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 Flash 0423 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-flash`	18	`moonshotai/kimi-k2.7-code`	19
DeepSeek: DeepSeek V4.1 Flash 1017 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4.1-flash-1017`	17	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs OpenAI: gpt-oss-20b	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-oss-20b`	17
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.5 397B A17B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-397b-a17b`	18
Google: Gemma 4 26B A4B vs MoonshotAI: Kimi K2.7 Code	`google/gemma-4-26b-a4b-it`	16	`moonshotai/kimi-k2.7-code`	19
Meta: Llama 3.3 70B Instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-3.3-70b-instruct`	14	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.5 vs MoonshotAI: Kimi K2.7 Code	`moonshotai/kimi-k2.5`	13	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.6 27B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.6-27b`	14
MoonshotAI: Kimi K2.7 Code vs Z.ai: GLM 5	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-5`	12
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v3.2`	14	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.5-9B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-9b`	12
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.8 2.4T A95B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.8-2.4t-a95b`	9
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.5-122B-A10B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-122b-a10b`	10
MoonshotAI: Kimi K2.7 Code vs Z.ai: GLM 4.7	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-4.7`	9
MoonshotAI: Kimi K2.7 Code vs Xiaomi: MiMo-V2.6-Flash	`moonshotai/kimi-k2.7-code`	19	`xiaomi/mimo-v2.6-flash`	9
MoonshotAI: Kimi K2.7 Code vs NVIDIA: Nemotron 3 Ultra	`moonshotai/kimi-k2.7-code`	19	`nvidia/nemotron-3-ultra-550b-a55b`	9
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.5-27B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-27b`	7
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.5-35B-A3B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-35b-a3b`	9
MoonshotAI: Kimi K2.7 Code vs Z.ai: GLM 4.6	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-4.6`	8
MiniMax: MiniMax M2.5 vs MoonshotAI: Kimi K2.7 Code	`minimax/minimax-m2.5`	8	`moonshotai/kimi-k2.7-code`	19
Google: Gemma 3 27B vs MoonshotAI: Kimi K2.7 Code	`google/gemma-3-27b-it`	9	`moonshotai/kimi-k2.7-code`	19
Meta: Llama 3.1 8B Instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-3.1-8b-instruct`	7	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs Z.ai: GLM 4.7 Flash	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-4.7-flash`	6
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3 14B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-14b`	6
MoonshotAI: Kimi K2.7 Code vs Xiaomi: MiMo-V2.6-Pro	`moonshotai/kimi-k2.7-code`	19	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-pro-0423`	4	`moonshotai/kimi-k2.7-code`	19
Google: Gemini 2.5 Flash vs MoonshotAI: Kimi K2.7 Code	`google/gemini-2.5-flash`	6	`moonshotai/kimi-k2.7-code`	19
Google: Gemini 3.1 Flash Lite vs MoonshotAI: Kimi K2.7 Code	`google/gemini-3.1-flash-lite`	6	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs Xiaomi: MiMo-V2.5	`moonshotai/kimi-k2.7-code`	19	`xiaomi/mimo-v2.5`	5
MoonshotAI: Kimi K2.7 Code vs Qwen3.7 Max	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.7-max`	7
MoonshotAI: Kimi K2.7 Code vs Qwen3.8 Max	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.8-max`	8
MoonshotAI: Kimi K2.7 Code vs Tencent: Hy4 preview	`moonshotai/kimi-k2.7-code`	19	`tencent/hy4-preview`	8
