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
MiniMax: MiniMax M3 vs Qwen3-4B-Instruct-2507	`minimax/minimax-m3`	25	`qwen/qwen3-4b-instruct-2507`	1
Qwen: Qwen3 Coder 30B A3B Instruct vs Z.ai: GLM 5.3	`qwen/qwen3-coder-30b-a3b-instruct`	1	`z-ai/glm-5.3`	50
Qwen: Qwen3 VL 8B Instruct vs Z.ai: GLM 5.2	`qwen/qwen3-vl-8b-instruct`	2	`z-ai/glm-5.2`	48
Qwen3 VL Plus vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-plus`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3 VL Plus 2025 09 23	`moonshotai/kimi-k3`	45	`qwen/qwen3-vl-plus-2025-09-23`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 VL Plus 2025 12 19	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3-vl-plus-2025-12-19`	1
OpenAI: gpt-oss-120b vs Qwen3.6 Plus 2026-04-02	`openai/gpt-oss-120b`	38	`qwen/qwen3.6-plus-2026-04-02`	2
Qwen: Qwen3.8 27B vs Union Alpha	`qwen/qwen3.8-27b`	30	`stealth/union-alpha`	1
MoonshotAI: Kimi K2.6 vs StepFun: Step 3.5 Flash	`moonshotai/kimi-k2.6`	27	`stepfun/step-3.5-flash`	1
Google: Gemma 4 31B vs Step 3.5 Flash 2603	`google/gemma-4-31b-it`	26	`stepfun/step-3.5-flash-2603`	1
DeepSeek: DeepSeek V4 Pro 0423 vs 0GM-1.0-35B-A3B	`deepseek/deepseek-v4-pro`	26	`zero-g/0gm-1.0-35b-a3b`	1
Inception: Mercury 2.5 vs MiniMax: MiniMax M3	`inception/mercury-2.5`	1	`minimax/minimax-m3`	25
ByteDance/Seed-1.8 vs Z.ai: GLM 5.3	`bytedance/seed-1.8`	2	`z-ai/glm-5.3`	50
ByteDance/Seed-2.0-code vs Z.ai: GLM 5.2	`bytedance/seed-2.0-code`	2	`z-ai/glm-5.2`	48
ByteDance/Seed-2.0-mini vs Z.ai: GLM 5.3 Flash	`bytedance/seed-2.0-mini`	2	`z-ai/glm-5.3-flash`	48
ByteDance/Seed-2.0-pro vs MoonshotAI: Kimi K3	`bytedance/seed-2.0-pro`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Gemma 4 Uncensored	`deepseek/deepseek-v4-flash-0731`	35	`google/gemma-4-uncensored`	2
DeepSeek: DeepSeek V4.1 Flash vs Mistral: Codestral 2508	`deepseek/deepseek-v4.1-flash`	37	`mistralai/codestral-2508`	2
Kimi K2.5 vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k2-5`	2	`openai/gpt-oss-120b`	38
Kimi K2.6 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2-6`	2	`qwen/qwen3.8-27b`	30
Kimi K2.7 Code vs MoonshotAI: Kimi K2.6	`moonshotai/kimi-k2-7-code`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs @cf/nvidia/nemotron-3-120b-a12b	`google/gemma-4-31b-it`	26	`nvidia/nemotron-3-120b-a12b`	1
DeepSeek: DeepSeek V4 Pro 0423 vs NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	`deepseek/deepseek-v4-pro`	26	`nvidia/nemotron-3-nano-30b-a3b-bf16`	1
MiniMax: MiniMax M3 vs Qwen 3.5 35B A3B	`minimax/minimax-m3`	25	`qwen/qwen3-5-35b-a3b`	2
Qwen 3.6 35B A3B vs Z.ai: GLM 5.3	`qwen/qwen3-6-35b-a3b`	2	`z-ai/glm-5.3`	50
