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
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 4.5 Air	`deepseek/deepseek-v4-flash-0731`	35	`z-ai/glm-4.5-air`	1
DeepSeek: DeepSeek V4.1 Flash vs GLM 4.5 Air	`deepseek/deepseek-v4.1-flash`	37	`zai-org/glm-4.5-air`	2
OpenAI: gpt-oss-120b vs GLM 4.6V	`openai/gpt-oss-120b`	37	`zai-org/glm-4.6v`	2
@cf/aisingapore/gemma-sea-lion-v4-27b-it vs Qwen: Qwen3.8 27B	`aisingapore/gemma-sea-lion-v4-27b-it`	1	`qwen/qwen3.8-27b`	33
ByteDance: UI-TARS 7B vs MoonshotAI: Kimi K2.6	`bytedance/ui-tars-1.5-7b`	2	`moonshotai/kimi-k2.6`	27
Cohere Embed v4.0 vs DeepSeek: DeepSeek V4.1 Flash 1017	`cohere/embed-v4.0`	2	`deepseek/deepseek-v4.1-flash-1017`	24
Inception: Mercury 2 vs MiniMax: MiniMax M3	`inception/mercury-2`	1	`minimax/minimax-m3`	25
@cf/meta/llama-3.2-11b-vision-instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-3.2-11b-vision-instruct`	1	`moonshotai/kimi-k2.7-code`	21
Llama 3.2 3B vs Z.ai: GLM 5.2	`meta-llama/llama-3.2-3b`	2	`z-ai/glm-5.2`	50
Llama 3.3 70B vs Z.ai: GLM 5.3	`meta-llama/llama-3.3-70b`	2	`z-ai/glm-5.3`	50
@cf/mistralai/mistral-small-3.1-24b-instruct vs Z.ai: GLM 5.3 Flash	`mistralai/mistral-small-3.1-24b-instruct`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Nemotron Nano 12B v2 VL	`moonshotai/kimi-k3`	45	`nvidia/nemotron-nano-12b-v2-vl`	2
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-4o	`deepseek/deepseek-v4-flash-0731`	35	`openai/gpt-4o`	2
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-4o-mini	`deepseek/deepseek-v4.1-flash`	37	`openai/gpt-4o-mini`	2
OpenAI: gpt-oss-120b vs Qwen: Qwen2.5 VL 72B Instruct	`openai/gpt-oss-120b`	37	`qwen/qwen2.5-vl-72b-instruct`	2
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.8 27B	`qwen/qwen3-235b-a22b-thinking-2507`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs Qwen3 VL 235B	`moonshotai/kimi-k2.6`	27	`qwen/qwen3-vl-235b-a22b`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR	`deepseek/deepseek-v4.1-flash-1017`	24	`intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar`	1
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b vs MiniMax: MiniMax M3	`deepseek/deepseek-r1-distill-qwen-32b`	1	`minimax/minimax-m3`	25
Meta: Llama 3.2 3B Instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-3.2-3b-instruct`	1	`moonshotai/kimi-k2.7-code`	21
alia-salamandra:40b vs Z.ai: GLM 5.2	`bsc-lt/alia-40b-instruct-2601`	1	`z-ai/glm-5.2`	50
Cloudflare Clairic vs Z.ai: GLM 5.3	`cloudflare/clairic`	1	`z-ai/glm-5.3`	50
Cloudflare Clef-Flash vs Z.ai: GLM 5.3 Flash	`cloudflare/clef-flash`	2	`z-ai/glm-5.3-flash`	48
Nano Banana 2 vs MoonshotAI: Kimi K3	`google/gemini-3.1-flash-image`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Nano Banana 2	`deepseek/deepseek-v4-flash-0731`	35	`google/gemini-3.1-flash-image-preview`	2
