0	`z-ai/glm-5.2`	50
Claude Opus 4.1 20250805 vs Z.ai: GLM 5.3	`anthropic/claude-opus-4.1-20250805`	0	`z-ai/glm-5.3`	50
Claude Opus 4.1 20250805 Coding vs Z.ai: GLM 5.3 Flash	`anthropic/claude-opus-4.1-20250805-coding`	0	`z-ai/glm-5.3-flash`	48
Claude Opus 4.5 20251101 vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4.5-20251101`	0	`moonshotai/kimi-k3`	45
Claude Opus 4.5 20251101 Coding vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-opus-4.5-20251101-coding`	0	`deepseek/deepseek-v4-flash-0731`	35
Claude Sonnet 4 20250514 Coding vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-sonnet-4-20250514-coding`	0	`deepseek/deepseek-v4.1-flash`	37
Claude Sonnet 4.5 20250929 vs OpenAI: gpt-oss-120b	`anthropic/claude-sonnet-4.5-20250929`	0	`openai/gpt-oss-120b`	37
Claude Sonnet 4.5 20250929 Coding vs Qwen: Qwen3.8 27B	`anthropic/claude-sonnet-4.5-20250929-coding`	0	`qwen/qwen3.8-27b`	33
Claude Sonnet 4.6 AWS vs MoonshotAI: Kimi K2.6	`anthropic/claude-sonnet-4.6-aws`	0	`moonshotai/kimi-k2.6`	27
Claude Sonnet 4.6 Coding vs DeepSeek: DeepSeek V4.1 Flash 1017	`anthropic/claude-sonnet-4.6-coding`	0	`deepseek/deepseek-v4.1-flash-1017`	24
DeepSeek: DeepSeek V3.1 Terminus vs MiniMax: MiniMax M3	`deepseek/deepseek-v3.1-terminus`	0	`minimax/minimax-m3`	25
MoonshotAI: Kimi K2.7 Code vs TrustedRouter Lev 1.0	`moonshotai/kimi-k2.7-code`	21	`trustedrouter/lev-1.0`	0
TrustedRouter Oev 1.0 vs Z.ai: GLM 5.2	`trustedrouter/oev-1.0`	0	`z-ai/glm-5.2`	50
TrustedRouter Trev 1.0 vs Z.ai: GLM 5.3	`trustedrouter/trev-1.0`	0	`z-ai/glm-5.3`	50
DeepSeek R1 Distill Qwen3 8B 0528 vs Z.ai: GLM 5.3 Flash	`deepseek/deepseek-r1-0528-qwen3-8b`	1	`z-ai/glm-5.3-flash`	48
DeepSeek V3 0324 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v3-0324`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Meta Llama 3.1 8B Instruct	`deepseek/deepseek-v4-flash-0731`	35	`meta-llama/Meta-Llama-3.1-8B-Instruct`	1
DeepSeek: DeepSeek V4.1 Flash vs nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3.5-lightning-30b-a3b-bf16`	1
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3.5-super-vl-120b-a12b-bf16`	1	`openai/gpt-oss-120b`	37
PaddleOCR VL vs Qwen: Qwen3.8 27B	`paddlepaddle/paddleocr-vl`	1	`qwen/qwen3.8-27b`	33
gemma 2 2b it vs MoonshotAI: Kimi K2.6	`google/gemma-2-2b-it`	1	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Hermes 2 Pro Llama 3 8B	`deepseek/deepseek-v4.1-flash-1017`	24	`nousresearch/hermes-2-pro-llama-3-8b`	1
MiniMax: MiniMax M3 vs Llama 3 70B Euryale V2.1	`minimax/minimax-m3`	25	`sao10k/l3-70b-euryale-v2.1`	1
Decision Models s1-vision (EU) vs MoonshotAI: Kimi K2.7 Code	`decisionmodelsio-eu/s1-vision`	0	`moonshotai/kimi-k2.7-code`	21
Decision Models s1-vision (GLOBAL) vs Z.ai: GLM 5.2	`decisionmodelsio/s1-vision`	0	`z-ai/glm-5.2`	50
