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 Vision Exp vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v4-flash-vision-exp`	6	`deepseek/deepseek-v4.1-flash`	37
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemini 2.5 Pro	`deepseek/deepseek-v4.1-flash`	37	`google/gemini-2.5-pro`	4
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemini 3.1 Pro Preview	`deepseek/deepseek-v4.1-flash`	37	`google/gemini-3.1-pro-preview`	5
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemini 3.8 Flash	`deepseek/deepseek-v4.1-flash`	37	`google/gemini-3.8-flash`	5
DeepSeek: DeepSeek V4.1 Flash vs stepfun-ai/Step-5-Preview	`deepseek/deepseek-v4.1-flash`	37	`stepfun-ai/step-5-preview`	5
DeepSeek: DeepSeek V4.1 Flash vs Xiaomi: MiMo-V2.5-Pro	`deepseek/deepseek-v4.1-flash`	37	`xiaomi/mimo-v2.5-pro`	5
DeepSeek: DeepSeek V4.1 Flash vs Qwen3.8 Flash	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3.8-flash`	6
DeepSeek: DeepSeek V4.1 Flash vs Thinking Machines: Inkling	`deepseek/deepseek-v4.1-flash`	37	`thinkingmachines/inkling`	5
DeepSeek: DeepSeek V4.1 Flash vs NVIDIA: Nemotron 3.5 Lightning	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3.5-lightning`	5
DeepSeek: DeepSeek V4.1 Flash vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3.8-Flash-Next	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3.8-flash-next`	3
DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5V Turbo	`deepseek/deepseek-v4.1-flash`	37	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-r1-0528`	6	`deepseek/deepseek-v4.1-flash`	37
DeepSeek: DeepSeek V4.1 Flash vs Llama 4 Scout Instruct	`deepseek/deepseek-v4.1-flash`	37	`meta-llama/llama-4-scout-17b-16e-instruct`	5
DeepSeek: DeepSeek V4.1 Flash vs Qwen: Qwen3 32B	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3-32b`	4
DeepSeek: DeepSeek V4.1 Flash vs Meta: Llama 4 Maverick	`deepseek/deepseek-v4.1-flash`	37	`meta-llama/llama-4-maverick`	5
DeepSeek: DeepSeek V4.1 Flash vs google/gemma-4-12B-it	`deepseek/deepseek-v4.1-flash`	37	`google/gemma-4-12b-it`	4
OpenAI: gpt-oss-120b vs Qwen: Qwen3.8 27B	`openai/gpt-oss-120b`	37	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k2.6`	27	`openai/gpt-oss-120b`	37
Google: Gemma 4 31B vs OpenAI: gpt-oss-120b	`google/gemma-4-31b-it`	26	`openai/gpt-oss-120b`	37
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-pro`	26	`openai/gpt-oss-120b`	37
MiniMax: MiniMax M3 vs OpenAI: gpt-oss-120b	`minimax/minimax-m3`	25	`openai/gpt-oss-120b`	37
MoonshotAI: Kimi K2.7 Code vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3.6 35B A3B	`openai/gpt-oss-120b`	37	`qwen/qwen3.6-35b-a3b`	19
OpenAI: gpt-oss-120b vs Z.ai: GLM 5.1	`openai/gpt-oss-120b`	37	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-flash`	18	`openai/gpt-oss-120b`	37
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4.1-flash-1017`	17	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs OpenAI: gpt-oss-20b	`openai/gpt-oss-120b`	37	`openai/gpt-oss-20b`	17
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5 397B A17B	`openai/gpt-oss-120b`	37	`qwen/qwen3.5-397b-a17b`	18
Google: Gemma 4 26B A4B vs OpenAI: gpt-oss-120b	`google/gemma-4-26b-a4b-it`	16	`openai/gpt-oss-120b`	37
Meta: Llama 3.3 70B Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-3.3-70b-instruct`	14	`openai/gpt-oss-120b`	37
