Find a model

Browse the full catalog →
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
OpenAI: GPT-4o-mini vs Qwen: Qwen3.8 27B openai/gpt-4o-mini 2 qwen/qwen3.8-27b 33
MoonshotAI: Kimi K2.6 vs gpt-oss-safeguard-20b moonshotai/kimi-k2.6 27 openai/gpt-oss-safeguard-20b 1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen: Qwen2.5 VL 72B Instruct deepseek/deepseek-v4.1-flash-1017 24 qwen/qwen2.5-vl-72b-instruct 2
MiniMax: MiniMax M3 vs Qwen: Qwen3 235B A22B Thinking 2507 minimax/minimax-m3 24 qwen/qwen3-235b-a22b-thinking-2507 2
MoonshotAI: Kimi K2.7 Code vs Qwen3 VL 235B moonshotai/kimi-k2.7-code 19 qwen/qwen3-vl-235b-a22b 2
ERNIE 4.5 21B A3B vs Z.ai: GLM 5.3 baidu/ernie-4.5-21B-a3b 2 z-ai/glm-5.3 50
Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR vs Z.ai: GLM 5.2 intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar 1 z-ai/glm-5.2 48
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b vs Z.ai: GLM 5.3 Flash deepseek/deepseek-r1-distill-qwen-32b 1 z-ai/glm-5.3-flash 48
alia-salamandra:40b vs MoonshotAI: Kimi K3 bsc-lt/alia-40b-instruct-2601 1 moonshotai/kimi-k3 45
Cloudflare Clairic vs DeepSeek: DeepSeek V4 Flash 0731 cloudflare/clairic 1 deepseek/deepseek-v4-flash-0731 35
Cloudflare Clef-Flash vs DeepSeek: DeepSeek V4.1 Flash cloudflare/clef-flash 2 deepseek/deepseek-v4.1-flash 37
Nano Banana 2 vs OpenAI: gpt-oss-120b google/gemini-3.1-flash-image 2 openai/gpt-oss-120b 38
Nano Banana 2 vs Qwen: Qwen3.8 27B google/gemini-3.1-flash-image-preview 2 qwen/qwen3.8-27b 33
MoonshotAI: Kimi K2.6 vs Qwen3 Omni 30B A3B Thinking moonshotai/kimi-k2.6 27 qwen/qwen3-omni-30b-a3b-thinking 2
DeepSeek: DeepSeek V4.1 Flash 1017 vs AutoGLM Phone 9B Multilingual deepseek/deepseek-v4.1-flash-1017 24 zai-org/autoglm-phone-9b-multilingual 2
MiniMax: MiniMax M3 vs GLM 4.5V minimax/minimax-m3 24 zai-org/glm-4.5v 2
WizardLM 2 8x22B vs MoonshotAI: Kimi K2.7 Code microsoft/wizardlm-2-8x22b 2 moonshotai/kimi-k2.7-code 19
DeepSeek R1 Turbo vs Z.ai: GLM 5.3 deepseek/deepseek-r1-turbo 2 z-ai/glm-5.3 50
@cf/meta/llama-3.2-1b-instruct vs Z.ai: GLM 5.2 meta-llama/llama-3.2-1b-instruct 1 z-ai/glm-5.2 48
Conversation Summary vs Z.ai: GLM 5.3 Flash neurometric/conversation-summary 1 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs Document Structured Extraction moonshotai/kimi-k3 45 neurometric/document-structured-extraction 1
DeepSeek: DeepSeek V4 Flash 0731 vs Grounded Document QA deepseek/deepseek-v4-flash-0731 35 neurometric/grounded-document-qa 1
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3 8B deepseek/deepseek-v4.1-flash 37 qwen/qwen3-8b 1
AionLabs: Aion-RP 1.0 (8B) vs OpenAI: gpt-oss-120b aion-labs/aion-rp-llama-3.1-8b 1 openai/gpt-oss-120b 38