Multilingual E5 Large Instruct vs Z.ai: GLM 5.3	`intfloat/multilingual-e5-large-instruct`	0	`z-ai/glm-5.3`	50
sonar vs Z.ai: GLM 5.3 Flash	`perplexity/sonar`	0	`z-ai/glm-5.3-flash`	48
Google: Gemini 2.5 Flash vs Xiaomi: MiMo-V2.6-Pro	`google/gemini-2.5-flash`	6	`xiaomi/mimo-v2.6-pro`	8
Google: Gemini 3.1 Flash Lite vs Xiaomi: MiMo-V2.6-Pro	`google/gemini-3.1-flash-lite`	6	`xiaomi/mimo-v2.6-pro`	8
NVIDIA: Nemotron 3.5 Super VL vs Xiaomi: MiMo-V2.6-Pro	`nvidia/nemotron-3.5-super-vl`	7	`xiaomi/mimo-v2.6-pro`	8
Qwen3.7 Max vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3.7-max`	7	`xiaomi/mimo-v2.6-pro`	8
Qwen3.8 Max vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3.8-max`	8	`xiaomi/mimo-v2.6-pro`	8
Xiaomi: MiMo-V2.5 vs Xiaomi: MiMo-V2.6-Pro	`xiaomi/mimo-v2.5`	5	`xiaomi/mimo-v2.6-pro`	8
Qwen/Qwen3-235B-A22B-Instruct-2507 vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3-235b-a22b-instruct-2507`	7	`xiaomi/mimo-v2.6-pro`	8
Qwen: Qwen3 Next 80B A3B Instruct vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3-next-80b-a3b-instruct`	7	`xiaomi/mimo-v2.6-pro`	8
Tencent: Hy3 vs Xiaomi: MiMo-V2.6-Pro	`tencent/hy3`	8	`xiaomi/mimo-v2.6-pro`	8
Xiaomi: MiMo-V2.6-Pro vs Z.ai: GLM 4.6	`xiaomi/mimo-v2.6-pro`	8	`z-ai/glm-4.6`	7
Xiaomi: MiMo-V2.6-Pro vs Z.ai: GLM 4.7 Flash	`xiaomi/mimo-v2.6-pro`	8	`z-ai/glm-4.7-flash`	4
Qwen: Qwen3 14B vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3-14b`	5	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-5.6 Luna vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-5.6-luna`	4	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-5.6 Sol vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-5.6-sol`	5	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs Xiaomi: MiMo-V2.6-Pro	`deepseek/deepseek-v4-pro-0423`	3	`xiaomi/mimo-v2.6-pro`	8
Google: Gemini 2.5 Pro vs Xiaomi: MiMo-V2.6-Pro	`google/gemini-2.5-pro`	4	`xiaomi/mimo-v2.6-pro`	8
Google: Gemini 3.1 Pro Preview vs Xiaomi: MiMo-V2.6-Pro	`google/gemini-3.1-pro-preview`	5	`xiaomi/mimo-v2.6-pro`	8
Google: Gemini 3.8 Flash vs Xiaomi: MiMo-V2.6-Pro	`google/gemini-3.8-flash`	5	`xiaomi/mimo-v2.6-pro`	8
NVIDIA: Nemotron 3.5 Lightning vs Xiaomi: MiMo-V2.6-Pro	`nvidia/nemotron-3.5-lightning`	5	`xiaomi/mimo-v2.6-pro`	8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Xiaomi: MiMo-V2.6-Pro	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`xiaomi/mimo-v2.6-pro`	8
Qwen: Qwen3.8-Flash-Next vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3.8-flash-next`	3	`xiaomi/mimo-v2.6-pro`	8
Xiaomi: MiMo-V2.6-Pro vs Z.ai: GLM 5V Turbo	`xiaomi/mimo-v2.6-pro`	8	`z-ai/glm-5v-turbo`	5
MiniMax: MiniMax M2.7 vs Xiaomi: MiMo-V2.6-Pro	`minimax/minimax-m2.7`	5	`xiaomi/mimo-v2.6-pro`	8
