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
Google: Gemini 3.6 Flash vs Z.ai: GLM 5.3 Flash	`google/gemini-3.6-flash`	4	`z-ai/glm-5.3-flash`	48
Google: Gemini 3.7 Flash vs MoonshotAI: Kimi K3	`google/gemini-3.7-flash`	4	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 4 Argon	`deepseek/deepseek-v4-flash-0731`	35	`google/gemini-4-argon`	4
DeepSeek: DeepSeek V4.1 Flash vs Llama 4 Maverick Instruct	`deepseek/deepseek-v4.1-flash`	37	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	3
Muse Spark Open vs OpenAI: gpt-oss-120b	`meta-models/muse-spark-open`	4	`openai/gpt-oss-120b`	38
Nemotron Super 3.5 vs Qwen: Qwen3.8 27B	`nvidia/nemotron-3.5-super-vl-120b-a12b`	3	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs StepFun: Step 5 Preview	`moonshotai/kimi-k2.6`	27	`stepfun/step-5-preview`	4
Google: Gemma 4 31B vs GLM 5.3 Fast on Fireworks	`google/gemma-4-31b-it`	26	`z-ai/glm-5.3-fast`	4
DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.3 FlashX	`deepseek/deepseek-v4-pro`	26	`z-ai/glm-5.3-flashx`	4
MiniMax: MiniMax M3 vs OpenAI: GPT-4.1 Mini	`minimax/minimax-m3`	25	`openai/gpt-4.1-mini`	3
Anthropic: Claude Sonnet 4.6 vs Z.ai: GLM 5.3	`anthropic/claude-sonnet-4.6`	3	`z-ai/glm-5.3`	50
DeepSeek V4 Flash 0731 Fast vs Z.ai: GLM 5.2	`deepseek/deepseek-v4-flash-0731-fast`	4	`z-ai/glm-5.2`	48
Qwen3.5 Flash vs Z.ai: GLM 5.3 Flash	`qwen/qwen3.5-flash`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3.5 Plus	`moonshotai/kimi-k3`	45	`qwen/qwen3.5-plus`	2
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.7 Plus	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3.7-plus`	2
DeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok 4.3	`deepseek/deepseek-v4.1-flash`	37	`x-ai/grok-4.3`	3
OpenAI: gpt-oss-120b vs Thinking Machines: Inkling Small	`openai/gpt-oss-120b`	38	`thinkingmachines/inkling-small`	4
Qwen: Qwen3.8 27B vs SpaceXAI: Grok 4.5	`qwen/qwen3.8-27b`	30	`x-ai/grok-4.5`	3
MoonshotAI: Kimi K2.6 vs SpaceXAI: Grok 4.6	`moonshotai/kimi-k2.6`	27	`x-ai/grok-4.6`	3
Google: Gemma 4 31B vs OpenAI: GPT-5 Mini	`google/gemma-4-31b-it`	26	`openai/gpt-5-mini`	3
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: GPT-5.4 Mini	`deepseek/deepseek-v4-pro`	26	`openai/gpt-5.4-mini`	4
inclusionAI: Ling 3.0 Flash vs MiniMax: MiniMax M3	`inclusionai/ling-3.0-flash`	4	`minimax/minimax-m3`	25
Ministral 3 14B Instruct vs Z.ai: GLM 5.3	`mistralai/ministral-3-14b-instruct`	3	`z-ai/glm-5.3`	50
Mistral: Mistral Large 3 2512 vs Z.ai: GLM 5.2	`mistralai/mistral-large-2512`	2	`z-ai/glm-5.2`	48
Mistral: Mistral Small 4 vs Z.ai: GLM 5.3 Flash	`mistralai/mistral-small-2603`	4	`z-ai/glm-5.3-flash`	48
moonshotai/Kimi: K2.7-Code-Highspeed vs MoonshotAI: Kimi K3	`moonshotai/kimi-k2.7-code-highspeed`	5	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3.5 Super VL	`deepseek/deepseek-v4-flash-0731`	35	`nvidia/nemotron-3.5-super-vl`	4
DeepSeek: DeepSeek V4.1 Flash vs Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3-coder-480b-a35b-instruct-turbo`	4
OpenAI: gpt-oss-120b vs Qwen3.6 Plus	`openai/gpt-oss-120b`	38	`qwen/qwen3.6-plus`	3
Qwen: Qwen3.8 27B vs StepFun: Step 3.7 Flash	`qwen/qwen3.8-27b`	30	`stepfun/step-3.7-flash`	3
MoonshotAI: Kimi K2.6 vs SpaceXAI: Grok Build 0.1	`moonshotai/kimi-k2.6`	27	`x-ai/grok-build-0.1`	3
deepseek-ai/DeepSeek-V3 vs Google: Gemma 4 31B	`deepseek/deepseek-v3`	3	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemma 3 4B	`deepseek/deepseek-v4-pro`	26	`google/gemma-3-4b-it`	3