MoonshotAI: Kimi K2.7 Code vs NVIDIA: Nemotron 3 Super	`moonshotai/kimi-k2.7-code`	19	`nvidia/nemotron-3-super-120b-a12b`	7
MoonshotAI: Kimi K2.7 Code vs Qwen/Qwen3-235B-A22B-Instruct-2507	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-235b-a22b-instruct-2507`	6
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3 Next 80B A3B Instruct	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-next-80b-a3b-instruct`	7
MoonshotAI: Kimi K2.7 Code vs Tencent: Hy3	`moonshotai/kimi-k2.7-code`	19	`tencent/hy3`	8
MiniMax: MiniMax M2.7 vs MoonshotAI: Kimi K2.7 Code	`minimax/minimax-m2.7`	7	`moonshotai/kimi-k2.7-code`	19
deepseek-ai/DeepSeek-V3.1 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v3.1`	5	`moonshotai/kimi-k2.7-code`	19
Google: Gemma 3 12B vs MoonshotAI: Kimi K2.7 Code	`google/gemma-3-12b-it`	6	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs OpenAI: GPT-5.6 Luna	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-5.6-luna`	4
MoonshotAI: Kimi K2.7 Code vs OpenAI: GPT-5.6 Sol	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-5.6-sol`	5
DeepSeek: DeepSeek V4 Flash Vision Exp vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-flash-vision-exp`	6	`moonshotai/kimi-k2.7-code`	19
Google: Gemini 2.5 Pro vs MoonshotAI: Kimi K2.7 Code	`google/gemini-2.5-pro`	4	`moonshotai/kimi-k2.7-code`	19
Google: Gemini 3.1 Pro Preview vs MoonshotAI: Kimi K2.7 Code	`google/gemini-3.1-pro-preview`	5	`moonshotai/kimi-k2.7-code`	19
Google: Gemini 3.8 Flash vs MoonshotAI: Kimi K2.7 Code	`google/gemini-3.8-flash`	5	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs stepfun-ai/Step-5-Preview	`moonshotai/kimi-k2.7-code`	19	`stepfun-ai/step-5-preview`	5
MoonshotAI: Kimi K2.7 Code vs Xiaomi: MiMo-V2.5-Pro	`moonshotai/kimi-k2.7-code`	19	`xiaomi/mimo-v2.5-pro`	5
MoonshotAI: Kimi K2.7 Code vs Qwen3.8 Flash	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.8-flash`	6
MoonshotAI: Kimi K2.7 Code vs Thinking Machines: Inkling	`moonshotai/kimi-k2.7-code`	19	`thinkingmachines/inkling`	5
MoonshotAI: Kimi K2.7 Code vs NVIDIA: Nemotron 3.5 Lightning	`moonshotai/kimi-k2.7-code`	19	`nvidia/nemotron-3.5-lightning`	5
MoonshotAI: Kimi K2.7 Code vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`moonshotai/kimi-k2.7-code`	19	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.8-Flash-Next	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.8-flash-next`	3
MoonshotAI: Kimi K2.7 Code vs Z.ai: GLM 5V Turbo	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-r1-0528`	6	`moonshotai/kimi-k2.7-code`	19
Llama 4 Scout Instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3 32B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-32b`	4
Meta: Llama 4 Maverick vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-4-maverick`	5	`moonshotai/kimi-k2.7-code`	19
google/gemma-4-12B-it vs MoonshotAI: Kimi K2.7 Code	`google/gemma-4-12b-it`	4	`moonshotai/kimi-k2.7-code`	19
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 5.1	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4-flash`	18	`qwen/qwen3.6-35b-a3b`	19
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4.1-flash-1017`	17	`qwen/qwen3.6-35b-a3b`	19
OpenAI: gpt-oss-20b vs Qwen: Qwen3.6 35B A3B	`openai/gpt-oss-20b`	17	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.5 397B A17B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.5-397b-a17b`	18	`qwen/qwen3.6-35b-a3b`	19
Google: Gemma 4 26B A4B vs Qwen: Qwen3.6 35B A3B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.6-35b-a3b`	19
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.6 35B A3B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.6-35b-a3b`	19