DeepSeek: DeepSeek V4.1 Flash vs Nemotron Nano 3 Omni	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3-nano-omni`	2
OpenAI: gpt-oss-120b vs Qwen3 Omni 30B A3B Thinking	`openai/gpt-oss-120b`	37	`qwen/qwen3-omni-30b-a3b-thinking`	2
Qwen: Qwen3.8 27B vs AutoGLM Phone 9B Multilingual	`qwen/qwen3.8-27b`	33	`zai-org/autoglm-phone-9b-multilingual`	2
MoonshotAI: Kimi K2.6 vs GLM 4.5V	`moonshotai/kimi-k2.6`	27	`zai-org/glm-4.5v`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs WizardLM 2 8x22B	`deepseek/deepseek-v4.1-flash-1017`	24	`microsoft/wizardlm-2-8x22b`	2
DeepSeek R1 Turbo vs MiniMax: MiniMax M3	`deepseek/deepseek-r1-turbo`	2	`minimax/minimax-m3`	25
@cf/meta/llama-3.2-1b-instruct vs MoonshotAI: Kimi K2.7 Code	`meta-llama/llama-3.2-1b-instruct`	1	`moonshotai/kimi-k2.7-code`	21
Conversation Summary vs Z.ai: GLM 5.2	`neurometric/conversation-summary`	1	`z-ai/glm-5.2`	50
Document Structured Extraction vs Z.ai: GLM 5.3	`neurometric/document-structured-extraction`	1	`z-ai/glm-5.3`	50
Grounded Document QA vs Z.ai: GLM 5.3 Flash	`neurometric/grounded-document-qa`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen: Qwen3 8B	`moonshotai/kimi-k3`	45	`qwen/qwen3-8b`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3 32B	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3-32b`	1
AionLabs: Aion-RP 1.0 (8B) vs DeepSeek: DeepSeek V4.1 Flash	`aion-labs/aion-rp-llama-3.1-8b`	1	`deepseek/deepseek-v4.1-flash`	37
granite-4.1-8b vs OpenAI: gpt-oss-120b	`ibm-granite/granite-4.1-8b`	1	`openai/gpt-oss-120b`	37
Jina AI: Jina Code Embeddings 0.5b vs Qwen: Qwen3.8 27B	`jina-ai/jina-code-embeddings-0.5b`	1	`qwen/qwen3.8-27b`	33
Jina AI: Jina Code Embeddings 1.5b vs MoonshotAI: Kimi K2.6	`jina-ai/jina-code-embeddings-1.5b`	1	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Jina AI: Jina Embeddings v4	`deepseek/deepseek-v4.1-flash-1017`	24	`jina-ai/jina-embeddings-v4`	1
Jina AI: Jina Embeddings v5 Omni Small vs MiniMax: MiniMax M3	`jina-ai/jina-embeddings-v5-omni-small`	1	`minimax/minimax-m3`	25
Jina AI: Jina Embeddings v5 Text Small vs MoonshotAI: Kimi K2.7 Code	`jina-ai/jina-embeddings-v5-text-small`	1	`moonshotai/kimi-k2.7-code`	21
Mistral: Mistral Small 3 vs Z.ai: GLM 5.2	`mistralai/mistral-small-24b-instruct-2501`	2	`z-ai/glm-5.2`	50
Classification Router vs Z.ai: GLM 5.3	`neurometric/classification-router`	1	`z-ai/glm-5.3`	50
tool-choice vs Z.ai: GLM 5.3 Flash	`neurometric/tool-choice`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen/Qwen-AgentWorld-35B-A3B	`moonshotai/kimi-k3`	45	`qwen/qwen-agentworld-35b-a3b`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen/Qwen2.5-72B-Instruct	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen2.5-72b-instruct`	2
