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
Ring 2.6 1T vs Z.ai: GLM 5.3	`inclusionai/ring-2.6-1t`	2	`z-ai/glm-5.3`	36
nemotron-3-ultra-550b-a55b vs Z.ai: GLM 5.3 Flash	`lightning-ai/nemotron-3-ultra-550b-a55b`	2	`z-ai/glm-5.3-flash`	34
Qwen3.8-27B vs MoonshotAI: Kimi K2.6	`lightning-ai/qwen3.8-27b`	2	`moonshotai/kimi-k2.6`	32
Macaron V1 Tall vs OpenAI: gpt-oss-120b	`mindai/macaron-v1-tall`	2	`openai/gpt-oss-120b`	32
DeepSeek: DeepSeek V4 Flash 0423 vs Ministral 3 14B Instruct	`deepseek/deepseek-v4-flash`	29	`mistralai/ministral-3-14b-instruct`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Mistral: Mistral Small 4	`deepseek/deepseek-v4-pro`	26	`mistralai/mistral-small-2603`	2
MoonshotAI: Kimi K2 0905 vs Z.ai: GLM 5.1	`moonshotai/kimi-k2-0905`	2	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs moonshotai/Kimi-K2-Instruct-0905	`minimax/minimax-m3`	22	`moonshotai/kimi-k2-instruct-0905`	2
moonshotai/Kimi: K2.7-Code-Highspeed vs Z.ai: GLM 5.2	`moonshotai/kimi-k2.7-code-highspeed`	3	`z-ai/glm-5.2`	48
MoonshotAI: Kimi K3 vs morph-v3-fast	`moonshotai/kimi-k3`	38	`morph/morph-v3-fast`	1
DeepSeek: DeepSeek V4 Flash 0731 vs morph-v3-large	`deepseek/deepseek-v4-flash-0731`	32	`morph/morph-v3-large`	1
nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B vs Z.ai: GLM 5.3	`nvidia/nemotron-3-nano-omni-reasoning-30b-a3b`	2	`z-ai/glm-5.3`	36
Ternary Bonsai 27B vs Z.ai: GLM 5.3 Flash	`prism-ml/ternary-bonsai-27b`	2	`z-ai/glm-5.3-flash`	34
MoonshotAI: Kimi K2.6 vs Qwen 3.8 2.4T	`moonshotai/kimi-k2.6`	32	`qwen/qwen-3-8-2-4t-a95b`	2
OpenAI: gpt-oss-120b vs Qwen 3.8 27B	`openai/gpt-oss-120b`	32	`qwen/qwen-3-8-27b`	2
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen VL OCR	`deepseek/deepseek-v4-flash`	29	`qwen/qwen-vl-ocr`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen VL OCR 2025 11 20	`deepseek/deepseek-v4-pro`	26	`qwen/qwen-vl-ocr-2025-11-20`	1
Qwen3 30b A3b Thinking 2507 vs Z.ai: GLM 5.1	`qwen/qwen3-30b-a3b-thinking-2507`	1	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs Qwen3 8b	`minimax/minimax-m3`	22	`qwen/qwen3-8b`	1
Google: Gemma 4 31B vs Qwen3 Max 2025 09 23	`google/gemma-4-31b-it`	24	`qwen/qwen3-max-2025-09-23`	1
Qwen3 Max 2026 01 23 vs Z.ai: GLM 5.2	`qwen/qwen3-max-2026-01-23`	1	`z-ai/glm-5.2`	48
MoonshotAI: Kimi K3 vs Qwen3 Max Preview	`moonshotai/kimi-k3`	38	`qwen/qwen3-max-preview`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 Next 80B A3B Thinking	`deepseek/deepseek-v4-flash-0731`	32	`qwen/qwen3-next-80b-a3b-thinking`	2
Qwen3 VL 32b Instruct vs Z.ai: GLM 5.3	`qwen/qwen3-vl-32b-instruct`	1	`z-ai/glm-5.3`	36
