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
Meta: Llama 3.1 8B Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-3.1-8b-instruct`	6	`openai/gpt-oss-120b`	36
OpenAI: gpt-oss-120b vs Qwen: Qwen3 235B A22B Thinking 2507	`openai/gpt-oss-120b`	36	`qwen/qwen3-235b-a22b-thinking-2507`	7
OpenAI: GPT-5.6 Terra vs OpenAI: gpt-oss-120b	`openai/gpt-5.6-terra`	6	`openai/gpt-oss-120b`	36
OpenAI: GPT-6 Astra vs OpenAI: gpt-oss-120b	`openai/gpt-6-astra`	6	`openai/gpt-oss-120b`	36
Llama 4 Maverick Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`openai/gpt-oss-120b`	36
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3-nano-30b-a3b`	6	`openai/gpt-oss-120b`	36
nvidia/Nemotron-3.5-Lightning-30B-A3B vs OpenAI: gpt-oss-120b	`nvidia/nemotron-3.5-lightning-30b-a3b`	4	`openai/gpt-oss-120b`	36
OpenAI: gpt-oss-120b vs Qwen3 Max	`openai/gpt-oss-120b`	36	`qwen/qwen3-max`	5
OpenAI: gpt-oss-120b vs Qwen: Qwen3 VL 30B A3B Instruct	`openai/gpt-oss-120b`	36	`qwen/qwen3-vl-30b-a3b-instruct`	5
OpenAI: gpt-oss-120b vs Qwen: Qwen3 VL 8B Instruct	`openai/gpt-oss-120b`	36	`qwen/qwen3-vl-8b-instruct`	4
OpenAI: gpt-oss-120b vs Z.ai: GLM 5V Turbo	`openai/gpt-oss-120b`	36	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-r1-0528`	6	`openai/gpt-oss-120b`	36
OpenAI: gpt-oss-120b vs Qwen: Qwen3 Coder 30B A3B Instruct	`openai/gpt-oss-120b`	36	`qwen/qwen3-coder-30b-a3b-instruct`	4
Google: Gemma 3 12B vs OpenAI: gpt-oss-120b	`google/gemma-3-12b-it`	5	`openai/gpt-oss-120b`	36
Meta: Llama 3.1 70B Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-3.1-70b-instruct`	5	`openai/gpt-oss-120b`	36
Llama 4 Scout Instruct vs OpenAI: gpt-oss-120b	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`openai/gpt-oss-120b`	36
Muse Glimmer 30B on Fireworks vs OpenAI: gpt-oss-120b	`meta-models/muse-glimmer-30b`	6	`openai/gpt-oss-120b`	36
DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-flash`	25	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-pro`	26	`moonshotai/kimi-k2.6`	33
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.6	`google/gemma-4-31b-it`	25	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4.1 Flash vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4.1-flash`	23	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs MoonshotAI: Kimi K2.7 Code	`moonshotai/kimi-k2.6`	33	`moonshotai/kimi-k2.7-code`	19
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.8-27b`	19
MiniMax: MiniMax M3 vs MoonshotAI: Kimi K2.6	`minimax/minimax-m3`	21	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.6 35B A3B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.6-35b-a3b`	17
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.1	`moonshotai/kimi-k2.6`	33	`z-ai/glm-5.1`	20
Meta: Llama 3.3 70B Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-3.3-70b-instruct`	18	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs OpenAI: gpt-oss-20b	`moonshotai/kimi-k2.6`	33	`openai/gpt-oss-20b`	18
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.5 397B A17B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.5-397b-a17b`	17
Google: Gemma 4 26B A4B vs MoonshotAI: Kimi K2.6	`google/gemma-4-26b-a4b-it`	15	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.6 27B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v3.2`	16	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.5 vs MoonshotAI: Kimi K2.6	`moonshotai/kimi-k2.5`	12	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.5-122B-A10B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.5-122b-a10b`	12
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 4.7	`moonshotai/kimi-k2.6`	33	`z-ai/glm-4.7`	11
MiniMax: MiniMax M2.5 vs MoonshotAI: Kimi K2.6	`minimax/minimax-m2.5`	13	`moonshotai/kimi-k2.6`	33