qwen3-coder-480b-a35b-instruct vs Z.ai: GLM 5.2	`qwen/qwen3-coder-480b-a35b-instruct`	1	`z-ai/glm-5.2`	48
Qwen 3 Next 80b vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-next-80b`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs StepFun: Step-3.7-Flash	`moonshotai/kimi-k3`	45	`stepfun-ai/step-3.7-flash`	2
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax: MiniMax M2	`deepseek/deepseek-v4-flash-0731`	35	`minimax/minimax-m2`	1
DeepSeek: DeepSeek V4.1 Flash vs MiniMax: MiniMax M2.1	`deepseek/deepseek-v4.1-flash`	37	`minimax/minimax-m2.1`	1
OpenAI: gpt-oss-120b vs GLM 4.6	`openai/gpt-oss-120b`	38	`zai-org/glm-4.6`	2
Qwen: Qwen3.8 27B vs GLM 4.7	`qwen/qwen3.8-27b`	30	`zai-org/glm-4.7`	2
MoonshotAI: Kimi K2.6 vs GLM 5.1	`moonshotai/kimi-k2.6`	27	`zai-org/GLM-5.1`	2
Google: Gemma 4 31B vs GLM 5.1	`google/gemma-4-31b-it`	26	`zai-org/glm-5.1`	2
DeepSeek: DeepSeek V4 Pro 0423 vs GLM 5	`deepseek/deepseek-v4-pro`	26	`zai-org/glm-5`	2
MiniMax: MiniMax M3 vs Z.ai: GLM 5 Turbo	`minimax/minimax-m3`	25	`z-ai/glm-5-turbo`	3
Anthropic: Claude Haiku 4.5 vs Z.ai: GLM 5.3	`anthropic/claude-haiku-4.5`	2	`z-ai/glm-5.3`	50
Anthropic: Claude Opus 4.5 vs Z.ai: GLM 5.2	`anthropic/claude-opus-4.5`	2	`z-ai/glm-5.2`	48
OpenAI: o1 vs Z.ai: GLM 5.3 Flash	`openai/o1`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: o3	`moonshotai/kimi-k3`	45	`openai/o3`	2
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: o3 Mini	`deepseek/deepseek-v4-flash-0731`	35	`openai/o3-mini`	2
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: o4 Mini	`deepseek/deepseek-v4.1-flash`	37	`openai/o4-mini`	2
OpenAI: gpt-oss-120b vs GLM 4.7 Flash	`openai/gpt-oss-120b`	38	`zai-org/glm-4.7-flash`	2
MiniMax M2.5 vs Qwen: Qwen3.8 27B	`minimax/minimax-m25`	2	`qwen/qwen3.8-27b`	30
MiniMax M2.7 vs MoonshotAI: Kimi K2.6	`minimax/minimax-m27`	2	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V3.1 Terminus vs Google: Gemma 4 31B	`deepseek/deepseek-v3.1-terminus`	1	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V3.2 Exp vs DeepSeek: DeepSeek V4 Pro 0423	`deepseek/deepseek-v3.2-exp`	1	`deepseek/deepseek-v4-pro`	26
Meta: Llama Guard 4 12B vs MiniMax: MiniMax M3	`meta-llama/llama-guard-4-12b`	2	`minimax/minimax-m3`	25
AionLabs: Aion 2.0 vs Z.ai: GLM 5.3	`aion-labs/aion-2.0`	1	`z-ai/glm-5.3`	50
AionLabs: Aion 3.0 vs Z.ai: GLM 5.2	`aion-labs/aion-3.0`	1	`z-ai/glm-5.2`	48
AionLabs: Aion 3.0 Mini vs Z.ai: GLM 5.3 Flash	`aion-labs/aion-3.0-mini`	1	`z-ai/glm-5.3-flash`	48
Baichuan M2 32B vs MoonshotAI: Kimi K3	`baichuan/baichuan-m2-32b`	2	`moonshotai/kimi-k3`	45
