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 reportsRun 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 V3.1 vs Google: Gemini 2.5 Pro deepseek/deepseek-v3.1 7 google/gemini-2.5-pro 6
DeepSeek V3.1 vs Google: Gemini 3 Flash Preview deepseek/deepseek-v3.1 7 google/gemini-3-flash-preview 6
DeepSeek V3.1 vs Google: Gemini 3.1 Flash Lite deepseek/deepseek-v3.1 7 google/gemini-3.1-flash-lite 6
DeepSeek V3.1 vs Google: Gemini 3.1 Pro Preview deepseek/deepseek-v3.1 7 google/gemini-3.1-pro-preview 7
DeepSeek V3.1 vs Google: Gemini 3.5 Flash deepseek/deepseek-v3.1 7 google/gemini-3.5-flash 7
DeepSeek V3.1 vs Qwen3.7 Max deepseek/deepseek-v3.1 7 qwen/qwen3.7-max 7
DeepSeek V3.1 vs Qwen3.8 Max deepseek/deepseek-v3.1 7 qwen/qwen3.8-max 8
DeepSeek V3.1 vs Thinking Machines: Inkling deepseek/deepseek-v3.1 7 thinkingmachines/inkling 7
DeepSeek V3.1 vs Thinking Machines: Inkling Small deepseek/deepseek-v3.1 7 thinkingmachines/inkling-small 7
DeepSeek V3.1 vs NVIDIA: Nemotron 3 Super deepseek/deepseek-v3.1 7 nvidia/nemotron-3-super-120b-a12b 7
DeepSeek V3.1 vs Qwen: Qwen3 Coder Next deepseek/deepseek-v3.1 7 qwen/qwen3-coder-next 7
DeepSeek V3.1 vs Qwen: Qwen3 VL 235B A22B Instruct deepseek/deepseek-v3.1 7 qwen/qwen3-vl-235b-a22b-instruct 7
DeepSeek V3.1 vs Qwen: Qwen3.5-27B deepseek/deepseek-v3.1 7 qwen/qwen3.5-27b 6
DeepSeek V3.1 vs Qwen: Qwen3.8 2.4T A95B deepseek/deepseek-v3.1 7 qwen/qwen3.8-2.4t-a95b 8
DeepSeek V3.1 vs Tencent: Hy3 deepseek/deepseek-v3.1 7 tencent/hy3 8
DeepSeek V3.1 vs Google: Gemma 3 27B deepseek/deepseek-v3.1 7 google/gemma-3-27b-it 8
DeepSeek V3.1 vs Meta: Llama 3.1 8B Instruct deepseek/deepseek-v3.1 7 meta-llama/llama-3.1-8b-instruct 6
DeepSeek V3.1 vs Qwen: Qwen3 235B A22B Thinking 2507 deepseek/deepseek-v3.1 7 qwen/qwen3-235b-a22b-thinking-2507 7
DeepSeek V3.1 vs OpenAI: GPT-5.6 Terra deepseek/deepseek-v3.1 7 openai/gpt-5.6-terra 6
DeepSeek V3.1 vs OpenAI: GPT-6 Astra deepseek/deepseek-v3.1 7 openai/gpt-6-astra 6
DeepSeek V3.1 vs Llama 4 Maverick Instruct deepseek/deepseek-v3.1 7 meta-llama/llama-4-maverick-17b-128e-instruct-fp8 5
DeepSeek V3.1 vs NVIDIA: Nemotron 3 Nano 30B A3B deepseek/deepseek-v3.1 7 nvidia/nemotron-3-nano-30b-a3b 6
DeepSeek V3.1 vs nvidia/Nemotron-3.5-Lightning-30B-A3B deepseek/deepseek-v3.1 7 nvidia/nemotron-3.5-lightning-30b-a3b 4
DeepSeek V3.1 vs Qwen3 Max deepseek/deepseek-v3.1 7 qwen/qwen3-max 5
DeepSeek V3.1 vs Qwen: Qwen3 VL 30B A3B Instruct deepseek/deepseek-v3.1 7 qwen/qwen3-vl-30b-a3b-instruct 5
DeepSeek V3.1 vs Qwen: Qwen3 VL 8B Instruct deepseek/deepseek-v3.1 7 qwen/qwen3-vl-8b-instruct 4