MiniMax: MiniMax M2.7 vs MoonshotAI: Kimi K2.6	`minimax/minimax-m2.7`	11	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 Next 80B A3B Instruct	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-next-80b-a3b-instruct`	10
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.5-35B-A3B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.5-35b-a3b`	10
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5	`moonshotai/kimi-k2.6`	33	`z-ai/glm-5`	10
MoonshotAI: Kimi K2.6 vs Qwen3 235B A22B Instruct 2507	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-235b-a22b-instruct-2507`	9
MoonshotAI: Kimi K2.6 vs Xiaomi: MiMo-V2.5	`moonshotai/kimi-k2.6`	33	`xiaomi/mimo-v2.5`	8
DeepSeek: DeepSeek V4 Flash Vision Exp vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-flash-vision-exp`	10	`moonshotai/kimi-k2.6`	33
Google: Gemini 2.5 Flash vs MoonshotAI: Kimi K2.6	`google/gemini-2.5-flash`	8	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs NVIDIA: Nemotron 3 Ultra	`moonshotai/kimi-k2.6`	33	`nvidia/nemotron-3-ultra-550b-a55b`	9
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.5-9B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.5-9b`	10
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 4.6	`moonshotai/kimi-k2.6`	33	`z-ai/glm-4.6`	8
DeepSeek V3.1 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v3.1`	7	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Xiaomi: MiMo-V2.5-Pro	`moonshotai/kimi-k2.6`	33	`xiaomi/mimo-v2.5-pro`	8
DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-pro-0423`	4	`moonshotai/kimi-k2.6`	33
Google: Gemini 2.5 Pro vs MoonshotAI: Kimi K2.6	`google/gemini-2.5-pro`	6	`moonshotai/kimi-k2.6`	33
Google: Gemini 3 Flash Preview vs MoonshotAI: Kimi K2.6	`google/gemini-3-flash-preview`	6	`moonshotai/kimi-k2.6`	33
Google: Gemini 3.1 Flash Lite vs MoonshotAI: Kimi K2.6	`google/gemini-3.1-flash-lite`	6	`moonshotai/kimi-k2.6`	33
Google: Gemini 3.1 Pro Preview vs MoonshotAI: Kimi K2.6	`google/gemini-3.1-pro-preview`	7	`moonshotai/kimi-k2.6`	33
Google: Gemini 3.5 Flash vs MoonshotAI: Kimi K2.6	`google/gemini-3.5-flash`	7	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen3.7 Max	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.7-max`	7
MoonshotAI: Kimi K2.6 vs Qwen3.8 Max	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.8-max`	8
MoonshotAI: Kimi K2.6 vs Thinking Machines: Inkling	`moonshotai/kimi-k2.6`	33	`thinkingmachines/inkling`	7
MoonshotAI: Kimi K2.6 vs Thinking Machines: Inkling Small	`moonshotai/kimi-k2.6`	33	`thinkingmachines/inkling-small`	7
MoonshotAI: Kimi K2.6 vs NVIDIA: Nemotron 3 Super	`moonshotai/kimi-k2.6`	33	`nvidia/nemotron-3-super-120b-a12b`	7
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 Coder Next	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-coder-next`	7
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 VL 235B A22B Instruct	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-vl-235b-a22b-instruct`	7
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.5-27B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.5-27b`	6
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3.8 2.4T A95B	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.8-2.4t-a95b`	8
MoonshotAI: Kimi K2.6 vs Tencent: Hy3	`moonshotai/kimi-k2.6`	33	`tencent/hy3`	8
Google: Gemma 3 27B vs MoonshotAI: Kimi K2.6	`google/gemma-3-27b-it`	8	`moonshotai/kimi-k2.6`	33
Meta: Llama 3.1 8B Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-3.1-8b-instruct`	6	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 235B A22B Thinking 2507	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-235b-a22b-thinking-2507`	7
MoonshotAI: Kimi K2.6 vs OpenAI: GPT-5.6 Terra	`moonshotai/kimi-k2.6`	33	`openai/gpt-5.6-terra`	6
