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 V4P1 Flash 1017 on Fireworks vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4p1-flash-1017`	2	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Google Gemini Omni Flash	`deepseek/deepseek-v4.1-flash-1017`	24	`google/gemini-omni-flash`	1
meta-models/Muse-Spark-Open-816B-A42B-NVFP4 vs MiniMax: MiniMax M3	`meta-models/muse-spark-open-816b-a42b-nvfp4`	2	`minimax/minimax-m3`	24
Meta: Muse Spark 1.1 vs MoonshotAI: Kimi K2.7 Code	`meta/muse-spark-1.1`	1	`moonshotai/kimi-k2.7-code`	19
Meta: Muse Spark 1.2 vs Z.ai: GLM 5.3	`meta/muse-spark-1.2`	1	`z-ai/glm-5.3`	50
Meta: Muse Spark 1.3 vs Z.ai: GLM 5.2	`meta/muse-spark-1.3`	1	`z-ai/glm-5.2`	48
Macaron V1 Venti vs Z.ai: GLM 5.3 Flash	`mindai/macaron-v1-venti`	2	`z-ai/glm-5.3-flash`	48
MiniMax-M3 vs MoonshotAI: Kimi K3	`MiniMaxAI/MiniMax-M3`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Mistral: Mistral Large 4	`deepseek/deepseek-v4-flash-0731`	35	`mistralai/mistral-large-4`	2
DeepSeek: DeepSeek V4.1 Flash vs Kimi K2.8 Preview	`deepseek/deepseek-v4.1-flash`	37	`moonshotai/kimi-k2.8-preview`	2
Kimi K3 Fast on Fireworks vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k3-fast`	2	`openai/gpt-oss-120b`	38
Kimi K3 vs Qwen: Qwen3.8 27B	`moonshotai/kimi-k3-p`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs MoonshotAI: Kimi K3.1 Pro	`moonshotai/kimi-k2.6`	27	`moonshotai/kimi-k3.1-pro`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs Kimi K3.1 Pro Highspeed	`deepseek/deepseek-v4.1-flash-1017`	24	`moonshotai/kimi-k3.1-pro-highspeed`	2
MiniMax: MiniMax M3 vs Laguna-S-2.1	`minimax/minimax-m3`	24	`poolside/laguna-s-2.1`	2
MoonshotAI: Kimi K2.7 Code vs Qwen Flash	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen-flash`	1
Qwen Flash 2025 07 28 vs Z.ai: GLM 5.3	`qwen/qwen-flash-2025-07-28`	1	`z-ai/glm-5.3`	50
Qwen Plus vs Z.ai: GLM 5.2	`qwen/qwen-plus`	1	`z-ai/glm-5.2`	48
Qwen Plus 2025 07 28 vs Z.ai: GLM 5.3 Flash	`qwen/qwen-plus-2025-07-28`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen Plus 2025 09 11	`moonshotai/kimi-k3`	45	`qwen/qwen-plus-2025-09-11`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen Plus 2025 12 01	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen-plus-2025-12-01`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen3 Coder Flash	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3-coder-flash`	1
OpenAI: gpt-oss-120b vs Qwen3 Coder Flash 2025 07 28	`openai/gpt-oss-120b`	38	`qwen/qwen3-coder-flash-2025-07-28`	1