DeepSeek V3.1 vs Z.ai: GLM 5V Turbo deepseek/deepseek-v3.1 7 z-ai/glm-5v-turbo 5
DeepSeek: R1 0528 vs DeepSeek V3.1 deepseek/deepseek-r1-0528 6 deepseek/deepseek-v3.1 7
DeepSeek V3.1 vs Qwen: Qwen3 Coder 30B A3B Instruct deepseek/deepseek-v3.1 7 qwen/qwen3-coder-30b-a3b-instruct 4
DeepSeek V3.1 vs Google: Gemma 3 12B deepseek/deepseek-v3.1 7 google/gemma-3-12b-it 5
DeepSeek V3.1 vs Meta: Llama 3.1 70B Instruct deepseek/deepseek-v3.1 7 meta-llama/llama-3.1-70b-instruct 5
DeepSeek V3.1 vs Llama 4 Scout Instruct deepseek/deepseek-v3.1 7 meta-llama/llama-4-scout-17b-16e-instruct 5
DeepSeek V3.1 vs Muse Glimmer 30B on Fireworks deepseek/deepseek-v3.1 7 meta-models/muse-glimmer-30b 6
DeepSeek V4 Pro 0423 vs Xiaomi: MiMo-V2.5-Pro deepseek/deepseek-v4-pro-0423 4 xiaomi/mimo-v2.5-pro 8
Google: Gemini 2.5 Pro vs Xiaomi: MiMo-V2.5-Pro google/gemini-2.5-pro 6 xiaomi/mimo-v2.5-pro 8
Google: Gemini 3 Flash Preview vs Xiaomi: MiMo-V2.5-Pro google/gemini-3-flash-preview 6 xiaomi/mimo-v2.5-pro 8
Google: Gemini 3.1 Flash Lite vs Xiaomi: MiMo-V2.5-Pro google/gemini-3.1-flash-lite 6 xiaomi/mimo-v2.5-pro 8
Google: Gemini 3.1 Pro Preview vs Xiaomi: MiMo-V2.5-Pro google/gemini-3.1-pro-preview 7 xiaomi/mimo-v2.5-pro 8
Google: Gemini 3.5 Flash vs Xiaomi: MiMo-V2.5-Pro google/gemini-3.5-flash 7 xiaomi/mimo-v2.5-pro 8
Qwen3.7 Max vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3.7-max 7 xiaomi/mimo-v2.5-pro 8
Qwen3.8 Max vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3.8-max 8 xiaomi/mimo-v2.5-pro 8
Thinking Machines: Inkling vs Xiaomi: MiMo-V2.5-Pro thinkingmachines/inkling 7 xiaomi/mimo-v2.5-pro 8
Thinking Machines: Inkling Small vs Xiaomi: MiMo-V2.5-Pro thinkingmachines/inkling-small 7 xiaomi/mimo-v2.5-pro 8
NVIDIA: Nemotron 3 Super vs Xiaomi: MiMo-V2.5-Pro nvidia/nemotron-3-super-120b-a12b 7 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 Coder Next vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-coder-next 7 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 VL 235B A22B Instruct vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-vl-235b-a22b-instruct 7 xiaomi/mimo-v2.5-pro 8
Mistral: Mistral Nemo vs Z.ai: GLM 5.3 mistralai/mistral-nemo 6 z-ai/glm-5.3 43
Qwen: Qwen3 VL 235B A22B Thinking vs Z.ai: GLM 5.3 Flash qwen/qwen3-vl-235b-a22b-thinking 4 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 4.7 Flash deepseek/deepseek-v4-flash-0731 33 z-ai/glm-4.7-flash 5
Meta: Llama 4 Maverick vs MoonshotAI: Kimi K3 meta-llama/llama-4-maverick 5 moonshotai/kimi-k3 39