DeepSeek: R1 0528 vs Xiaomi: MiMo-V2.6-Pro	`deepseek/deepseek-r1-0528`	6	`xiaomi/mimo-v2.6-pro`	8
deepseek-ai/DeepSeek-V3.1 vs Xiaomi: MiMo-V2.6-Pro	`deepseek/deepseek-v3.1`	4	`xiaomi/mimo-v2.6-pro`	8
Meta: Llama 3.1 8B Instruct vs Xiaomi: MiMo-V2.6-Pro	`meta-llama/llama-3.1-8b-instruct`	4	`xiaomi/mimo-v2.6-pro`	8
Llama 4 Scout Instruct vs Xiaomi: MiMo-V2.6-Pro	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`xiaomi/mimo-v2.6-pro`	8
Meta: Llama 4 Maverick vs Xiaomi: MiMo-V2.6-Pro	`meta-llama/llama-4-maverick`	5	`xiaomi/mimo-v2.6-pro`	8
google/gemma-4-12B-it vs Xiaomi: MiMo-V2.6-Pro	`google/gemma-4-12b-it`	4	`xiaomi/mimo-v2.6-pro`	8
Qwen3 Embedding 8B vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3-embedding-8b`	4	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-5.5 vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-5.5`	4	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-5.6 Terra vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-5.6-terra`	4	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-6 Astra vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-6-astra`	4	`xiaomi/mimo-v2.6-pro`	8
OpenAI: GPT-6 Luna vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-6-luna`	4	`xiaomi/mimo-v2.6-pro`	8
Google: Gemini 2.5 Flash vs Google: Gemini 3.1 Flash Lite	`google/gemini-2.5-flash`	6	`google/gemini-3.1-flash-lite`	6
Google: Gemini 2.5 Flash vs NVIDIA: Nemotron 3.5 Super VL	`google/gemini-2.5-flash`	6	`nvidia/nemotron-3.5-super-vl`	7
Google: Gemini 2.5 Flash vs Qwen3.7 Max	`google/gemini-2.5-flash`	6	`qwen/qwen3.7-max`	7
Google: Gemini 2.5 Flash vs Qwen3.8 Max	`google/gemini-2.5-flash`	6	`qwen/qwen3.8-max`	8
Google: Gemini 2.5 Flash vs Xiaomi: MiMo-V2.5	`google/gemini-2.5-flash`	6	`xiaomi/mimo-v2.5`	5
Google: Gemini 2.5 Flash vs Qwen/Qwen3-235B-A22B-Instruct-2507	`google/gemini-2.5-flash`	6	`qwen/qwen3-235b-a22b-instruct-2507`	7
Google: Gemini 2.5 Flash vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-2.5-flash`	6	`qwen/qwen3-next-80b-a3b-instruct`	7
Google: Gemini 2.5 Flash vs Tencent: Hy3	`google/gemini-2.5-flash`	6	`tencent/hy3`	8
Google: Gemini 2.5 Flash vs Z.ai: GLM 4.6	`google/gemini-2.5-flash`	6	`z-ai/glm-4.6`	7
Google: Gemini 2.5 Flash vs Z.ai: GLM 4.7 Flash	`google/gemini-2.5-flash`	6	`z-ai/glm-4.7-flash`	4
Google: Gemini 2.5 Flash vs Qwen: Qwen3 14B	`google/gemini-2.5-flash`	6	`qwen/qwen3-14b`	5
Google: Gemini 2.5 Flash vs OpenAI: GPT-5.6 Luna	`google/gemini-2.5-flash`	6	`openai/gpt-5.6-luna`	4
Google: Gemini 2.5 Flash vs OpenAI: GPT-5.6 Sol	`google/gemini-2.5-flash`	6	`openai/gpt-5.6-sol`	5
DeepSeek V4 Pro 0423 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v4-pro-0423`	3	`google/gemini-2.5-flash`	6
Google: Gemini 2.5 Flash vs Google: Gemini 2.5 Pro	`google/gemini-2.5-flash`	6	`google/gemini-2.5-pro`	4