IBM: Granite 4.2 8B vs MiniMax: MiniMax M3	`ibm-granite/granite-4.2-8b`	3	`minimax/minimax-m3`	25
Meta: Llama 3.1 70B Instruct vs Z.ai: GLM 5.3	`meta-llama/llama-3.1-70b-instruct`	4	`z-ai/glm-5.3`	50
meta-models/Muse-Glimmer-30B vs Z.ai: GLM 5.2	`meta-models/muse-glimmer-30b`	4	`z-ai/glm-5.2`	48
Mistral: Mistral Nemo vs Z.ai: GLM 5.3 Flash	`mistralai/mistral-nemo`	4	`z-ai/glm-5.3-flash`	48
mistralai/Mistral-Nemo-Instruct-2407 vs MoonshotAI: Kimi K3	`mistralai/mistral-nemo-instruct-2407`	3	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Nemotron-3-Nano-Omni-30B	`deepseek/deepseek-v4-flash-0731`	35	`nvidia/nemotron-3-nano-omni`	4
DeepSeek: DeepSeek V4.1 Flash vs GPT-OSS Safeguard 120B	`deepseek/deepseek-v4.1-flash`	37	`openai/gpt-oss-safeguard-120b`	3
OpenAI: gpt-oss-120b vs Qwen: Qwen3 VL 235B A22B Thinking	`openai/gpt-oss-120b`	38	`qwen/qwen3-vl-235b-a22b-thinking`	2
Qwen: Qwen3 VL 30B A3B Instruct vs Qwen: Qwen3.8 27B	`qwen/qwen3-vl-30b-a3b-instruct`	4	`qwen/qwen3.8-27b`	30
@cf/meta/llama-3.2-11b-vision-instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-3.2-11b-vision-instruct`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs mistralai/Mistral-Small-3.2-24B-Instruct-2506	`google/gemma-4-31b-it`	26	`mistralai/mistral-small-3.2-24b-instruct-2506`	3
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3 30B A3B	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-30b-a3b`	3
MiniMax: MiniMax M3 vs @cf/qwen/qwen2.5-coder-32b-instruct	`minimax/minimax-m3`	25	`qwen/qwen2.5-coder-32b-instruct`	2
Qwen3-235B-A22B vs Z.ai: GLM 5.3	`qwen/qwen3-235b-a22b`	3	`z-ai/glm-5.3`	50
Qwen3 Embedding 8B vs Z.ai: GLM 5.2	`qwen/qwen3-embedding-8b`	2	`z-ai/glm-5.2`	48
TypeSafe AI Jev vs Z.ai: GLM 5.3 Flash	`typesafe-ai/jev`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen MT Plus	`moonshotai/kimi-k3`	45	`qwen/qwen-mt-plus`	3
ByteDance Seedance 2.5 vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/seedance-2.5`	2	`deepseek/deepseek-v4-flash-0731`	35
ByteDance Seedance 2.0 vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/seedance-2.0`	2	`deepseek/deepseek-v4.1-flash`	37
ByteDance Seedance 2.0 Fast vs OpenAI: gpt-oss-120b	`bytedance/seedance-2.0-fast`	2	`openai/gpt-oss-120b`	38
DeepSeek OCR 2 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-ocr-2`	3	`qwen/qwen3.8-27b`	30
MythoMax 13B vs MoonshotAI: Kimi K2.6	`gryphe/mythomax-l2-13b`	4	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs MiniMax Hailuo 3 (H3)	`google/gemma-4-31b-it`	26	`minimax/hailuo-3`	2
Alibaba Wan 2.7 vs DeepSeek: DeepSeek V4 Pro 0423	`alibaba/wan-2.7`	2	`deepseek/deepseek-v4-pro`	26
Lightricks LTX 2.3 vs MiniMax: MiniMax M3	`lightricks/ltx-2.3`	2	`minimax/minimax-m3`	25
Lightricks LTX 2.3 Fast vs Z.ai: GLM 5.3	`lightricks/ltx-2.3-fast`	2	`z-ai/glm-5.3`	50
Kling Video 3.0 Omni Pro vs Z.ai: GLM 5.2	`kling/o3-pro`	2	`z-ai/glm-5.2`	48
Kling Video 3.0 Pro vs Z.ai: GLM 5.3 Flash	`kling/v3-pro`	2	`z-ai/glm-5.3-flash`	48
Google Veo 3.1 vs MoonshotAI: Kimi K3	`google/veo-3.1`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Google Veo 3.1 Fast	`deepseek/deepseek-v4-flash-0731`	35	`google/veo-3.1-fast`	2
DeepSeek: DeepSeek V4.1 Flash vs OpenAI Sora 2	`deepseek/deepseek-v4.1-flash`	37	`openai/sora-2`	2
OpenAI: gpt-oss-120b vs OpenAI Sora 2 Pro	`openai/gpt-oss-120b`	38	`openai/sora-2-pro`	2
Qwen: Qwen3.8 27B vs Runway Gen-4.5	`qwen/qwen3.8-27b`	30	`runway/gen-4.5`	2
MoonshotAI: Kimi K2.6 vs grok-4.20-0309-reasoning	`moonshotai/kimi-k2.6`	27	`x-ai/grok-4.20-reasoning`	3
