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
OpenAI: GPT-5.6 Sol vs Qwen: Qwen3.6 35B A3B	`openai/gpt-5.6-sol`	5	`qwen/qwen3.6-35b-a3b`	19
DeepSeek: DeepSeek V4 Flash Vision Exp vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4-flash-vision-exp`	6	`qwen/qwen3.6-35b-a3b`	19
Google: Gemini 2.5 Pro vs Qwen: Qwen3.6 35B A3B	`google/gemini-2.5-pro`	4	`qwen/qwen3.6-35b-a3b`	19
Google: Gemini 3.1 Pro Preview vs Qwen: Qwen3.6 35B A3B	`google/gemini-3.1-pro-preview`	5	`qwen/qwen3.6-35b-a3b`	19
Google: Gemini 3.8 Flash vs Qwen: Qwen3.6 35B A3B	`google/gemini-3.8-flash`	5	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs stepfun-ai/Step-5-Preview	`qwen/qwen3.6-35b-a3b`	19	`stepfun-ai/step-5-preview`	5
Qwen: Qwen3.6 35B A3B vs Xiaomi: MiMo-V2.5-Pro	`qwen/qwen3.6-35b-a3b`	19	`xiaomi/mimo-v2.5-pro`	5
Qwen: Qwen3.6 35B A3B vs Qwen3.8 Flash	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.8-flash`	6
Qwen: Qwen3.6 35B A3B vs Thinking Machines: Inkling	`qwen/qwen3.6-35b-a3b`	19	`thinkingmachines/inkling`	5
MoonshotAI: Kimi K2 Thinking vs Qwen: Qwen3.6 35B A3B	`moonshotai/kimi-k2-thinking`	5	`qwen/qwen3.6-35b-a3b`	19
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3.6 35B A3B	`nvidia/nemotron-3-nano-30b-a3b`	5	`qwen/qwen3.6-35b-a3b`	19
NVIDIA: Nemotron 3.5 Lightning vs Qwen: Qwen3.6 35B A3B	`nvidia/nemotron-3.5-lightning`	5	`qwen/qwen3.6-35b-a3b`	19
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Qwen: Qwen3.6 35B A3B	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3 Coder Next vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3-coder-next`	4	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Qwen: Qwen3.8-Flash-Next	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.8-flash-next`	3
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 5V Turbo	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-r1-0528`	6	`qwen/qwen3.6-35b-a3b`	19
OpenAI: gpt-oss-20b vs Z.ai: GLM 5.1	`openai/gpt-oss-20b`	18	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash 0423 vs Z.ai: GLM 5.1	`deepseek/deepseek-v4-flash`	18	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4.1 Flash 1017 vs Z.ai: GLM 5.1	`deepseek/deepseek-v4.1-flash-1017`	17	`z-ai/glm-5.1`	21
Qwen: Qwen3.5 397B A17B vs Z.ai: GLM 5.1	`qwen/qwen3.5-397b-a17b`	18	`z-ai/glm-5.1`	21
Google: Gemma 4 26B A4B vs Z.ai: GLM 5.1	`google/gemma-4-26b-a4b-it`	16	`z-ai/glm-5.1`	21
