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
Doubao Seed 1.6 Flash vs MoonshotAI: Kimi K2.7 Code	`bytedance/doubao-seed-1.6-flash-250828`	1	`moonshotai/kimi-k2.7-code`	19
Doubao Seed 1.8 vs Z.ai: GLM 5.2	`bytedance/doubao-seed-1.8-251228`	1	`z-ai/glm-5.2`	44
Doubao Seed 2.0 Code Preview vs Z.ai: GLM 5.3	`bytedance/doubao-seed-2.0-code-preview-260215`	1	`z-ai/glm-5.3`	43
Doubao Seed 2.0 Lite vs Z.ai: GLM 5.3 Flash	`bytedance/doubao-seed-2.0-lite-260428`	1	`z-ai/glm-5.3-flash`	41
Doubao Seed 2.0 Mini vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/doubao-seed-2.0-mini-260428`	1	`deepseek/deepseek-v4-flash-0731`	33
Doubao Seed 2.0 Pro vs MoonshotAI: Kimi K3	`bytedance/doubao-seed-2.0-pro-260215`	1	`moonshotai/kimi-k3`	39
Doubao Seed 2.1 Pro vs OpenAI: gpt-oss-120b	`bytedance/doubao-seed-2.1-pro-260628`	1	`openai/gpt-oss-120b`	36
Doubao Seed 2.1 Turbo vs MoonshotAI: Kimi K2.6	`bytedance/doubao-seed-2.1-turbo-260628`	1	`moonshotai/kimi-k2.6`	33
Doubao Seed Evolving vs DeepSeek: DeepSeek V4 Flash 0423	`bytedance/doubao-seed-evolving`	1	`deepseek/deepseek-v4-flash`	25
DeepSeek: DeepSeek V4 Pro 0423 vs google/gemma-4-31B-it-turbo	`deepseek/deepseek-v4-pro`	26	`google/gemma-4-31b-it-turbo`	2
Google: Gemma 4 31B vs inclusionAI: Ling 3.0 Flash Fin	`google/gemma-4-31b-it`	25	`inclusionai/ling-3.0-flash-fin`	3
DeepSeek: DeepSeek V4.1 Flash vs Qwen3.8-27B	`deepseek/deepseek-v4.1-flash`	23	`lightning-ai/qwen3.8-27b`	2
Macaron V1 Tall vs MoonshotAI: Kimi K2.7 Code	`mindai/macaron-v1-tall`	2	`moonshotai/kimi-k2.7-code`	19
Ministral 3 14B Instruct vs Z.ai: GLM 5.2	`mistralai/ministral-3-14b-instruct`	2	`z-ai/glm-5.2`	44
Mistral: Mistral Medium 3.5 vs Z.ai: GLM 5.3	`mistralai/mistral-medium-3-5`	2	`z-ai/glm-5.3`	43
MoonshotAI: Kimi K2 0905 vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k2-0905`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs moonshotai/Kimi-K2-Instruct-0905	`deepseek/deepseek-v4-flash-0731`	33	`moonshotai/kimi-k2-instruct-0905`	2
moonshotai/Kimi: K2.7-Code-Highspeed vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k2.7-code-highspeed`	3	`openai/gpt-oss-120b`	36
MoonshotAI: Kimi K2.6 vs morph-v3-fast	`moonshotai/kimi-k2.6`	33	`morph/morph-v3-fast`	1
DeepSeek: DeepSeek V4 Flash 0423 vs morph-v3-large	`deepseek/deepseek-v4-flash`	25	`morph/morph-v3-large`	1
DeepSeek: DeepSeek V4 Pro 0423 vs nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B	`deepseek/deepseek-v4-pro`	26	`nvidia/nemotron-3-nano-omni-reasoning-30b-a3b`	2
Google: Gemma 4 31B vs Ternary Bonsai 27B	`google/gemma-4-31b-it`	25	`prism-ml/ternary-bonsai-27b`	2
DeepSeek: DeepSeek V4.1 Flash vs Qwen 3.8 2.4T	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen-3-8-2-4t-a95b`	2