MoonshotAI: Kimi K2.6 vs OpenAI: GPT-6 Astra	`moonshotai/kimi-k2.6`	33	`openai/gpt-6-astra`	6
Llama 4 Maverick Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	5	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs NVIDIA: Nemotron 3 Nano 30B A3B	`moonshotai/kimi-k2.6`	33	`nvidia/nemotron-3-nano-30b-a3b`	6
MoonshotAI: Kimi K2.6 vs nvidia/Nemotron-3.5-Lightning-30B-A3B	`moonshotai/kimi-k2.6`	33	`nvidia/nemotron-3.5-lightning-30b-a3b`	4
MoonshotAI: Kimi K2.6 vs Qwen3 Max	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-max`	5
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 VL 30B A3B Instruct	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-vl-30b-a3b-instruct`	5
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 VL 8B Instruct	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-vl-8b-instruct`	4
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5V Turbo	`moonshotai/kimi-k2.6`	33	`z-ai/glm-5v-turbo`	5
DeepSeek: R1 0528 vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-r1-0528`	6	`moonshotai/kimi-k2.6`	33
MoonshotAI: Kimi K2.6 vs Qwen: Qwen3 Coder 30B A3B Instruct	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-coder-30b-a3b-instruct`	4
Google: Gemma 3 12B vs MoonshotAI: Kimi K2.6	`google/gemma-3-12b-it`	5	`moonshotai/kimi-k2.6`	33
Meta: Llama 3.1 70B Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-3.1-70b-instruct`	5	`moonshotai/kimi-k2.6`	33
Llama 4 Scout Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-4-scout-17b-16e-instruct`	5	`moonshotai/kimi-k2.6`	33
Muse Glimmer 30B on Fireworks vs MoonshotAI: Kimi K2.6	`meta-models/muse-glimmer-30b`	6	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs DeepSeek: DeepSeek V4 Pro 0423	`deepseek/deepseek-v4-flash`	25	`deepseek/deepseek-v4-pro`	26
DeepSeek: DeepSeek V4 Flash 0423 vs Google: Gemma 4 31B	`deepseek/deepseek-v4-flash`	25	`google/gemma-4-31b-it`	25
DeepSeek: DeepSeek V4 Flash 0423 vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v4-flash`	25	`deepseek/deepseek-v4.1-flash`	23
DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-flash`	25	`moonshotai/kimi-k2.7-code`	19
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.8-27b`	19
DeepSeek: DeepSeek V4 Flash 0423 vs MiniMax: MiniMax M3	`deepseek/deepseek-v4-flash`	25	`minimax/minimax-m3`	21
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.6 35B A3B	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.6-35b-a3b`	17
DeepSeek: DeepSeek V4 Flash 0423 vs Z.ai: GLM 5.1	`deepseek/deepseek-v4-flash`	25	`z-ai/glm-5.1`	20
DeepSeek: DeepSeek V4 Flash 0423 vs Meta: Llama 3.3 70B Instruct	`deepseek/deepseek-v4-flash`	25	`meta-llama/llama-3.3-70b-instruct`	18
DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: gpt-oss-20b	`deepseek/deepseek-v4-flash`	25	`openai/gpt-oss-20b`	18
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.5 397B A17B	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.5-397b-a17b`	17
DeepSeek: DeepSeek V4 Flash 0423 vs Google: Gemma 4 26B A4B	`deepseek/deepseek-v4-flash`	25	`google/gemma-4-26b-a4b-it`	15
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.6 27B	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.6-27b`	14
DeepSeek: DeepSeek V3.2 vs DeepSeek: DeepSeek V4 Flash 0423	`deepseek/deepseek-v3.2`	16	`deepseek/deepseek-v4-flash`	25
DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K2.5	`deepseek/deepseek-v4-flash`	25	`moonshotai/kimi-k2.5`	12
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen: Qwen3.5-122B-A10B	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.5-122b-a10b`	12
DeepSeek: DeepSeek V4 Flash 0423 vs Z.ai: GLM 4.7	`deepseek/deepseek-v4-flash`	25	`z-ai/glm-4.7`	11