Qwen3.5 Flash 2026 02 23 vs Qwen: Qwen3.8 27B	`qwen/qwen3.5-flash-2026-02-23`	1	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs Qwen3.5 Plus 2026 02 15	`moonshotai/kimi-k2.6`	27	`qwen/qwen3.5-plus-2026-02-15`	1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen3.6 Flash	`deepseek/deepseek-v4.1-flash-1017`	24	`qwen/qwen3.6-flash`	1
MiniMax: MiniMax M3 vs Qwen3.6 Flash 2026 04 16	`minimax/minimax-m3`	24	`qwen/qwen3.6-flash-2026-04-16`	1
MoonshotAI: Kimi K2.7 Code vs Qwen3.7 Flash	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.7-flash`	1
Qwen3.7 Flash 2026 07 15 vs Z.ai: GLM 5.3	`qwen/qwen3.7-flash-2026-07-15`	1	`z-ai/glm-5.3`	50
Qwen3.7 Max 2026 05 20 vs Z.ai: GLM 5.2	`qwen/qwen3.7-max-2026-05-20`	1	`z-ai/glm-5.2`	48
Qwen3.7 Max 2026 06 08 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3.7-max-2026-06-08`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3.7 Plus 2026 05 26	`moonshotai/kimi-k3`	45	`qwen/qwen3.7-plus-2026-05-26`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.8-Flash-Next-FP8	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3.8-flash-next-fp8`	1
DeepSeek: DeepSeek V4.1 Flash vs Reflection Beam 1.0	`deepseek/deepseek-v4.1-flash`	37	`reflection/beam`	2
OpenAI: gpt-oss-120b vs Beam	`openai/gpt-oss-120b`	38	`reflection/beam-1.0`	2
Qwen: Qwen3.8 27B vs XiaomiMiMo/MiMo-V2.6-Flash-RL	`qwen/qwen3.8-27b`	33	`xiaomi/mimo-v2.6-flash-rl`	2
MoonshotAI: Kimi K2.6 vs Xiaomi MiMo V2.6 Pro UltraSpeed	`moonshotai/kimi-k2.6`	27	`xiaomi/mimo-v2.6-pro-ultraspeed`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs GLM 5.2 Fast	`deepseek/deepseek-v4.1-flash-1017`	24	`z-ai/glm-5.2-fast`	2
MiniMax: MiniMax M3 vs zai-org/glm-5.3-p	`minimax/minimax-m3`	24	`z-ai/glm-5.3-p`	2
MoonshotAI: Kimi K2.7 Code vs GLM-5.2	`moonshotai/kimi-k2.7-code`	19	`zai-org/GLM-5.2`	2
OpenAI: GPT-4.1 vs Z.ai: GLM 5.3	`openai/gpt-4.1`	2	`z-ai/glm-5.3`	50
OpenAI: GPT-4.1 Mini vs Z.ai: GLM 5.2	`openai/gpt-4.1-mini`	2	`z-ai/glm-5.2`	48
Abliterated Large vs Z.ai: GLM 5.3 Flash	`abliteration/abliterated-model-large`	1	`z-ai/glm-5.3-flash`	48
Abliterated Large v2 vs MoonshotAI: Kimi K3	`abliteration/abliterated-model-large-v2`	1	`moonshotai/kimi-k3`	45
Anthropic: Claude Fable 5 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-fable-5`	2	`deepseek/deepseek-v4-flash-0731`	35
Anthropic: Claude Fable 5.1 vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-fable-5.1`	2	`deepseek/deepseek-v4.1-flash`	37
Anthropic: Claude Opus 4.6 vs OpenAI: gpt-oss-120b	`anthropic/claude-opus-4.6`	2	`openai/gpt-oss-120b`	38
Anthropic: Claude Opus 4.7 vs Qwen: Qwen3.8 27B	`anthropic/claude-opus-4.7`	2	`qwen/qwen3.8-27b`	33
Anthropic: Claude Opus 5 vs MoonshotAI: Kimi K2.6	`anthropic/claude-opus-5`	3	`moonshotai/kimi-k2.6`	27