Qwen3 VL 32b Thinking vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-32b-thinking`	1	`z-ai/glm-5.3-flash`	34
MoonshotAI: Kimi K2.6 vs Qwen3 VL Flash	`moonshotai/kimi-k2.6`	32	`qwen/qwen3-vl-flash`	1
OpenAI: gpt-oss-120b vs Qwen3 VL Flash 2025 10 15	`openai/gpt-oss-120b`	32	`qwen/qwen3-vl-flash-2025-10-15`	1
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3 VL Flash 2026 01 22	`deepseek/deepseek-v4-flash`	29	`qwen/qwen3-vl-flash-2026-01-22`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3 VL Plus	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-vl-plus`	1
Qwen3 VL Plus 2025 09 23 vs Z.ai: GLM 5.1	`qwen/qwen3-vl-plus-2025-09-23`	1	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs Qwen3 VL Plus 2025 12 19	`minimax/minimax-m3`	22	`qwen/qwen3-vl-plus-2025-12-19`	1
Qwen3.6 Plus 2026-04-02 vs Z.ai: GLM 5.2	`qwen/qwen3.6-plus-2026-04-02`	2	`z-ai/glm-5.2`	48
MoonshotAI: Kimi K3 vs stepfun-ai/Step-3.7-Flash	`moonshotai/kimi-k3`	38	`stepfun-ai/step-3.7-flash`	3
DeepSeek: DeepSeek V4 Flash 0731 vs StepFun: Step 3.5 Flash	`deepseek/deepseek-v4-flash-0731`	32	`stepfun/step-3.5-flash`	1
Step 3.5 Flash 2603 vs Z.ai: GLM 5.3	`stepfun/step-3.5-flash-2603`	1	`z-ai/glm-5.3`	36
tencent/hy4-preview vs Z.ai: GLM 5.3 Flash	`tencent/hy4-preview`	2	`z-ai/glm-5.3-flash`	34
MoonshotAI: Kimi K2.6 vs Xiaomi MiMo V2.5 Pro UltraSpeed	`moonshotai/kimi-k2.6`	32	`xiaomi/mimo-v2.5-pro-ultraspeed`	2
OpenAI: gpt-oss-120b vs 0GM-1.0-35B-A3B	`openai/gpt-oss-120b`	32	`zero-g/0gm-1.0-35b-a3b`	1
ByteDance/Seed-1.8 vs DeepSeek: DeepSeek V4 Flash 0423	`bytedance/seed-1.8`	2	`deepseek/deepseek-v4-flash`	29
ByteDance/Seed-2.0-code vs DeepSeek: DeepSeek V4 Pro 0423	`bytedance/seed-2.0-code`	2	`deepseek/deepseek-v4-pro`	26
ByteDance/Seed-2.0-mini vs Z.ai: GLM 5.1	`bytedance/seed-2.0-mini`	2	`z-ai/glm-5.1`	25
ByteDance/Seed-2.0-pro vs MiniMax: MiniMax M3	`bytedance/seed-2.0-pro`	2	`minimax/minimax-m3`	22
Google: Gemma 4 31B vs Gemma 4 Uncensored	`google/gemma-4-31b-it`	24	`google/gemma-4-uncensored`	2
KAT Coder Pro vs Z.ai: GLM 5.2	`kwaipilot/kat-coder-pro`	2	`z-ai/glm-5.2`	48
Mistral: Codestral 2508 vs MoonshotAI: Kimi K3	`mistralai/codestral-2508`	2	`moonshotai/kimi-k3`	38
DeepSeek: DeepSeek V4 Flash 0731 vs Kimi K2.5	`deepseek/deepseek-v4-flash-0731`	32	`moonshotai/kimi-k2-5`	2
Kimi K2.6 vs Z.ai: GLM 5.3	`moonshotai/kimi-k2-6`	2	`z-ai/glm-5.3`	36
Kimi K2.7 Code vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k2-7-code`	2	`z-ai/glm-5.3-flash`	34
MoonshotAI: Kimi K2.6 vs @cf/nvidia/nemotron-3-120b-a12b	`moonshotai/kimi-k2.6`	32	`nvidia/nemotron-3-120b-a12b`	1