MoonshotAI: Kimi K2.7 Code vs Qwen 3.8 27B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen-3-8-27b`	2
Qwen VL OCR vs Z.ai: GLM 5.2	`qwen/qwen-vl-ocr`	1	`z-ai/glm-5.2`	44
Qwen VL OCR 2025 11 20 vs Z.ai: GLM 5.3	`qwen/qwen-vl-ocr-2025-11-20`	1	`z-ai/glm-5.3`	43
Qwen: Qwen3 235B A22B Instruct 2507 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-235b-a22b-2507`	1	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 30b A3b Thinking 2507	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-30b-a3b-thinking-2507`	1
MoonshotAI: Kimi K3 vs Qwen3-4B-Instruct-2507	`moonshotai/kimi-k3`	39	`qwen/qwen3-4b-instruct-2507`	1
OpenAI: gpt-oss-120b vs Qwen3 8b	`openai/gpt-oss-120b`	36	`qwen/qwen3-8b`	1
MoonshotAI: Kimi K2.6 vs Qwen3 Max 2025 09 23	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-max-2025-09-23`	1
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3 Max 2026 01 23	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3-max-2026-01-23`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3 Max Preview	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-max-preview`	1
Google: Gemma 4 31B vs Qwen3 Next 80B A3B Thinking	`google/gemma-4-31b-it`	25	`qwen/qwen3-next-80b-a3b-thinking`	2
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3 VL 30B A3B Thinking	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3-vl-30b-a3b-thinking`	1
MoonshotAI: Kimi K2.7 Code vs Qwen3 VL 32b Instruct	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-vl-32b-instruct`	1
Qwen3 VL 32b Thinking vs Z.ai: GLM 5.2	`qwen/qwen3-vl-32b-thinking`	1	`z-ai/glm-5.2`	44
Qwen3 VL Flash vs Z.ai: GLM 5.3	`qwen/qwen3-vl-flash`	1	`z-ai/glm-5.3`	43
Qwen3 VL Flash 2025 10 15 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-flash-2025-10-15`	1	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3 VL Flash 2026 01 22	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-vl-flash-2026-01-22`	1
MoonshotAI: Kimi K3 vs Qwen3 VL Plus	`moonshotai/kimi-k3`	39	`qwen/qwen3-vl-plus`	1
OpenAI: gpt-oss-120b vs Qwen3 VL Plus 2025 09 23	`openai/gpt-oss-120b`	36	`qwen/qwen3-vl-plus-2025-09-23`	1
MoonshotAI: Kimi K2.6 vs Qwen3 VL Plus 2025 12 19	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-vl-plus-2025-12-19`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3.6 Plus 2026-04-02	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3.6-plus-2026-04-02`	2
Google: Gemma 4 31B vs Union Alpha	`google/gemma-4-31b-it`	25	`stealth/union-alpha`	1
DeepSeek: DeepSeek V4.1 Flash vs stepfun-ai/Step-3.7-Flash	`deepseek/deepseek-v4.1-flash`	23	`stepfun-ai/step-3.7-flash`	3
MoonshotAI: Kimi K2.7 Code vs StepFun: Step 3.5 Flash	`moonshotai/kimi-k2.7-code`	19	`stepfun/step-3.5-flash`	1