granite-4.1-8b vs Qwen: Qwen3.8 27B ibm-granite/granite-4.1-8b 1 qwen/qwen3.8-27b 33
Jina AI: Jina Code Embeddings 0.5b vs MoonshotAI: Kimi K2.6 jina-ai/jina-code-embeddings-0.5b 1 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Jina AI: Jina Code Embeddings 1.5b deepseek/deepseek-v4.1-flash-1017 24 jina-ai/jina-code-embeddings-1.5b 1
Jina AI: Jina Embeddings v4 vs MiniMax: MiniMax M3 jina-ai/jina-embeddings-v4 1 minimax/minimax-m3 24
Jina AI: Jina Embeddings v5 Omni Small vs MoonshotAI: Kimi K2.7 Code jina-ai/jina-embeddings-v5-omni-small 1 moonshotai/kimi-k2.7-code 19
Jina AI: Jina Embeddings v5 Text Small vs Z.ai: GLM 5.3 jina-ai/jina-embeddings-v5-text-small 1 z-ai/glm-5.3 50
Microsoft Decision-1 vs Z.ai: GLM 5.2 microsoft/microsoft-decision-1 1 z-ai/glm-5.2 48
Mistral: Mistral Small 3 vs Z.ai: GLM 5.3 Flash mistralai/mistral-small-24b-instruct-2501 2 z-ai/glm-5.3-flash 48
Voxtral Small 24B vs MoonshotAI: Kimi K3 mistralai/voxtral-small-24b 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4 Flash 0731 vs Classification Router deepseek/deepseek-v4-flash-0731 35 neurometric/classification-router 1
DeepSeek: DeepSeek V4.1 Flash vs tool-choice deepseek/deepseek-v4.1-flash 37 neurometric/tool-choice 1
OpenAI: gpt-oss-120b vs Qwen/Qwen-AgentWorld-35B-A3B openai/gpt-oss-120b 38 qwen/qwen-agentworld-35b-a3b 1
Qwen/Qwen2.5-72B-Instruct vs Qwen: Qwen3.8 27B qwen/qwen2.5-72b-instruct 2 qwen/qwen3.8-27b 33
MoonshotAI: Kimi K2.6 vs Qwen2.5-Coder-3B-Instruct moonshotai/kimi-k2.6 27 qwen/qwen2.5-coder-3b-instruct 1
DeepSeek: DeepSeek V4.1 Flash 1017 vs @cf/qwen/qwen3-30b-a3b-fp8 deepseek/deepseek-v4.1-flash-1017 24 qwen/qwen3-30b-a3b-fp8 1
MiniMax: MiniMax M3 vs Qwen3-Embedding 4B minimax/minimax-m3 24 qwen/qwen3-embedding-4b 1
MoonshotAI: Kimi K2.7 Code vs Qwen/Qwen3.5-2B moonshotai/kimi-k2.7-code 19 qwen/qwen3.5-2b 1
Qwen/Qwen3.5-4B vs Z.ai: GLM 5.3 qwen/qwen3.5-4b 1 z-ai/glm-5.3 50
Qwen/WebWorld-8B vs Z.ai: GLM 5.2 qwen/webworld-8b 1 z-ai/glm-5.2 48
TheDrummer: Skyfall 36B V2 vs Z.ai: GLM 5.3 Flash thedrummer/skyfall-36b-v2 2 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B moonshotai/kimi-k3 45 xiaomi/mimo-v2.6-distill-qwen-9b 1
DeepSeek: DeepSeek V4 Flash 0731 vs 0GM-1.0-35B-A3B-SIA deepseek/deepseek-v4-flash-0731 35 zero-g/0gm-1.0-35b-a3b-sia 1
DeepSeek: DeepSeek V4.1 Flash vs @cf/meta/llama-3.1-8b-instruct-fp8 deepseek/deepseek-v4.1-flash 37 meta-llama/llama-3.1-8b-instruct-fp8 1
OpenAI: gpt-oss-120b vs Qwen3 Embedding 8B openai/gpt-oss-120b 38 Qwen/Qwen3-Embedding-8B 2
Qwen: Qwen3.8 27B vs TypeSafe AI Jev qwen/qwen3.8-27b 33 typesafe-ai/jev 1
MoonshotAI: Kimi K2.6 vs Voyage 3 Large moonshotai/kimi-k2.6 27 voyage/voyage-3-large 2