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3-nano-30b-a3b-bf16`	1	`openai/gpt-oss-120b`	32
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen 3.5 35B A3B	`deepseek/deepseek-v4-flash`	29	`qwen/qwen3-5-35b-a3b`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen 3.6 35B A3B	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-6-35b-a3b`	2
Qwen/Qwen3-Max-Thinking vs Z.ai: GLM 5.1	`qwen/qwen3-max-thinking`	2	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs Qwen 3 Next 80b	`minimax/minimax-m3`	22	`qwen/qwen3-next-80b`	2
Google: Gemma 4 31B vs MiniMax: MiniMax M2.1	`google/gemma-4-31b-it`	24	`minimax/minimax-m2.1`	3
MiniMax-M2.1-highspeed vs Z.ai: GLM 5.2	`minimax/minimax-m2.1-highspeed`	2	`z-ai/glm-5.2`	48
MiniMax-M2.7-highspeed vs MoonshotAI: Kimi K3	`minimax/minimax-m2.7-highspeed`	2	`moonshotai/kimi-k3`	38
DeepSeek: DeepSeek V4 Flash 0731 vs GLM 4.6	`deepseek/deepseek-v4-flash-0731`	32	`zai-org/glm-4.6`	2
Z.ai: GLM 5.3 vs GLM 4.7	`z-ai/glm-5.3`	36	`zai-org/glm-4.7`	2
Z.ai: GLM 5.3 Flash vs GLM 5.1	`z-ai/glm-5.3-flash`	34	`zai-org/GLM-5.1`	2
MoonshotAI: Kimi K2.6 vs GLM 5.1	`moonshotai/kimi-k2.6`	32	`zai-org/glm-5.1`	2
OpenAI: gpt-oss-120b vs GLM 5	`openai/gpt-oss-120b`	32	`zai-org/glm-5`	2
DeepSeek: DeepSeek V4 Flash 0423 vs Z.ai: GLM 5 Turbo	`deepseek/deepseek-v4-flash`	29	`z-ai/glm-5-turbo`	3
Anthropic: Claude Haiku 4.5 vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-haiku-4.5`	3	`deepseek/deepseek-v4-pro`	26
Anthropic: Claude Opus 4.5 vs Z.ai: GLM 5.1	`anthropic/claude-opus-4.5`	3	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs OpenAI: o1	`minimax/minimax-m3`	22	`openai/o1`	2
Google: Gemma 4 31B vs OpenAI: o3	`google/gemma-4-31b-it`	24	`openai/o3`	2
OpenAI: o3 Mini vs Z.ai: GLM 5.2	`openai/o3-mini`	2	`z-ai/glm-5.2`	48
MoonshotAI: Kimi K3 vs OpenAI: o4 Mini	`moonshotai/kimi-k3`	38	`openai/o4-mini`	2
DeepSeek: DeepSeek V4 Flash 0731 vs GLM 4.7 Flash	`deepseek/deepseek-v4-flash-0731`	32	`zai-org/glm-4.7-flash`	2
MiniMax M2.5 vs Z.ai: GLM 5.3	`minimax/minimax-m25`	2	`z-ai/glm-5.3`	36
MiniMax M2.7 vs Z.ai: GLM 5.3 Flash	`minimax/minimax-m27`	2	`z-ai/glm-5.3-flash`	34
MiniMaxAI/MiniMax-M2.7-Turbo vs MoonshotAI: Kimi K2.6	`minimax/minimax-m2.7-turbo`	2	`moonshotai/kimi-k2.6`	32
deepseek-ai/DeepSeek-V3 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v3`	2	`openai/gpt-oss-120b`	32
DeepSeek: DeepSeek V4 Flash 0423 vs Meta: Llama Guard 4 12B	`deepseek/deepseek-v4-flash`	29	`meta-llama/llama-guard-4-12b`	2
Baichuan M2 32B vs DeepSeek: DeepSeek V4 Pro 0423	`baichuan/baichuan-m2-32b`	2	`deepseek/deepseek-v4-pro`	26