OpenAI: gpt-oss-120b vs Qwen: Qwen3 14B openai/gpt-oss-120b 36 qwen/qwen3-14b 4
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 32B moonshotai/kimi-k2.6 33 qwen/qwen3-32b 4
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3-235B-A22B deepseek/deepseek-v4-flash 25 qwen/qwen3-235b-a22b 4
DeepSeek: DeepSeek V4 Pro 0423 vs MythoMax 13B deepseek/deepseek-v4-pro 26 gryphe/mythomax-l2-13b 5
google/gemma-4-12B-it vs Google: Gemma 4 31B google/gemma-4-12b-it 4 google/gemma-4-31b-it 25
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-5.5 deepseek/deepseek-v4.1-flash 23 openai/gpt-5.5 4
MoonshotAI: Kimi K2.7 Code vs OpenAI: GPT-5.6 Luna moonshotai/kimi-k2.7-code 19 openai/gpt-5.6-luna 3
OpenAI: GPT-5.6 Sol vs Z.ai: GLM 5.2 openai/gpt-5.6-sol 4 z-ai/glm-5.2 44
DeepSeek V4 Pro 0813 vs Z.ai: GLM 5.3 deepseek/deepseek-v4-pro-0813 2 z-ai/glm-5.3 43
Google: Gemini 2.5 Flash Lite vs Z.ai: GLM 5.3 Flash google/gemini-2.5-flash-lite 2 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.5 Flash Lite deepseek/deepseek-v4-flash-0731 33 google/gemini-3.5-flash-lite 4
Google: Gemini 3.6 Flash vs MoonshotAI: Kimi K3 google/gemini-3.6-flash 4 moonshotai/kimi-k3 39
Google: Gemini 3.7 Flash vs OpenAI: gpt-oss-120b google/gemini-3.7-flash 4 openai/gpt-oss-120b 36
Google: Gemini 3.8 Flash vs MoonshotAI: Kimi K2.6 google/gemini-3.8-flash 4 moonshotai/kimi-k2.6 33
DeepSeek: DeepSeek V4 Flash 0423 vs GLM 5.2 Fast on Fireworks deepseek/deepseek-v4-flash 25 z-ai/glm-5.2-fast 4
DeepSeek: DeepSeek V4 Pro 0423 vs GLM 5.3 Fast on Fireworks deepseek/deepseek-v4-pro 26 z-ai/glm-5.3-fast 4
Google: Gemma 4 31B vs OpenAI: GPT-4.1 google/gemma-4-31b-it 25 openai/gpt-4.1 4
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-4.1 Mini deepseek/deepseek-v4.1-flash 23 openai/gpt-4.1-mini 3
DeepSeek V4 Flash 0731 Fast vs MoonshotAI: Kimi K2.7 Code deepseek/deepseek-v4-flash-0731-fast 4 moonshotai/kimi-k2.7-code 19
Qwen3.5 Flash vs Z.ai: GLM 5.2 qwen/qwen3.5-flash 2 z-ai/glm-5.2 44
Qwen3.5 Plus vs Z.ai: GLM 5.3 qwen/qwen3.5-plus 2 z-ai/glm-5.3 43
Qwen3.7 Plus vs Z.ai: GLM 5.3 Flash qwen/qwen3.7-plus 2 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.8 Flash deepseek/deepseek-v4-flash-0731 33 qwen/qwen3.8-flash 5
MoonshotAI: Kimi K3 vs SpaceXAI: Grok 4.3 moonshotai/kimi-k3 39 x-ai/grok-4.3 3
OpenAI: gpt-oss-120b vs SpaceXAI: Grok 4.5 openai/gpt-oss-120b 36 x-ai/grok-4.5 3
MoonshotAI: Kimi K2.6 vs SpaceXAI: Grok 4.6 moonshotai/kimi-k2.6 33 x-ai/grok-4.6 3
DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: GPT-5 Mini deepseek/deepseek-v4-flash 25 openai/gpt-5-mini 3