MoonshotAI: Kimi K2.5 vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k2.5`	13	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3.6 27B	`openai/gpt-oss-120b`	37	`qwen/qwen3.6-27b`	14
OpenAI: gpt-oss-120b vs Z.ai: GLM 5	`openai/gpt-oss-120b`	37	`z-ai/glm-5`	12
DeepSeek: DeepSeek V3.2 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v3.2`	14	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5-9B	`openai/gpt-oss-120b`	37	`qwen/qwen3.5-9b`	12
OpenAI: gpt-oss-120b vs Qwen: Qwen3.8 2.4T A95B	`openai/gpt-oss-120b`	37	`qwen/qwen3.8-2.4t-a95b`	9
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5-122B-A10B	`openai/gpt-oss-120b`	37	`qwen/qwen3.5-122b-a10b`	10
OpenAI: gpt-oss-120b vs Z.ai: GLM 4.7	`openai/gpt-oss-120b`	37	`z-ai/glm-4.7`	9
OpenAI: gpt-oss-120b vs Xiaomi: MiMo-V2.6-Flash	`openai/gpt-oss-120b`	37	`xiaomi/mimo-v2.6-flash`	9
NVIDIA: Nemotron 3 Ultra vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3-ultra-550b-a55b`	9	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5-27B	`openai/gpt-oss-120b`	37	`qwen/qwen3.5-27b`	7
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5-35B-A3B	`openai/gpt-oss-120b`	37	`qwen/qwen3.5-35b-a3b`	9
OpenAI: gpt-oss-120b vs Z.ai: GLM 4.6	`openai/gpt-oss-120b`	37	`z-ai/glm-4.6`	8
MiniMax: MiniMax M2.5 vs OpenAI: gpt-oss-120b	`minimax/minimax-m2.5`	8	`openai/gpt-oss-120b`	37
Google: Gemma 3 27B vs OpenAI: gpt-oss-120b	`google/gemma-3-27b-it`	9	`openai/gpt-oss-120b`	37
Meta: Llama 3.1 8B Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-3.1-8b-instruct`	7	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Z.ai: GLM 4.7 Flash	`openai/gpt-oss-120b`	37	`z-ai/glm-4.7-flash`	6
OpenAI: gpt-oss-120b vs Qwen: Qwen3 14B	`openai/gpt-oss-120b`	37	`qwen/qwen3-14b`	6
OpenAI: gpt-oss-120b vs Xiaomi: MiMo-V2.6-Pro	`openai/gpt-oss-120b`	37	`xiaomi/mimo-v2.6-pro`	8
DeepSeek V4 Pro 0423 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-pro-0423`	4	`openai/gpt-oss-120b`	37
Google: Gemini 2.5 Flash vs OpenAI: gpt-oss-120b	`google/gemini-2.5-flash`	6	`openai/gpt-oss-120b`	37
Google: Gemini 3.1 Flash Lite vs OpenAI: gpt-oss-120b	`google/gemini-3.1-flash-lite`	6	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Xiaomi: MiMo-V2.5	`openai/gpt-oss-120b`	37	`xiaomi/mimo-v2.5`	5
OpenAI: gpt-oss-120b vs Qwen3.7 Max	`openai/gpt-oss-120b`	37	`qwen/qwen3.7-max`	7
OpenAI: gpt-oss-120b vs Qwen3.8 Max	`openai/gpt-oss-120b`	37	`qwen/qwen3.8-max`	8
OpenAI: gpt-oss-120b vs Tencent: Hy4 preview	`openai/gpt-oss-120b`	37	`tencent/hy4-preview`	8
NVIDIA: Nemotron 3 Super vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3-super-120b-a12b`	7	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen/Qwen3-235B-A22B-Instruct-2507	`openai/gpt-oss-120b`	37	`qwen/qwen3-235b-a22b-instruct-2507`	6
OpenAI: gpt-oss-120b vs Qwen: Qwen3 Next 80B A3B Instruct	`openai/gpt-oss-120b`	37	`qwen/qwen3-next-80b-a3b-instruct`	7
OpenAI: gpt-oss-120b vs Tencent: Hy3	`openai/gpt-oss-120b`	37	`tencent/hy3`	8
MiniMax: MiniMax M2.7 vs OpenAI: gpt-oss-120b	`minimax/minimax-m2.7`	7	`openai/gpt-oss-120b`	37
deepseek-ai/DeepSeek-V3.1 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v3.1`	5	`openai/gpt-oss-120b`	37
Google: Gemma 3 12B vs OpenAI: gpt-oss-120b	`google/gemma-3-12b-it`	6	`openai/gpt-oss-120b`	37