DeepSeek: DeepSeek V4.1 Flash 1017 vs apertus-70b deepseek/deepseek-v4.1-flash-1017 24 swiss-ai/apertus-70b-instruct 2
@cf/meta/llama-3.3-70b-instruct-fp8-fast vs MiniMax: MiniMax M3 meta-llama/llama-3.3-70b-instruct-fp8-fast 1 minimax/minimax-m3 24
MoonshotAI: Kimi K2.7 Code vs @cf/qwen/qwq-32b moonshotai/kimi-k2.7-code 19 qwen/qwq-32b 1
OpenAI: GPT-3.5 Turbo vs Z.ai: GLM 5.3 openai/gpt-3.5-turbo 2 z-ai/glm-5.3 50
Microsoft: Phi 4 vs Z.ai: GLM 5.2 microsoft/phi-4 2 z-ai/glm-5.2 48
Reka Edge 2603 vs Z.ai: GLM 5.3 Flash reka/reka-edge-2603 1 z-ai/glm-5.3-flash 48
Decart Lucy 2.5 vs MoonshotAI: Kimi K3 decart/lucy-2.5 1 moonshotai/kimi-k3 45
Decart Lucy Restyle 2 vs DeepSeek: DeepSeek V4 Flash 0731 decart/lucy-restyle-2 1 deepseek/deepseek-v4-flash-0731 35
Decart Lucy VTON 3.5 vs DeepSeek: DeepSeek V4.1 Flash decart/lucy-vton-3.5 1 deepseek/deepseek-v4.1-flash 37
MiniMax H3 Max vs OpenAI: gpt-oss-120b minimax/h3-max 1 openai/gpt-oss-120b 38
Qwen: Qwen3.8 27B vs xAI Grok Imagine Video qwen/qwen3.8-27b 33 x-ai/grok-imagine-video 1
Decision Models s1-pro (EU) vs MoonshotAI: Kimi K2.6 decisionmodelsio-eu/s1-pro 1 moonshotai/kimi-k2.6 27
Decision Models s1-pro-2 (EU) vs DeepSeek: DeepSeek V4.1 Flash 1017 decisionmodelsio-eu/s1-pro-2 1 deepseek/deepseek-v4.1-flash-1017 24
Decision Models s1-pro-3 (EU) vs MiniMax: MiniMax M3 decisionmodelsio-eu/s1-pro-3 1 minimax/minimax-m3 24
Decision Models s1-pro (GLOBAL) vs MoonshotAI: Kimi K2.7 Code decisionmodelsio/s1-pro 1 moonshotai/kimi-k2.7-code 19
Decision Models s1-pro-2 (GLOBAL) vs Z.ai: GLM 5.3 decisionmodelsio/s1-pro-2 1 z-ai/glm-5.3 50
Decision Models s1-pro-3 (GLOBAL) vs Z.ai: GLM 5.2 decisionmodelsio/s1-pro-3 1 z-ai/glm-5.2 48
DeepSeek OCR vs Z.ai: GLM 5.3 Flash deepseek/deepseek-ocr 1 z-ai/glm-5.3-flash 48
Google: Gemini 3.8 Flash Lite TTS vs MoonshotAI: Kimi K3 google/gemini-3.8-flash-lite-tts 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.8 Flash TTS deepseek/deepseek-v4-flash-0731 35 google/gemini-3.8-flash-tts 1
DeepSeek: DeepSeek V4.1 Flash vs gemma-2b-it deepseek/deepseek-v4.1-flash 37 google/gemma-2b-it 2
MythoMax 13B vs OpenAI: gpt-oss-120b gryphe/mythomax-l2-13b 2 openai/gpt-oss-120b 38
Jina AI: Jina Clip v1 vs Qwen: Qwen3.8 27B jina-ai/jina-clip-v1 1 qwen/qwen3.8-27b 33
Jina AI: Jina Clip v2 vs MoonshotAI: Kimi K2.6 jina-ai/jina-clip-v2 1 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Jina AI: Jina Colbert v2 deepseek/deepseek-v4.1-flash-1017 24 jina-ai/jina-colbert-v2 1
Jina AI: Jina Embeddings v2 Base Code vs MiniMax: MiniMax M3 jina-ai/jina-embeddings-v2-base-code 1 minimax/minimax-m3 24
Jina AI: Jina Embeddings v2 Base DE vs MoonshotAI: Kimi K2.7 Code jina-ai/jina-embeddings-v2-base-de 1 moonshotai/kimi-k2.7-code 19