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: GPT-5 Nano deepseek/deepseek-v4-pro 26 openai/gpt-5-nano 4
Google: Gemma 4 31B vs OpenAI: GPT-5.4 Mini google/gemma-4-31b-it 25 openai/gpt-5.4-mini 4
DeepSeek: DeepSeek V4.1 Flash vs KAT Coder Air V2.5 deepseek/deepseek-v4.1-flash 23 kwaipilot/kat-coder-air-v2.5 2
KAT Coder Pro V2 vs MoonshotAI: Kimi K2.7 Code kwaipilot/kat-coder-pro-v2 2 moonshotai/kimi-k2.7-code 19
KAT Coder Pro V2.5 vs Z.ai: GLM 5.2 kwaipilot/kat-coder-pro-v2.5 2 z-ai/glm-5.2 44
Mistral: Mistral Small 4 vs Z.ai: GLM 5.3 mistralai/mistral-small-2603 4 z-ai/glm-5.3 43
MoonshotAI: Kimi K2 Thinking vs Z.ai: GLM 5.3 Flash moonshotai/kimi-k2-thinking 4 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3.5 Lightning deepseek/deepseek-v4-flash-0731 33 nvidia/nemotron-3.5-lightning 4
MoonshotAI: Kimi K3 vs Qwen: Qwen3 30B A3B Instruct 2507 moonshotai/kimi-k3 39 qwen/qwen3-30b-a3b-instruct-2507 2
OpenAI: gpt-oss-120b vs Qwen3 Coder 480B A35B Instruct openai/gpt-oss-120b 36 qwen/qwen3-coder-480b-a35b-instruct 3
MoonshotAI: Kimi K2.6 vs Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo moonshotai/kimi-k2.6 33 qwen/qwen3-coder-480b-a35b-instruct-turbo 4
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3.6 Plus deepseek/deepseek-v4-flash 25 qwen/qwen3.6-plus 3
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3.8-Flash-Next deepseek/deepseek-v4-pro 26 qwen/qwen3.8-flash-next 2
Google: Gemma 4 31B vs StepFun: Step 3.7 Flash google/gemma-4-31b-it 25 stepfun/step-3.7-flash 3
DeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok Build 0.1 deepseek/deepseek-v4.1-flash 23 x-ai/grok-build-0.1 3
MiniMax: MiniMax M2 vs MoonshotAI: Kimi K2.7 Code minimax/minimax-m2 4 moonshotai/kimi-k2.7-code 19
MiniMax M2.5 Highspeed vs Z.ai: GLM 5.2 minimax/minimax-m2.5-highspeed 4 z-ai/glm-5.2 44
DeepSeek: DeepSeek V3.2 Exp vs Z.ai: GLM 5.3 deepseek/deepseek-v3.2-exp 3 z-ai/glm-5.3 43
DeepSeek: DeepSeek V3.1 Terminus vs Z.ai: GLM 5.3 Flash deepseek/deepseek-v3.1-terminus 3 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs IBM: Granite 4.2 8B deepseek/deepseek-v4-flash-0731 33 ibm-granite/granite-4.2-8b 3
inclusionAI: Ling 3.0 Flash vs MoonshotAI: Kimi K3 inclusionai/ling-3.0-flash 4 moonshotai/kimi-k3 39
mistralai/Mistral-Nemo-Instruct-2407 vs OpenAI: gpt-oss-120b mistralai/mistral-nemo-instruct-2407 3 openai/gpt-oss-120b 36
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 4.5 Air moonshotai/kimi-k2.6 33 z-ai/glm-4.5-air 3
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.