DeepSeek: DeepSeek V4.1 Flash vs @cf/qwen/qwen2.5-coder-32b-instruct	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen2.5-coder-32b-instruct`	1
OpenAI: gpt-oss-120b vs @cf/qwen/qwen3-30b-a3b-fp8	`openai/gpt-oss-120b`	37	`qwen/qwen3-30b-a3b-fp8`	1
Qwen/Qwen3.5-2B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-2b`	1	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs Qwen/Qwen3.5-4B	`moonshotai/kimi-k2.6`	27	`qwen/qwen3.5-4b`	1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen/WebWorld-8B	`deepseek/deepseek-v4.1-flash-1017`	24	`qwen/webworld-8b`	1
MiniMax: MiniMax M3 vs TheDrummer: Skyfall 36B V2	`minimax/minimax-m3`	25	`thedrummer/skyfall-36b-v2`	2
MoonshotAI: Kimi K2.7 Code vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B	`moonshotai/kimi-k2.7-code`	21	`xiaomi/mimo-v2.6-distill-qwen-9b`	1
Z.ai: GLM 5.2 vs 0GM-1.0-35B-A3B-SIA	`z-ai/glm-5.2`	50	`zero-g/0gm-1.0-35b-a3b-sia`	1
@cf/meta/llama-3.1-8b-instruct-fp8 vs Z.ai: GLM 5.3	`meta-llama/llama-3.1-8b-instruct-fp8`	1	`z-ai/glm-5.3`	50
TypeSafe AI Jev vs Z.ai: GLM 5.3 Flash	`typesafe-ai/jev`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Voyage 3 Large	`moonshotai/kimi-k3`	45	`voyage/voyage-3-large`	2
DeepSeek: DeepSeek V4 Flash 0731 vs apertus-70b	`deepseek/deepseek-v4-flash-0731`	35	`swiss-ai/apertus-70b-instruct`	2
DeepSeek: DeepSeek V4.1 Flash vs @cf/meta/llama-3.3-70b-instruct-fp8-fast	`deepseek/deepseek-v4.1-flash`	37	`meta-llama/llama-3.3-70b-instruct-fp8-fast`	1
OpenAI: gpt-oss-120b vs @cf/qwen/qwq-32b	`openai/gpt-oss-120b`	37	`qwen/qwq-32b`	1
OpenAI: GPT-3.5 Turbo vs Qwen: Qwen3.8 27B	`openai/gpt-3.5-turbo`	2	`qwen/qwen3.8-27b`	33
elephant-1 vs MoonshotAI: Kimi K2.6	`decision-models/baseten-elephant-9b-latest`	2	`moonshotai/kimi-k2.6`	27
joey-1 vs DeepSeek: DeepSeek V4.1 Flash 1017	`decision-models/baseten-joey-2b-latest`	2	`deepseek/deepseek-v4.1-flash-1017`	24
mammoth-1 vs MiniMax: MiniMax M3	`decision-models/baseten-mammoth-27b-latest`	2	`minimax/minimax-m3`	25
Microsoft: Phi 4 vs MoonshotAI: Kimi K2.7 Code	`microsoft/phi-4`	2	`moonshotai/kimi-k2.7-code`	21
Reka Edge 2603 vs Z.ai: GLM 5.2	`reka/reka-edge-2603`	1	`z-ai/glm-5.2`	50
Decart Lucy 2.5 vs Z.ai: GLM 5.3	`decart/lucy-2.5`	1	`z-ai/glm-5.3`	50
Decart Lucy Restyle 2 vs Z.ai: GLM 5.3 Flash	`decart/lucy-restyle-2`	1	`z-ai/glm-5.3-flash`	48
Decart Lucy VTON 3.5 vs MoonshotAI: Kimi K3	`decart/lucy-vton-3.5`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax H3 Max	`deepseek/deepseek-v4-flash-0731`	35	`minimax/h3-max`	1
DeepSeek: DeepSeek V4.1 Flash vs xAI Grok Imagine Video	`deepseek/deepseek-v4.1-flash`	37	`x-ai/grok-imagine-video`	1
Decision Models s1-pro (EU) vs OpenAI: gpt-oss-120b	`decisionmodelsio-eu/s1-pro`	1	`openai/gpt-oss-120b`	37
Decision Models s1-pro-2 (EU) vs Qwen: Qwen3.8 27B	`decisionmodelsio-eu/s1-pro-2`	1	`qwen/qwen3.8-27b`	33