Google: Gemini 2.5 Flash vs Google: Gemini 3.1 Pro Preview	`google/gemini-2.5-flash`	6	`google/gemini-3.1-pro-preview`	5
Google: Gemini 2.5 Flash vs Google: Gemini 3.8 Flash	`google/gemini-2.5-flash`	6	`google/gemini-3.8-flash`	5
Google: Gemini 2.5 Flash vs NVIDIA: Nemotron 3.5 Lightning	`google/gemini-2.5-flash`	6	`nvidia/nemotron-3.5-lightning`	5
Google: Gemini 2.5 Flash vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`google/gemini-2.5-flash`	6	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
Google: Gemini 2.5 Flash vs Qwen: Qwen3.8-Flash-Next	`google/gemini-2.5-flash`	6	`qwen/qwen3.8-flash-next`	3
Google: Gemini 2.5 Flash vs Z.ai: GLM 5V Turbo	`google/gemini-2.5-flash`	6	`z-ai/glm-5v-turbo`	5
Google: Gemini 2.5 Flash vs MiniMax: MiniMax M2.7	`google/gemini-2.5-flash`	6	`minimax/minimax-m2.7`	5
DeepSeek: R1 0528 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-r1-0528`	6	`google/gemini-2.5-flash`	6
deepseek-ai/DeepSeek-V3.1 vs Google: Gemini 2.5 Flash	`deepseek/deepseek-v3.1`	4	`google/gemini-2.5-flash`	6
Google: Gemini 2.5 Flash vs Meta: Llama 3.1 8B Instruct	`google/gemini-2.5-flash`	6	`meta-llama/llama-3.1-8b-instruct`	4
Google: Gemini 2.5 Flash vs Llama 4 Scout Instruct	`google/gemini-2.5-flash`	6	`meta-llama/llama-4-scout-17b-16e-instruct`	5
Google: Gemini 2.5 Flash vs Meta: Llama 4 Maverick	`google/gemini-2.5-flash`	6	`meta-llama/llama-4-maverick`	5
Google: Gemini 2.5 Flash vs google/gemma-4-12B-it	`google/gemini-2.5-flash`	6	`google/gemma-4-12b-it`	4
Google: Gemini 2.5 Flash vs Qwen3 Embedding 8B	`google/gemini-2.5-flash`	6	`qwen/qwen3-embedding-8b`	4
Google: Gemini 2.5 Flash vs OpenAI: GPT-5.5	`google/gemini-2.5-flash`	6	`openai/gpt-5.5`	4
Google: Gemini 2.5 Flash vs OpenAI: GPT-5.6 Terra	`google/gemini-2.5-flash`	6	`openai/gpt-5.6-terra`	4
Google: Gemini 2.5 Flash vs OpenAI: GPT-6 Astra	`google/gemini-2.5-flash`	6	`openai/gpt-6-astra`	4
Google: Gemini 2.5 Flash vs OpenAI: GPT-6 Luna	`google/gemini-2.5-flash`	6	`openai/gpt-6-luna`	4
Google: Gemini 3.1 Flash Lite vs NVIDIA: Nemotron 3.5 Super VL	`google/gemini-3.1-flash-lite`	6	`nvidia/nemotron-3.5-super-vl`	7
Google: Gemini 3.1 Flash Lite vs Qwen3.7 Max	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.7-max`	7
Google: Gemini 3.1 Flash Lite vs Qwen3.8 Max	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.8-max`	8
Google: Gemini 3.1 Flash Lite vs Xiaomi: MiMo-V2.5	`google/gemini-3.1-flash-lite`	6	`xiaomi/mimo-v2.5`	5
Google: Gemini 3.1 Flash Lite vs Qwen/Qwen3-235B-A22B-Instruct-2507	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3-235b-a22b-instruct-2507`	7
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3 Next 80B A3B Instruct	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3-next-80b-a3b-instruct`	7