OpenAI: GPT-5.6 Luna vs OpenAI: gpt-oss-120b	`openai/gpt-5.6-luna`	4	`openai/gpt-oss-120b`	37
OpenAI: GPT-5.6 Sol vs OpenAI: gpt-oss-120b	`openai/gpt-5.6-sol`	5	`openai/gpt-oss-120b`	37
DeepSeek: DeepSeek V4 Flash Vision Exp vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-flash-vision-exp`	6	`openai/gpt-oss-120b`	37
Google: Gemini 2.5 Pro vs OpenAI: gpt-oss-120b	`google/gemini-2.5-pro`	4	`openai/gpt-oss-120b`	37
Google: Gemini 3.1 Pro Preview vs OpenAI: gpt-oss-120b	`google/gemini-3.1-pro-preview`	5	`openai/gpt-oss-120b`	37
Google: Gemini 3.8 Flash vs OpenAI: gpt-oss-120b	`google/gemini-3.8-flash`	5	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs stepfun-ai/Step-5-Preview	`openai/gpt-oss-120b`	37	`stepfun-ai/step-5-preview`	5
OpenAI: gpt-oss-120b vs Xiaomi: MiMo-V2.5-Pro	`openai/gpt-oss-120b`	37	`xiaomi/mimo-v2.5-pro`	5
OpenAI: gpt-oss-120b vs Qwen3.8 Flash	`openai/gpt-oss-120b`	37	`qwen/qwen3.8-flash`	6
OpenAI: gpt-oss-120b vs Thinking Machines: Inkling	`openai/gpt-oss-120b`	37	`thinkingmachines/inkling`	5
NVIDIA: Nemotron 3.5 Lightning vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3.5-lightning`	5	`openai/gpt-oss-120b`	37
nvidia/Nemotron-3.5-Lightning-30B-A3B vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3.8-Flash-Next	`openai/gpt-oss-120b`	37	`qwen/qwen3.8-flash-next`	3
OpenAI: gpt-oss-120b vs Z.ai: GLM 5V Turbo	`openai/gpt-oss-120b`	37	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-r1-0528`	6	`openai/gpt-oss-120b`	37
Llama 4 Scout Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`openai/gpt-oss-120b`	37
OpenAI: gpt-oss-120b vs Qwen: Qwen3 32B	`openai/gpt-oss-120b`	37	`qwen/qwen3-32b`	4
Meta: Llama 4 Maverick vs OpenAI: gpt-oss-120b	`meta-llama/llama-4-maverick`	5	`openai/gpt-oss-120b`	37
google/gemma-4-12B-it vs OpenAI: gpt-oss-120b	`google/gemma-4-12b-it`	4	`openai/gpt-oss-120b`	37
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2.6`	27	`qwen/qwen3.8-27b`	30
Google: Gemma 4 31B vs Qwen: Qwen3.8 27B	`google/gemma-4-31b-it`	26	`qwen/qwen3.8-27b`	30
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3.8-27b`	30
MiniMax: MiniMax M3 vs Qwen: Qwen3.8 27B	`minimax/minimax-m3`	25	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.8-27b`	30
Qwen: Qwen3.6 35B A3B vs Qwen: Qwen3.8 27B	`qwen/qwen3.6-35b-a3b`	19	`qwen/qwen3.8-27b`	30
Qwen: Qwen3.8 27B vs Z.ai: GLM 5.1	`qwen/qwen3.8-27b`	30	`z-ai/glm-5.1`	21
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-flash`	18	`qwen/qwen3.8-27b`	30
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4.1-flash-1017`	17	`qwen/qwen3.8-27b`	30
OpenAI: gpt-oss-20b vs Qwen: Qwen3.8 27B	`openai/gpt-oss-20b`	17	`qwen/qwen3.8-27b`	30
Qwen: Qwen3.5 397B A17B vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-397b-a17b`	18	`qwen/qwen3.8-27b`	30
Google: Gemma 4 26B A4B vs Qwen: Qwen3.8 27B	`google/gemma-4-26b-a4b-it`	16	`qwen/qwen3.8-27b`	30
Meta: Llama 3.3 70B Instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-3.3-70b-instruct`	14	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.5 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2.5`	13	`qwen/qwen3.8-27b`	30
Qwen: Qwen3.6 27B vs Qwen: Qwen3.8 27B	`qwen/qwen3.6-27b`	14	`qwen/qwen3.8-27b`	30
Qwen: Qwen3.8 27B vs Z.ai: GLM 5	`qwen/qwen3.8-27b`	30	`z-ai/glm-5`	12
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v3.2`	14	`qwen/qwen3.8-27b`	30