Decision Models s1-pro-3 (EU) vs MoonshotAI: Kimi K2.6	`decisionmodelsio-eu/s1-pro-3`	1	`moonshotai/kimi-k2.6`	27
Decision Models s1-pro (GLOBAL) vs DeepSeek: DeepSeek V4.1 Flash 1017	`decisionmodelsio/s1-pro`	1	`deepseek/deepseek-v4.1-flash-1017`	24
Decision Models s1-pro-2 (GLOBAL) vs MiniMax: MiniMax M3	`decisionmodelsio/s1-pro-2`	1	`minimax/minimax-m3`	25
Decision Models s1-pro-3 (GLOBAL) vs MoonshotAI: Kimi K2.7 Code	`decisionmodelsio/s1-pro-3`	1	`moonshotai/kimi-k2.7-code`	21
DeepSeek OCR vs Z.ai: GLM 5.2	`deepseek/deepseek-ocr`	1	`z-ai/glm-5.2`	50
DeepSeek OCR 2 vs Z.ai: GLM 5.3	`deepseek/deepseek-ocr-2`	2	`z-ai/glm-5.3`	50
Google: Gemini 3.8 Flash Lite TTS vs Z.ai: GLM 5.3 Flash	`google/gemini-3.8-flash-lite-tts`	1	`z-ai/glm-5.3-flash`	48
Google: Gemini 3.8 Flash TTS vs MoonshotAI: Kimi K3	`google/gemini-3.8-flash-tts`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs MythoMax 13B	`deepseek/deepseek-v4-flash-0731`	35	`gryphe/mythomax-l2-13b`	2
DeepSeek: DeepSeek V4.1 Flash vs Jina AI: Jina Clip v1	`deepseek/deepseek-v4.1-flash`	37	`jina-ai/jina-clip-v1`	1
Jina AI: Jina Clip v2 vs OpenAI: gpt-oss-120b	`jina-ai/jina-clip-v2`	1	`openai/gpt-oss-120b`	37
Jina AI: Jina Colbert v2 vs Qwen: Qwen3.8 27B	`jina-ai/jina-colbert-v2`	1	`qwen/qwen3.8-27b`	33
Jina AI: Jina Embeddings v2 Base Code vs MoonshotAI: Kimi K2.6	`jina-ai/jina-embeddings-v2-base-code`	1	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Jina AI: Jina Embeddings v2 Base DE	`deepseek/deepseek-v4.1-flash-1017`	24	`jina-ai/jina-embeddings-v2-base-de`	1
Jina AI: Jina Embeddings v2 Base EN vs MiniMax: MiniMax M3	`jina-ai/jina-embeddings-v2-base-en`	1	`minimax/minimax-m3`	25
Jina AI: Jina Embeddings v2 Base ES vs MoonshotAI: Kimi K2.7 Code	`jina-ai/jina-embeddings-v2-base-es`	1	`moonshotai/kimi-k2.7-code`	21
Jina AI: Jina Embeddings v2 Base ZH vs Z.ai: GLM 5.2	`jina-ai/jina-embeddings-v2-base-zh`	1	`z-ai/glm-5.2`	50
Jina AI: Jina Embeddings v3 vs Z.ai: GLM 5.3	`jina-ai/jina-embeddings-v3`	1	`z-ai/glm-5.3`	50
Jina AI: Jina Embeddings v5 Omni Nano vs Z.ai: GLM 5.3 Flash	`jina-ai/jina-embeddings-v5-omni-nano`	1	`z-ai/glm-5.3-flash`	48
Jina AI: Jina Embeddings v5 Text Nano vs MoonshotAI: Kimi K3	`jina-ai/jina-embeddings-v5-text-nano`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Sao10K/L3-8B-Lunaris-v1-Turbo	`deepseek/deepseek-v4-flash-0731`	35	`sao10k/l3-8b-lunaris-v1-turbo`	2
DeepSeek: DeepSeek V4.1 Flash vs Llama 3 8B Stheno V3.2	`deepseek/deepseek-v4.1-flash`	37	`Sao10K/L3-8B-Stheno-v3.2`	2
OpenAI: gpt-oss-120b vs OpenAI Text Embedding 3 Large	`openai/gpt-oss-120b`	37	`openai/text-embedding-3-large`	2
OpenAI Text Embedding 3 Small vs Qwen: Qwen3.8 27B	`openai/text-embedding-3-small`	2	`qwen/qwen3.8-27b`	33