MoonshotAI: Kimi K2.5 vs Z.ai: GLM 5.1	`moonshotai/kimi-k2.5`	14	`z-ai/glm-5.1`	21
Meta: Llama 3.3 70B Instruct vs Z.ai: GLM 5.1	`meta-llama/llama-3.3-70b-instruct`	14	`z-ai/glm-5.1`	21
Qwen: Qwen3.6 27B vs Z.ai: GLM 5.1	`qwen/qwen3.6-27b`	14	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5.1	`deepseek/deepseek-v3.2`	15	`z-ai/glm-5.1`	21
Z.ai: GLM 5 vs Z.ai: GLM 5.1	`z-ai/glm-5`	12	`z-ai/glm-5.1`	21
Qwen: Qwen3.5-9B vs Z.ai: GLM 5.1	`qwen/qwen3.5-9b`	12	`z-ai/glm-5.1`	21
Z.ai: GLM 4.7 vs Z.ai: GLM 5.1	`z-ai/glm-4.7`	10	`z-ai/glm-5.1`	21
Qwen: Qwen3.8 2.4T A95B vs Z.ai: GLM 5.1	`qwen/qwen3.8-2.4t-a95b`	9	`z-ai/glm-5.1`	21
Qwen: Qwen3.5-122B-A10B vs Z.ai: GLM 5.1	`qwen/qwen3.5-122b-a10b`	10	`z-ai/glm-5.1`	21
MiniMax: MiniMax M2.5 vs Z.ai: GLM 5.1	`minimax/minimax-m2.5`	9	`z-ai/glm-5.1`	21
Google: Gemma 3 27B vs Z.ai: GLM 5.1	`google/gemma-3-27b-it`	10	`z-ai/glm-5.1`	21
Z.ai: GLM 4.7 Flash vs Z.ai: GLM 5.1	`z-ai/glm-4.7-flash`	7	`z-ai/glm-5.1`	21
Xiaomi: MiMo-V2.6-Flash vs Z.ai: GLM 5.1	`xiaomi/mimo-v2.6-flash`	9	`z-ai/glm-5.1`	21
NVIDIA: Nemotron 3 Super vs Z.ai: GLM 5.1	`nvidia/nemotron-3-super-120b-a12b`	8	`z-ai/glm-5.1`	21
NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 5.1	`nvidia/nemotron-3-ultra-550b-a55b`	9	`z-ai/glm-5.1`	21
Qwen/Qwen3-235B-A22B-Instruct-2507 vs Z.ai: GLM 5.1	`qwen/qwen3-235b-a22b-instruct-2507`	7	`z-ai/glm-5.1`	21
Qwen: Qwen3 Next 80B A3B Instruct vs Z.ai: GLM 5.1	`qwen/qwen3-next-80b-a3b-instruct`	8	`z-ai/glm-5.1`	21
Qwen: Qwen3.5-27B vs Z.ai: GLM 5.1	`qwen/qwen3.5-27b`	7	`z-ai/glm-5.1`	21
Qwen: Qwen3.5-35B-A3B vs Z.ai: GLM 5.1	`qwen/qwen3.5-35b-a3b`	9	`z-ai/glm-5.1`	21
Z.ai: GLM 4.6 vs Z.ai: GLM 5.1	`z-ai/glm-4.6`	8	`z-ai/glm-5.1`	21
deepseek-ai/DeepSeek-V3.1 vs Z.ai: GLM 5.1	`deepseek/deepseek-v3.1`	6	`z-ai/glm-5.1`	21
Google: Gemma 3 12B vs Z.ai: GLM 5.1	`google/gemma-3-12b-it`	7	`z-ai/glm-5.1`	21
Meta: Llama 3.1 8B Instruct vs Z.ai: GLM 5.1	`meta-llama/llama-3.1-8b-instruct`	7	`z-ai/glm-5.1`	21
Qwen: Qwen3 14B vs Z.ai: GLM 5.1	`qwen/qwen3-14b`	6	`z-ai/glm-5.1`	21
Xiaomi: MiMo-V2.6-Pro vs Z.ai: GLM 5.1	`xiaomi/mimo-v2.6-pro`	8	`z-ai/glm-5.1`	21
DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.1	`deepseek/deepseek-v4-pro-0423`	4	`z-ai/glm-5.1`	21
Google: Gemini 2.5 Flash vs Z.ai: GLM 5.1	`google/gemini-2.5-flash`	6	`z-ai/glm-5.1`	21