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.6 35B A3B	`moonshotai/kimi-k2.5`	13	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 27B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.6-27b`	14	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 5	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-5`	12
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v3.2`	14	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.5-9B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.5-9b`	12	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Qwen: Qwen3.8 2.4T A95B	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.8-2.4t-a95b`	9
Qwen: Qwen3.5-122B-A10B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.5-122b-a10b`	10	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 4.7	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-4.7`	9
Qwen: Qwen3.6 35B A3B vs Xiaomi: MiMo-V2.6-Flash	`qwen/qwen3.6-35b-a3b`	19	`xiaomi/mimo-v2.6-flash`	9
NVIDIA: Nemotron 3 Ultra vs Qwen: Qwen3.6 35B A3B	`nvidia/nemotron-3-ultra-550b-a55b`	9	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.5-27B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.5-27b`	7	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.5-35B-A3B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3.5-35b-a3b`	9	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 4.6	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-4.6`	8
MiniMax: MiniMax M2.5 vs Qwen: Qwen3.6 35B A3B	`minimax/minimax-m2.5`	8	`qwen/qwen3.6-35b-a3b`	19
Google: Gemma 3 27B vs Qwen: Qwen3.6 35B A3B	`google/gemma-3-27b-it`	9	`qwen/qwen3.6-35b-a3b`	19
Meta: Llama 3.1 8B Instruct vs Qwen: Qwen3.6 35B A3B	`meta-llama/llama-3.1-8b-instruct`	7	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Z.ai: GLM 4.7 Flash	`qwen/qwen3.6-35b-a3b`	19	`z-ai/glm-4.7-flash`	6
Qwen: Qwen3 14B vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3-14b`	6	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Xiaomi: MiMo-V2.6-Pro	`qwen/qwen3.6-35b-a3b`	19	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4-pro-0423`	4	`qwen/qwen3.6-35b-a3b`	19
Google: Gemini 2.5 Flash vs Qwen: Qwen3.6 35B A3B	`google/gemini-2.5-flash`	6	`qwen/qwen3.6-35b-a3b`	19
Google: Gemini 3.1 Flash Lite vs Qwen: Qwen3.6 35B A3B	`google/gemini-3.1-flash-lite`	6	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Xiaomi: MiMo-V2.5	`qwen/qwen3.6-35b-a3b`	19	`xiaomi/mimo-v2.5`	5
Qwen: Qwen3.6 35B A3B vs Qwen3.7 Max	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.7-max`	7
Qwen: Qwen3.6 35B A3B vs Qwen3.8 Max	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.8-max`	8
Qwen: Qwen3.6 35B A3B vs Tencent: Hy4 preview	`qwen/qwen3.6-35b-a3b`	19	`tencent/hy4-preview`	8
NVIDIA: Nemotron 3 Super vs Qwen: Qwen3.6 35B A3B	`nvidia/nemotron-3-super-120b-a12b`	7	`qwen/qwen3.6-35b-a3b`	19
Qwen/Qwen3-235B-A22B-Instruct-2507 vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3-235b-a22b-instruct-2507`	6	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3 Next 80B A3B Instruct vs Qwen: Qwen3.6 35B A3B	`qwen/qwen3-next-80b-a3b-instruct`	7	`qwen/qwen3.6-35b-a3b`	19
Qwen: Qwen3.6 35B A3B vs Tencent: Hy3	`qwen/qwen3.6-35b-a3b`	19	`tencent/hy3`	8
MiniMax: MiniMax M2.7 vs Qwen: Qwen3.6 35B A3B	`minimax/minimax-m2.7`	7	`qwen/qwen3.6-35b-a3b`	19
deepseek-ai/DeepSeek-V3.1 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v3.1`	5	`qwen/qwen3.6-35b-a3b`	19
Google: Gemma 3 12B vs Qwen: Qwen3.6 35B A3B	`google/gemma-3-12b-it`	6	`qwen/qwen3.6-35b-a3b`	19
OpenAI: GPT-5.6 Luna vs Qwen: Qwen3.6 35B A3B	`openai/gpt-5.6-luna`	4	`qwen/qwen3.6-35b-a3b`	19
OpenAI: GPT-5.6 Sol vs Qwen: Qwen3.6 35B A3B	`openai/gpt-5.6-sol`	5	`qwen/qwen3.6-35b-a3b`	19