CoBuddy vs DeepSeek: DeepSeek V4 Flash 0731	`baidu/cobuddy`	2	`deepseek/deepseek-v4-flash-0731`	35
Doubao Seed Character vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/doubao-seed-character-260628`	1	`deepseek/deepseek-v4.1-flash`	37
OpenAI GPT OSS vs OpenAI: gpt-oss-120b	`cerebras/gpt-oss-120b`	2	`openai/gpt-oss-120b`	38
DeepSeek-R1-Distill-Qwen-14B vs Qwen: Qwen3.8 27B	`deepseek/deepseek-r1-distill-qwen-14b`	1	`qwen/qwen3.8-27b`	30
google/gemma-4-31B-it-Ultra vs MoonshotAI: Kimi K2.6	`google/gemma-4-31b-it-ultra`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs google/gemma-4-31B-turbo	`google/gemma-4-31b-it`	26	`google/gemma-4-31b-turbo`	2
DeepSeek: DeepSeek V4 Pro 0423 vs inclusionAI: Ling 3.0 Flash VL	`deepseek/deepseek-v4-pro`	26	`inclusionai/ling-3.0-flash-vl`	2
meta-llama/Llama-3.3-70B-Instruct-Turbo vs MiniMax: MiniMax M3	`meta-llama/llama-3.3-70b-instruct-turbo`	2	`minimax/minimax-m3`	25
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo vs Z.ai: GLM 5.3	`meta-llama/meta-llama-3.1-8b-instruct-turbo`	2	`z-ai/glm-5.3`	50
Mistral: Ministral 3 3B 2512 vs Z.ai: GLM 5.2	`mistralai/ministral-3b-2512`	2	`z-ai/glm-5.2`	48
Kimi K2 Instruct vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k2-instruct`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Nous: Hermes 3 405B Instruct	`moonshotai/kimi-k3`	45	`nousresearch/hermes-3-llama-3.1-405b`	2
DeepSeek: DeepSeek V4 Flash 0731 vs Hermes 4 405B	`deepseek/deepseek-v4-flash-0731`	35	`NousResearch/Hermes-4-405B`	2
DeepSeek: DeepSeek V4.1 Flash vs Nemotron 3 Ultra	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3-ultra-550b`	2
nvidia/Nemotron-Content-Safety-3.5 vs OpenAI: gpt-oss-120b	`nvidia/nemotron-content-safety-3.5`	2	`openai/gpt-oss-120b`	38
openai/gpt-oss-120b-Ultra vs Qwen: Qwen3.8 27B	`openai/gpt-oss-120b-ultra`	2	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen MT Flash	`moonshotai/kimi-k2.6`	27	`qwen/qwen-mt-flash`	1
Google: Gemma 4 31B vs Qwen MT Lite	`google/gemma-4-31b-it`	26	`qwen/qwen-mt-lite`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen2.5-Coder-7B-Instruct	`deepseek/deepseek-v4-pro`	26	`qwen/qwen2.5-coder-7b-instruct`	1
Qwen3 30B A3B Instruct 2507 vs Z.ai: GLM 5.3	`Qwen/Qwen3-30B-A3B-Instruct-2507`	2	`z-ai/glm-5.3`	50
Qwen3-30B-A3B-Thinking-2507 vs Z.ai: GLM 5.2	`qwen/qwen3-30b-a3b-thinking-2507`	1	`z-ai/glm-5.2`	48
Sao10K/L3.1-70B-Euryale-v2.2 vs Z.ai: GLM 5.3 Flash	`sao10k/l3.1-70b-euryale-v2.2`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Tencent: Hunyuan A13B Instruct	`moonshotai/kimi-k3`	45	`tencent/hunyuan-a13b-instruct`	2