Step 3.5 Flash 2603 vs Z.ai: GLM 5.2	`stepfun/step-3.5-flash-2603`	1	`z-ai/glm-5.2`	44
tencent/hy4-preview vs Z.ai: GLM 5.3	`tencent/hy4-preview`	2	`z-ai/glm-5.3`	43
Z.ai: GLM 5.3 Flash vs 0GM-1.0-35B-A3B	`z-ai/glm-5.3-flash`	41	`zero-g/0gm-1.0-35b-a3b`	1
ByteDance/Seed-1.8 vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/seed-1.8`	2	`deepseek/deepseek-v4-flash-0731`	33
ByteDance/Seed-2.0-code vs MoonshotAI: Kimi K3	`bytedance/seed-2.0-code`	2	`moonshotai/kimi-k3`	39
ByteDance/Seed-2.0-mini vs OpenAI: gpt-oss-120b	`bytedance/seed-2.0-mini`	2	`openai/gpt-oss-120b`	36
ByteDance/Seed-2.0-pro vs MoonshotAI: Kimi K2.6	`bytedance/seed-2.0-pro`	2	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs Gemma 4 Uncensored	`deepseek/deepseek-v4-flash`	25	`google/gemma-4-uncensored`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Mistral: Codestral 2508	`deepseek/deepseek-v4-pro`	26	`mistralai/codestral-2508`	2
Google: Gemma 4 31B vs Kimi K2.5	`google/gemma-4-31b-it`	25	`moonshotai/kimi-k2-5`	2
DeepSeek: DeepSeek V4.1 Flash vs Kimi K2.6	`deepseek/deepseek-v4.1-flash`	23	`moonshotai/kimi-k2-6`	2
Kimi K2.7 Code vs MoonshotAI: Kimi K2.7 Code	`moonshotai/kimi-k2-7-code`	2	`moonshotai/kimi-k2.7-code`	19
@cf/nvidia/nemotron-3-120b-a12b vs Z.ai: GLM 5.2	`nvidia/nemotron-3-120b-a12b`	1	`z-ai/glm-5.2`	44
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 vs Z.ai: GLM 5.3	`nvidia/nemotron-3-nano-30b-a3b-bf16`	1	`z-ai/glm-5.3`	43
Qwen 3.5 35B A3B vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-5-35b-a3b`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen 3.6 35B A3B	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3-6-35b-a3b`	2
MoonshotAI: Kimi K3 vs Qwen/Qwen3-Max-Thinking	`moonshotai/kimi-k3`	39	`qwen/qwen3-max-thinking`	2
OpenAI: gpt-oss-120b vs Qwen 3 Next 80b	`openai/gpt-oss-120b`	36	`qwen/qwen3-next-80b`	2
MiniMax: MiniMax M2.1 vs MoonshotAI: Kimi K2.6	`minimax/minimax-m2.1`	3	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs MiniMax-M2.1-highspeed	`deepseek/deepseek-v4-flash`	25	`minimax/minimax-m2.1-highspeed`	2
DeepSeek: DeepSeek V4 Pro 0423 vs MiniMax-M2.7-highspeed	`deepseek/deepseek-v4-pro`	26	`minimax/minimax-m2.7-highspeed`	2
Google: Gemma 4 31B vs GLM 4.6	`google/gemma-4-31b-it`	25	`zai-org/glm-4.6`	2
DeepSeek: DeepSeek V4.1 Flash vs GLM 4.7	`deepseek/deepseek-v4.1-flash`	23	`zai-org/glm-4.7`	2
MoonshotAI: Kimi K2.7 Code vs GLM 5.1	`moonshotai/kimi-k2.7-code`	19	`zai-org/GLM-5.1`	2
Z.ai: GLM 5.2 vs GLM 5.1	`z-ai/glm-5.2`	44	`zai-org/glm-5.1`	2
Z.ai: GLM 5.3 vs GLM 5	`z-ai/glm-5.3`	43	`zai-org/glm-5`	2
Z.ai: GLM 5 Turbo vs Z.ai: GLM 5.3 Flash	`z-ai/glm-5-turbo`	3	`z-ai/glm-5.3-flash`	41