CoBuddy vs Z.ai: GLM 5.1	`baidu/cobuddy`	2	`z-ai/glm-5.1`	25
Doubao Seed Character vs MiniMax: MiniMax M3	`bytedance/doubao-seed-character-260628`	1	`minimax/minimax-m3`	22
OpenAI GPT OSS vs Google: Gemma 4 31B	`cerebras/gpt-oss-120b`	2	`google/gemma-4-31b-it`	24
Google: Gemma 3 4B vs Z.ai: GLM 5.2	`google/gemma-3-4b-it`	2	`z-ai/glm-5.2`	48
google/gemma-4-31B-it-Ultra vs MoonshotAI: Kimi K3	`google/gemma-4-31b-it-ultra`	2	`moonshotai/kimi-k3`	38
DeepSeek: DeepSeek V4 Flash 0731 vs google/gemma-4-31B-turbo	`deepseek/deepseek-v4-flash-0731`	32	`google/gemma-4-31b-turbo`	2
google/gemma-4-E4B-it vs Z.ai: GLM 5.3	`google/gemma-4-e4b-it`	2	`z-ai/glm-5.3`	36
ibm-granite/granite-4.2-30b vs Z.ai: GLM 5.3 Flash	`ibm-granite/granite-4.2-30b`	2	`z-ai/glm-5.3-flash`	34
ibm-granite/granite-4.2-3b vs MoonshotAI: Kimi K2.6	`ibm-granite/granite-4.2-3b`	2	`moonshotai/kimi-k2.6`	32
JetBrains Mellum2 12B A2.5B vs OpenAI: gpt-oss-120b	`jetbrains/mellum2-12b-a2.5b-instruct`	1	`openai/gpt-oss-120b`	32
DeepSeek: DeepSeek V4 Flash 0423 vs Meta: Llama 3.2 3B Instruct	`deepseek/deepseek-v4-flash`	29	`meta-llama/llama-3.2-3b-instruct`	2
DeepSeek: DeepSeek V4 Pro 0423 vs meta-llama/Llama-3.3-70B-Instruct-Turbo	`deepseek/deepseek-v4-pro`	26	`meta-llama/llama-3.3-70b-instruct-turbo`	2
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo vs Z.ai: GLM 5.1	`meta-llama/meta-llama-3.1-8b-instruct-turbo`	2	`z-ai/glm-5.1`	25
MiniMax: MiniMax M3 vs Kimi K2 Instruct	`minimax/minimax-m3`	22	`moonshotai/kimi-k2-instruct`	2
Google: Gemma 4 31B vs Nous: Hermes 3 405B Instruct	`google/gemma-4-31b-it`	24	`nousresearch/hermes-3-llama-3.1-405b`	2
Hermes 4 405B vs Z.ai: GLM 5.2	`NousResearch/Hermes-4-405B`	2	`z-ai/glm-5.2`	48
MoonshotAI: Kimi K3 vs Nemotron 3 Ultra	`moonshotai/kimi-k3`	38	`nvidia/nemotron-3-ultra-550b`	2
DeepSeek: DeepSeek V4 Flash 0731 vs nvidia/Nemotron-Content-Safety-3.5	`deepseek/deepseek-v4-flash-0731`	32	`nvidia/nemotron-content-safety-3.5`	2
openai/gpt-oss-120b-Turbo vs Z.ai: GLM 5.3	`openai/gpt-oss-120b-turbo`	2	`z-ai/glm-5.3`	36
openai/gpt-oss-120b-Ultra vs Z.ai: GLM 5.3 Flash	`openai/gpt-oss-120b-ultra`	2	`z-ai/glm-5.3-flash`	34
MoonshotAI: Kimi K2.6 vs Qwen MT Flash	`moonshotai/kimi-k2.6`	32	`qwen/qwen-mt-flash`	1
OpenAI: gpt-oss-120b vs Qwen MT Lite	`openai/gpt-oss-120b`	32	`qwen/qwen-mt-lite`	1
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen MT Turbo	`deepseek/deepseek-v4-flash`	29	`qwen/qwen-mt-turbo`	1
Qwen3 30B A3B Instruct 2507 vs Z.ai: GLM 5.1	`Qwen/Qwen3-30B-A3B-Instruct-2507`	2	`z-ai/glm-5.1`	25