Google: Gemini 3.1 Flash Lite vs Z.ai: GLM 5.1	`google/gemini-3.1-flash-lite`	6	`z-ai/glm-5.1`	21
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5.1	`xiaomi/mimo-v2.5`	5	`z-ai/glm-5.1`	21
Qwen3.7 Max vs Z.ai: GLM 5.1	`qwen/qwen3.7-max`	7	`z-ai/glm-5.1`	21
Qwen3.8 Max vs Z.ai: GLM 5.1	`qwen/qwen3.8-max`	8	`z-ai/glm-5.1`	21
Tencent: Hy4 preview vs Z.ai: GLM 5.1	`tencent/hy4-preview`	8	`z-ai/glm-5.1`	21
Tencent: Hy3 vs Z.ai: GLM 5.1	`tencent/hy3`	8	`z-ai/glm-5.1`	21
MiniMax: MiniMax M2.7 vs Z.ai: GLM 5.1	`minimax/minimax-m2.7`	7	`z-ai/glm-5.1`	21
Qwen: Qwen3 32B vs Z.ai: GLM 5.1	`qwen/qwen3-32b`	5	`z-ai/glm-5.1`	21
OpenAI: GPT-5.6 Luna vs Z.ai: GLM 5.1	`openai/gpt-5.6-luna`	4	`z-ai/glm-5.1`	21
OpenAI: GPT-5.6 Sol vs Z.ai: GLM 5.1	`openai/gpt-5.6-sol`	5	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash Vision Exp vs Z.ai: GLM 5.1	`deepseek/deepseek-v4-flash-vision-exp`	6	`z-ai/glm-5.1`	21
Google: Gemini 2.5 Pro vs Z.ai: GLM 5.1	`google/gemini-2.5-pro`	4	`z-ai/glm-5.1`	21
Google: Gemini 3.1 Pro Preview vs Z.ai: GLM 5.1	`google/gemini-3.1-pro-preview`	5	`z-ai/glm-5.1`	21
Google: Gemini 3.8 Flash vs Z.ai: GLM 5.1	`google/gemini-3.8-flash`	5	`z-ai/glm-5.1`	21
stepfun-ai/Step-5-Preview vs Z.ai: GLM 5.1	`stepfun-ai/step-5-preview`	5	`z-ai/glm-5.1`	21
Xiaomi: MiMo-V2.5-Pro vs Z.ai: GLM 5.1	`xiaomi/mimo-v2.5-pro`	5	`z-ai/glm-5.1`	21
Qwen3.8 Flash vs Z.ai: GLM 5.1	`qwen/qwen3.8-flash`	6	`z-ai/glm-5.1`	21
Thinking Machines: Inkling vs Z.ai: GLM 5.1	`thinkingmachines/inkling`	5	`z-ai/glm-5.1`	21
MoonshotAI: Kimi K2 Thinking vs Z.ai: GLM 5.1	`moonshotai/kimi-k2-thinking`	5	`z-ai/glm-5.1`	21
NVIDIA: Nemotron 3 Nano 30B A3B vs Z.ai: GLM 5.1	`nvidia/nemotron-3-nano-30b-a3b`	5	`z-ai/glm-5.1`	21
NVIDIA: Nemotron 3.5 Lightning vs Z.ai: GLM 5.1	`nvidia/nemotron-3.5-lightning`	5	`z-ai/glm-5.1`	21
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Z.ai: GLM 5.1	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`z-ai/glm-5.1`	21
Qwen: Qwen3 Coder Next vs Z.ai: GLM 5.1	`qwen/qwen3-coder-next`	4	`z-ai/glm-5.1`	21
Qwen: Qwen3.8-Flash-Next vs Z.ai: GLM 5.1	`qwen/qwen3.8-flash-next`	3	`z-ai/glm-5.1`	21
Z.ai: GLM 5.1 vs Z.ai: GLM 5V Turbo	`z-ai/glm-5.1`	21	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs Z.ai: GLM 5.1	`deepseek/deepseek-r1-0528`	6	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v4-flash`	18	`openai/gpt-oss-20b`	18