Anthropic: Claude Sonnet 4.5 vs DeepSeek: DeepSeek V4.1 Flash 1017	`anthropic/claude-sonnet-4.5`	2	`deepseek/deepseek-v4.1-flash-1017`	24
DeepSeek V4.1 Flash vs MiniMax: MiniMax M3	`deepseek/deepseek-v4-1-flash`	2	`minimax/minimax-m3`	24
DeepSeek v4.1 Flash (1017) vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-1-flash-1017`	2	`moonshotai/kimi-k2.7-code`	19
DeepSeek V4.1 Flash Uncensored vs Z.ai: GLM 5.3	`deepseek/deepseek-v4-1-flash-uncensored`	2	`z-ai/glm-5.3`	50
google/gemini-3.1-pro vs Z.ai: GLM 5.2	`google/gemini-3.1-pro`	2	`z-ai/glm-5.2`	48
Inception: Mercury 3 vs Z.ai: GLM 5.3 Flash	`inception/mercury-3`	1	`z-ai/glm-5.3-flash`	48
MiniMax M1 vs MoonshotAI: Kimi K3	`minimaxai/minimax-m1-80k`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Kimi K3.1 Pro	`deepseek/deepseek-v4-flash-0731`	35	`moonshotai/kimi-k3-1-pro`	2
DeepSeek: DeepSeek V4.1 Flash vs Kimi K3.1 Pro Highspeed	`deepseek/deepseek-v4.1-flash`	37	`moonshotai/kimi-k3-1-pro-highspeed`	2
Kimi K3 Fast vs OpenAI: gpt-oss-120b	`moonshotai/kimi-k3-fast-api`	2	`openai/gpt-oss-120b`	38
Qwen 3.6 Plus Uncensored vs Qwen: Qwen3.8 27B	`qwen/qwen-3-6-plus`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs Qwen 3.7 Max	`moonshotai/kimi-k2.6`	27	`qwen/qwen-3-7-max`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs Qwen 3.7 Plus	`deepseek/deepseek-v4.1-flash-1017`	24	`qwen/qwen-3-7-plus`	2
MiniMax: MiniMax M3 vs Qwen 3.8 Flash	`minimax/minimax-m3`	24	`qwen/qwen-3-8-flash`	2
MoonshotAI: Kimi K2.7 Code vs Qwen 3.8 Max	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen-3-8-max`	2
fugu-ultra-v1.1 vs Z.ai: GLM 5.3	`sakana-ai/fugu-ultra-v1.1`	1	`z-ai/glm-5.3`	50
ScaleDown Classify vs Z.ai: GLM 5.2	`scaledown/classify`	1	`z-ai/glm-5.2`	48
ScaleDown Compress vs Z.ai: GLM 5.3 Flash	`scaledown/compress`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs ScaleDown Extract	`moonshotai/kimi-k3`	45	`scaledown/extract`	1
DeepSeek: DeepSeek V4 Flash 0731 vs ScaleDown Summarize	`deepseek/deepseek-v4-flash-0731`	35	`scaledown/summarize`	1
DeepSeek: DeepSeek V4.1 Flash vs Dolly 1 Security	`deepseek/deepseek-v4.1-flash`	37	`zro/dolly1-security`	1
OpenAI: gpt-oss-120b vs Dolly 2 Security	`openai/gpt-oss-120b`	38	`zro/dolly2-security`	1
MiniMax M3 Preview vs Qwen: Qwen3.8 27B	`minimax/minimax-m3-preview`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs SpaceXAI: Grok 4.7	`moonshotai/kimi-k2.6`	27	`x-ai/grok-4.7`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI: GPT-5	`deepseek/deepseek-v4.1-flash-1017`	24	`openai/gpt-5`	2
MiniMax: MiniMax M3 vs OpenAI: GPT-5 Nano	`minimax/minimax-m3`	24	`openai/gpt-5-nano`	2
MoonshotAI: Kimi K2.7 Code vs OpenAI: GPT-5.1	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-5.1`	2