DeepSeek: DeepSeek V4 Flash 0731 vs TheDrummer: Cydonia 24B V4.1	`deepseek/deepseek-v4-flash-0731`	35	`thedrummer/cydonia-24b-v4.1`	2
DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 4.5 Air	`deepseek/deepseek-v4.1-flash`	37	`z-ai/glm-4.5-air`	1
OpenAI: gpt-oss-120b vs GLM 4.5 Air	`openai/gpt-oss-120b`	38	`zai-org/glm-4.5-air`	2
Qwen: Qwen3.8 27B vs GLM 4.6V	`qwen/qwen3.8-27b`	30	`zai-org/glm-4.6v`	2
@cf/ibm-granite/granite-4.0-h-micro vs MoonshotAI: Kimi K2.6	`ibm-granite/granite-4.0-h-micro`	1	`moonshotai/kimi-k2.6`	27
@cf/aisingapore/gemma-sea-lion-v4-27b-it vs Google: Gemma 4 31B	`aisingapore/gemma-sea-lion-v4-27b-it`	1	`google/gemma-4-31b-it`	26
ByteDance: UI-TARS 7B vs DeepSeek: DeepSeek V4 Pro 0423	`bytedance/ui-tars-1.5-7b`	2	`deepseek/deepseek-v4-pro`	26
Cohere Embed v4.0 vs MiniMax: MiniMax M3	`cohere/embed-v4.0`	2	`minimax/minimax-m3`	25
Inception: Mercury 2 vs Z.ai: GLM 5.3	`inception/mercury-2`	1	`z-ai/glm-5.3`	50
Llama 3.2 3B vs Z.ai: GLM 5.2	`meta-llama/llama-3.2-3b`	2	`z-ai/glm-5.2`	48
Llama 3.3 70B vs Z.ai: GLM 5.3 Flash	`meta-llama/llama-3.3-70b`	2	`z-ai/glm-5.3-flash`	48
Devstral-Small-2505 vs MoonshotAI: Kimi K3	`mistralai/devstral-small-2505`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Mistral Large	`deepseek/deepseek-v4-flash-0731`	35	`mistralai/mistral-large`	2
DeepSeek: DeepSeek V4.1 Flash vs @cf/mistralai/mistral-small-3.1-24b-instruct	`deepseek/deepseek-v4.1-flash`	37	`mistralai/mistral-small-3.1-24b-instruct`	1
Nemotron Nano 12B v2 VL vs OpenAI: gpt-oss-120b	`nvidia/nemotron-nano-12b-v2-vl`	2	`openai/gpt-oss-120b`	38
OpenAI: GPT-4o vs Qwen: Qwen3.8 27B	`openai/gpt-4o`	2	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs OpenAI: GPT-4o (2024-05-13)	`moonshotai/kimi-k2.6`	27	`openai/gpt-4o-2024-05-13`	2
Google: Gemma 4 31B vs OpenAI: GPT-4o-mini	`google/gemma-4-31b-it`	26	`openai/gpt-4o-mini`	2
DeepSeek: DeepSeek V4 Pro 0423 vs gpt-oss-safeguard-20b	`deepseek/deepseek-v4-pro`	26	`openai/gpt-oss-safeguard-20b`	1
MiniMax: MiniMax M3 vs Qwen: Qwen2.5 VL 72B Instruct	`minimax/minimax-m3`	25	`qwen/qwen2.5-vl-72b-instruct`	2
Qwen: Qwen3 235B A22B Thinking 2507 vs Z.ai: GLM 5.3	`qwen/qwen3-235b-a22b-thinking-2507`	2	`z-ai/glm-5.3`	50
Qwen3 VL 235B vs Z.ai: GLM 5.2	`qwen/qwen3-vl-235b-a22b`	2	`z-ai/glm-5.2`	48
ERNIE 4.5 21B A3B vs Z.ai: GLM 5.3 Flash	`baidu/ernie-4.5-21B-a3b`	2	`z-ai/glm-5.3-flash`	48
Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR vs MoonshotAI: Kimi K3	`intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar`	1	`moonshotai/kimi-k3`	45
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-r1-distill-qwen-32b`	1	`deepseek/deepseek-v4-flash-0731`	35