Anthropic: Claude Haiku 4.5 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-haiku-4.5`	3	`deepseek/deepseek-v4-flash-0731`	33
Anthropic: Claude Opus 4.5 vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4.5`	3	`moonshotai/kimi-k3`	39
OpenAI: gpt-oss-120b vs OpenAI: o1	`openai/gpt-oss-120b`	36	`openai/o1`	2
MoonshotAI: Kimi K2.6 vs OpenAI: o3	`moonshotai/kimi-k2.6`	33	`openai/o3`	2
DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: o3 Mini	`deepseek/deepseek-v4-flash`	25	`openai/o3-mini`	2
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: o4 Mini	`deepseek/deepseek-v4-pro`	26	`openai/o4-mini`	2
Google: Gemma 4 31B vs GLM 4.7 Flash	`google/gemma-4-31b-it`	25	`zai-org/glm-4.7-flash`	2
DeepSeek: DeepSeek V4.1 Flash vs MiniMax M2.5	`deepseek/deepseek-v4.1-flash`	23	`minimax/minimax-m25`	2
MiniMax M2.7 vs MoonshotAI: Kimi K2.7 Code	`minimax/minimax-m27`	2	`moonshotai/kimi-k2.7-code`	19
MiniMaxAI/MiniMax-M2.7-Turbo vs Z.ai: GLM 5.2	`minimax/minimax-m2.7-turbo`	2	`z-ai/glm-5.2`	44
deepseek-ai/DeepSeek-V3 vs Z.ai: GLM 5.3	`deepseek/deepseek-v3`	2	`z-ai/glm-5.3`	43
deepseek-ai/DeepSeek-V3-0324 vs Z.ai: GLM 5.3 Flash	`deepseek/deepseek-v3-0324`	3	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Meta: Llama Guard 4 12B	`deepseek/deepseek-v4-flash-0731`	33	`meta-llama/llama-guard-4-12b`	2
AionLabs: Aion 2.0 vs MoonshotAI: Kimi K3	`aion-labs/aion-2.0`	1	`moonshotai/kimi-k3`	39
AionLabs: Aion 3.0 vs OpenAI: gpt-oss-120b	`aion-labs/aion-3.0`	1	`openai/gpt-oss-120b`	36
AionLabs: Aion 3.0 Mini vs MoonshotAI: Kimi K2.6	`aion-labs/aion-3.0-mini`	1	`moonshotai/kimi-k2.6`	33
Baichuan M2 32B vs DeepSeek: DeepSeek V4 Flash 0423	`baichuan/baichuan-m2-32b`	2	`deepseek/deepseek-v4-flash`	25
CoBuddy vs DeepSeek: DeepSeek V4 Pro 0423	`baidu/cobuddy`	2	`deepseek/deepseek-v4-pro`	26
Doubao Seed Character vs Google: Gemma 4 31B	`bytedance/doubao-seed-character-260628`	1	`google/gemma-4-31b-it`	25
OpenAI GPT OSS vs DeepSeek: DeepSeek V4.1 Flash	`cerebras/gpt-oss-120b`	2	`deepseek/deepseek-v4.1-flash`	23
Google: Gemma 3 4B vs MoonshotAI: Kimi K2.7 Code	`google/gemma-3-4b-it`	2	`moonshotai/kimi-k2.7-code`	19
google/gemma-4-31B-it-Ultra vs Z.ai: GLM 5.2	`google/gemma-4-31b-it-ultra`	2	`z-ai/glm-5.2`	44
google/gemma-4-31B-turbo vs Z.ai: GLM 5.3	`google/gemma-4-31b-turbo`	2	`z-ai/glm-5.3`	43
google/gemma-4-E4B-it vs Z.ai: GLM 5.3 Flash	`google/gemma-4-e4b-it`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs ibm-granite/granite-4.2-30b	`deepseek/deepseek-v4-flash-0731`	33	`ibm-granite/granite-4.2-30b`	2
ibm-granite/granite-4.2-3b vs MoonshotAI: Kimi K3	`ibm-granite/granite-4.2-3b`	2	`moonshotai/kimi-k3`	39