OpenAI: GPT-5.2 vs Z.ai: GLM 5.3	`openai/gpt-5.2`	2	`z-ai/glm-5.3`	50
OpenAI: GPT-5.4 Mini vs Z.ai: GLM 5.2	`openai/gpt-5.4-mini`	3	`z-ai/glm-5.2`	48
Abliterated Model vs Z.ai: GLM 5.3 Flash	`abliteration/abliterated-model`	1	`z-ai/glm-5.3-flash`	48
AionLabs: Aion 3.5 vs MoonshotAI: Kimi K3	`aion-labs/aion-3.5`	1	`moonshotai/kimi-k3`	45
AionLabs: Aion 3.5 Mini vs DeepSeek: DeepSeek V4 Flash 0731	`aion-labs/aion-3.5-mini`	1	`deepseek/deepseek-v4-flash-0731`	35
ByteDance Seed: Seed 2.1 Turbo vs DeepSeek: DeepSeek V4.1 Flash	`bytedance-seed/seed-2-1-turbo`	1	`deepseek/deepseek-v4.1-flash`	37
dola-seed-2-1-turbo vs OpenAI: gpt-oss-120b	`bytedance/dola-seed-2-1-turbo-260628`	1	`openai/gpt-oss-120b`	38
Doubao Seed 1.6 vs Qwen: Qwen3.8 27B	`bytedance/doubao-seed-1.6-251015`	1	`qwen/qwen3.8-27b`	33
Doubao Seed 1.6 Flash vs MoonshotAI: Kimi K2.6	`bytedance/doubao-seed-1.6-flash-250828`	1	`moonshotai/kimi-k2.6`	27
Doubao Seed 1.8 vs DeepSeek: DeepSeek V4.1 Flash 1017	`bytedance/doubao-seed-1.8-251228`	1	`deepseek/deepseek-v4.1-flash-1017`	24
Doubao Seed 2.0 Code Preview vs MiniMax: MiniMax M3	`bytedance/doubao-seed-2.0-code-preview-260215`	1	`minimax/minimax-m3`	24
Doubao Seed 2.0 Lite vs MoonshotAI: Kimi K2.7 Code	`bytedance/doubao-seed-2.0-lite-260428`	1	`moonshotai/kimi-k2.7-code`	19
Doubao Seed 2.0 Mini vs Z.ai: GLM 5.3	`bytedance/doubao-seed-2.0-mini-260428`	1	`z-ai/glm-5.3`	50
Doubao Seed 2.0 Pro vs Z.ai: GLM 5.2	`bytedance/doubao-seed-2.0-pro-260215`	1	`z-ai/glm-5.2`	48
Doubao Seed 2.1 Pro vs Z.ai: GLM 5.3 Flash	`bytedance/doubao-seed-2.1-pro-260628`	1	`z-ai/glm-5.3-flash`	48
Doubao Seed 2.1 Turbo vs MoonshotAI: Kimi K3	`bytedance/doubao-seed-2.1-turbo-260628`	1	`moonshotai/kimi-k3`	45
Doubao Seed Evolving vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/doubao-seed-evolving`	1	`deepseek/deepseek-v4-flash-0731`	35
seed-2-0-code vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/seed-2-0-code-preview-260328`	1	`deepseek/deepseek-v4.1-flash`	37
seed-2-0-lite vs OpenAI: gpt-oss-120b	`bytedance/seed-2-0-lite-260428`	1	`openai/gpt-oss-120b`	38
seed-2-0-mini vs Qwen: Qwen3.8 27B	`bytedance/seed-2-0-mini-260428`	1	`qwen/qwen3.8-27b`	33
seed-2-0-pro vs MoonshotAI: Kimi K2.6	`bytedance/seed-2-0-pro-260328`	1	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs google/gemma-4-31B-it-turbo	`deepseek/deepseek-v4.1-flash-1017`	24	`google/gemma-4-31b-it-turbo`	2
inclusionAI: Ling 3.1 Flash vs MiniMax: MiniMax M3	`inclusionai/ling-3.1-flash`	2	`minimax/minimax-m3`	24
KAT Coder Air V2.5 vs MoonshotAI: Kimi K2.7 Code	`kwaipilot/kat-coder-air-v2.5`	1	`moonshotai/kimi-k2.7-code`	19