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v4.1-flash-1017`	17	`openai/gpt-oss-20b`	18
OpenAI: gpt-oss-20b vs Qwen: Qwen3.5 397B A17B	`openai/gpt-oss-20b`	18	`qwen/qwen3.5-397b-a17b`	18
Google: Gemma 4 26B A4B vs OpenAI: gpt-oss-20b	`google/gemma-4-26b-a4b-it`	16	`openai/gpt-oss-20b`	18
MoonshotAI: Kimi K2.5 vs OpenAI: gpt-oss-20b	`moonshotai/kimi-k2.5`	14	`openai/gpt-oss-20b`	18
Meta: Llama 3.3 70B Instruct vs OpenAI: gpt-oss-20b	`meta-llama/llama-3.3-70b-instruct`	14	`openai/gpt-oss-20b`	18
OpenAI: gpt-oss-20b vs Qwen: Qwen3.6 27B	`openai/gpt-oss-20b`	18	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v3.2`	15	`openai/gpt-oss-20b`	18
OpenAI: gpt-oss-20b vs Z.ai: GLM 5	`openai/gpt-oss-20b`	18	`z-ai/glm-5`	12
OpenAI: gpt-oss-20b vs Qwen: Qwen3.5-9B	`openai/gpt-oss-20b`	18	`qwen/qwen3.5-9b`	12
OpenAI: gpt-oss-20b vs Z.ai: GLM 4.7	`openai/gpt-oss-20b`	18	`z-ai/glm-4.7`	10
OpenAI: gpt-oss-20b vs Qwen: Qwen3.8 2.4T A95B	`openai/gpt-oss-20b`	18	`qwen/qwen3.8-2.4t-a95b`	9
OpenAI: gpt-oss-20b vs Qwen: Qwen3.5-122B-A10B	`openai/gpt-oss-20b`	18	`qwen/qwen3.5-122b-a10b`	10
MiniMax: MiniMax M2.5 vs OpenAI: gpt-oss-20b	`minimax/minimax-m2.5`	9	`openai/gpt-oss-20b`	18
Google: Gemma 3 27B vs OpenAI: gpt-oss-20b	`google/gemma-3-27b-it`	10	`openai/gpt-oss-20b`	18
OpenAI: gpt-oss-20b vs Z.ai: GLM 4.7 Flash	`openai/gpt-oss-20b`	18	`z-ai/glm-4.7-flash`	7
OpenAI: gpt-oss-20b vs Xiaomi: MiMo-V2.6-Flash	`openai/gpt-oss-20b`	18	`xiaomi/mimo-v2.6-flash`	9
NVIDIA: Nemotron 3 Super vs OpenAI: gpt-oss-20b	`nvidia/nemotron-3-super-120b-a12b`	8	`openai/gpt-oss-20b`	18
NVIDIA: Nemotron 3 Ultra vs OpenAI: gpt-oss-20b	`nvidia/nemotron-3-ultra-550b-a55b`	9	`openai/gpt-oss-20b`	18
OpenAI: gpt-oss-20b vs Qwen/Qwen3-235B-A22B-Instruct-2507	`openai/gpt-oss-20b`	18	`qwen/qwen3-235b-a22b-instruct-2507`	7
OpenAI: gpt-oss-20b vs Qwen: Qwen3 Next 80B A3B Instruct	`openai/gpt-oss-20b`	18	`qwen/qwen3-next-80b-a3b-instruct`	8
OpenAI: gpt-oss-20b vs Qwen: Qwen3.5-27B	`openai/gpt-oss-20b`	18	`qwen/qwen3.5-27b`	7
OpenAI: gpt-oss-20b vs Qwen: Qwen3.5-35B-A3B	`openai/gpt-oss-20b`	18	`qwen/qwen3.5-35b-a3b`	9
OpenAI: gpt-oss-20b vs Z.ai: GLM 4.6	`openai/gpt-oss-20b`	18	`z-ai/glm-4.6`	8
deepseek-ai/DeepSeek-V3.1 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v3.1`	6	`openai/gpt-oss-20b`	18