Jina AI: Jina Embeddings v2 Base EN vs Z.ai: GLM 5.3 jina-ai/jina-embeddings-v2-base-en 1 z-ai/glm-5.3 50
Jina AI: Jina Embeddings v2 Base ES vs Z.ai: GLM 5.2 jina-ai/jina-embeddings-v2-base-es 1 z-ai/glm-5.2 48
Jina AI: Jina Embeddings v2 Base ZH vs Z.ai: GLM 5.3 Flash jina-ai/jina-embeddings-v2-base-zh 1 z-ai/glm-5.3-flash 48
Jina AI: Jina Embeddings v3 vs MoonshotAI: Kimi K3 jina-ai/jina-embeddings-v3 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4 Flash 0731 vs Jina AI: Jina Embeddings v5 Omni Nano deepseek/deepseek-v4-flash-0731 35 jina-ai/jina-embeddings-v5-omni-nano 1
DeepSeek: DeepSeek V4.1 Flash vs Jina AI: Jina Embeddings v5 Text Nano deepseek/deepseek-v4.1-flash 37 jina-ai/jina-embeddings-v5-text-nano 1
Nomic Embed Text vs OpenAI: gpt-oss-120b nomic-ai/nomic-embed-text 2 openai/gpt-oss-120b 38
Qwen: Qwen3.8 27B vs Sao10K/L3-8B-Lunaris-v1-Turbo qwen/qwen3.8-27b 33 sao10k/l3-8b-lunaris-v1-turbo 2
MoonshotAI: Kimi K2.6 vs Llama 3 8B Stheno V3.2 moonshotai/kimi-k2.6 27 Sao10K/L3-8B-Stheno-v3.2 2
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI Text Embedding 3 Large deepseek/deepseek-v4.1-flash-1017 24 openai/text-embedding-3-large 2
MiniMax: MiniMax M3 vs OpenAI Text Embedding 3 Small minimax/minimax-m3 24 openai/text-embedding-3-small 2
MoonshotAI: Kimi K2.7 Code vs OpenAI Text Embedding Ada 002 moonshotai/kimi-k2.7-code 19 openai/text-embedding-ada-002 2
Decision Models s1-fast (EU) vs Z.ai: GLM 5.3 decisionmodelsio-eu/s1-fast 1 z-ai/glm-5.3 50
Decision Models s1-fast-2 (EU) vs Z.ai: GLM 5.2 decisionmodelsio-eu/s1-fast-2 1 z-ai/glm-5.2 48
Decision Models s1-fast (GLOBAL) vs Z.ai: GLM 5.3 Flash decisionmodelsio/s1-fast 1 z-ai/glm-5.3-flash 48
Decision Models s1-fast-2 (GLOBAL) vs MoonshotAI: Kimi K3 decisionmodelsio/s1-fast-2 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4.1 Flash vs Nemotron-3.5-Lightning deepseek/deepseek-v4.1-flash 37 nvidia/nemotron-3_5-lightning 2
OpenAI: gpt-oss-120b vs openbmb/MiniCPM-V-4_5 openai/gpt-oss-120b 38 openbmb/MiniCPM-V-4_5 2
devstral-2-123b vs Qwen: Qwen3.8 27B mistralai/devstral-2-123b 1 qwen/qwen3.8-27b 33
magistral-small-2509 vs MoonshotAI: Kimi K2.6 mistralai/magistral-small-2509 1 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs ministral-3-3b-instruct deepseek/deepseek-v4.1-flash-1017 24 mistralai/ministral-3-3b-instruct 1
MiniMax: MiniMax M3 vs ministral-3-8b-instruct minimax/minimax-m3 24 mistralai/ministral-3-8b-instruct 1
MoonshotAI: Kimi K2.7 Code vs nemotron-nano-12b-v2 moonshotai/kimi-k2.7-code 19 nvidia/nemotron-nano-12b-v2 1
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

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