Google: Gemma 4 31B vs SpaceXAI: Grok 4.20	`google/gemma-4-31b-it`	26	`x-ai/grok-4.20`	2
DeepSeek: DeepSeek V4 Pro 0423 vs GPT 5.6 Luna	`deepseek/deepseek-v4-pro`	26	`openai/gpt-5.6-luna-az`	1
MiniMax: MiniMax M3 vs GPT 5.6 Sol	`minimax/minimax-m3`	25	`openai/gpt-5.6-sol-az`	1
GPT 5.6 Sol vs Z.ai: GLM 5.3	`openai/gpt-5.6-sol-codex`	1	`z-ai/glm-5.3`	50
GPT 5.6 Terra vs Z.ai: GLM 5.2	`openai/gpt-5.6-terra-az`	1	`z-ai/glm-5.2`	48
GPT 6 Sol vs Z.ai: GLM 5.3 Flash	`openai/gpt-6-sol-codex`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-6.1 Sol	`moonshotai/kimi-k3`	45	`openai/gpt-6.1-sol`	3
DeepSeek: DeepSeek V4 Flash 0731 vs LongCat 2.0	`deepseek/deepseek-v4-flash-0731`	35	`meituan-longcat/longcat-2.0`	1
DeepSeek V4 Pro vs DeepSeek: DeepSeek V4.1 Flash	`deepseek-ai/DeepSeek-V4-Pro`	2	`deepseek/deepseek-v4.1-flash`	37
DeepSeek V4.1 Flash (rolling) vs OpenAI: gpt-oss-120b	`deepseek/deepseek-flash`	2	`openai/gpt-oss-120b`	38
DeepSeek-V4-Flash-0423 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-flash-0423`	2	`qwen/qwen3.8-27b`	30
deepseek/deepseek-v4-flash-0731-p vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-flash-0731-p`	2	`moonshotai/kimi-k2.6`	27
DeepSeek V4 Pro 0813 vs Google: Gemma 4 31B	`deepseek/deepseek-v4-pro-0813`	1	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs deepseek/deepseek-v4-pro-0813-p	`deepseek/deepseek-v4-pro`	26	`deepseek/deepseek-v4-pro-0813-p`	2
DeepSeek V4.1 Flash 1017 Fast vs MiniMax: MiniMax M3	`deepseek/deepseek-v4.1-flash-1017-fast`	2	`minimax/minimax-m3`	25
DeepSeek V4.1 Flash DST vs Z.ai: GLM 5.3	`deepseek/deepseek-v4.1-flash-dst`	2	`z-ai/glm-5.3`	50
DeepSeek V4.1 Flash Fast vs Z.ai: GLM 5.2	`deepseek/deepseek-v4.1-flash-fast`	2	`z-ai/glm-5.2`	48
DeepSeek V4.1 Flash vs Z.ai: GLM 5.3 Flash	`deepseek/deepseek-v4.1-flash-p`	2	`z-ai/glm-5.3-flash`	48
Deepseek V4P1 Flash on Fireworks vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4p1-flash`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Deepseek V4P1 Flash 1017 on Fireworks	`deepseek/deepseek-v4-flash-0731`	35	`deepseek/deepseek-v4p1-flash-1017`	2
DeepSeek: DeepSeek V4.1 Flash vs Google Gemini Omni Flash	`deepseek/deepseek-v4.1-flash`	37	`google/gemini-omni-flash`	1
meta-models/Muse-Spark-Open-816B-A42B-NVFP4 vs OpenAI: gpt-oss-120b	`meta-models/muse-spark-open-816b-a42b-nvfp4`	2	`openai/gpt-oss-120b`	38
Meta: Muse Spark 1.1 vs Qwen: Qwen3.8 27B	`meta/muse-spark-1.1`	1	`qwen/qwen3.8-27b`	30
Meta: Muse Spark 1.2 vs MoonshotAI: Kimi K2.6	`meta/muse-spark-1.2`	1	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs Meta: Muse Spark 1.3	`google/gemma-4-31b-it`	26	`meta/muse-spark-1.3`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Macaron V1 Venti	`deepseek/deepseek-v4-pro`	26	`mindai/macaron-v1-venti`	2
MiniMax: MiniMax M3 vs MiniMax-M3	`minimax/minimax-m3`	25	`MiniMaxAI/MiniMax-M3`	2
Mistral: Mistral Large 4 vs Z.ai: GLM 5.3	`mistralai/mistral-large-4`	2	`z-ai/glm-5.3`	50
Kimi K2.8 Preview vs Z.ai: GLM 5.2	`moonshotai/kimi-k2.8-preview`	2	`z-ai/glm-5.2`	48
Kimi K3 Fast on Fireworks vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k3-fast`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Kimi K3	`moonshotai/kimi-k3`	45	`moonshotai/kimi-k3-p`	2
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen Flash	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen-flash`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen Flash 2025 07 28	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen-flash-2025-07-28`	1