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 Omni Flash vs Z.ai: GLM 5.2	`google/gemini-omni-flash`	1	`z-ai/glm-5.2`	48
meta-models/Muse-Spark-Open-816B-A42B-NVFP4 vs Z.ai: GLM 5.3 Flash	`meta-models/muse-spark-open-816b-a42b-nvfp4`	2	`z-ai/glm-5.3-flash`	48
Meta: Muse Spark 1.1 vs MoonshotAI: Kimi K3	`meta/muse-spark-1.1`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Meta: Muse Spark 1.2	`deepseek/deepseek-v4-flash-0731`	35	`meta/muse-spark-1.2`	1
DeepSeek: DeepSeek V4.1 Flash vs Meta: Muse Spark 1.3	`deepseek/deepseek-v4.1-flash`	37	`meta/muse-spark-1.3`	1
Macaron V1 Venti vs OpenAI: gpt-oss-120b	`mindai/macaron-v1-venti`	2	`openai/gpt-oss-120b`	37
MiniMax-M3 vs Qwen: Qwen3.8 27B	`MiniMaxAI/MiniMax-M3`	2	`qwen/qwen3.8-27b`	30
Mistral: Mistral Large 4 vs MoonshotAI: Kimi K2.6	`mistralai/mistral-large-4`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs Kimi K2.8 Preview	`google/gemma-4-31b-it`	26	`moonshotai/kimi-k2.8-preview`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Kimi K3 Fast on Fireworks	`deepseek/deepseek-v4-pro`	26	`moonshotai/kimi-k3-fast`	2
MiniMax: MiniMax M3 vs Kimi K3	`minimax/minimax-m3`	25	`moonshotai/kimi-k3-p`	2
Qwen Flash vs Z.ai: GLM 5.3	`qwen/qwen-flash`	1	`z-ai/glm-5.3`	50
Qwen Flash 2025 07 28 vs Z.ai: GLM 5.2	`qwen/qwen-flash-2025-07-28`	1	`z-ai/glm-5.2`	48
Qwen Plus vs Z.ai: GLM 5.3 Flash	`qwen/qwen-plus`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen Plus 2025 07 28	`moonshotai/kimi-k3`	45	`qwen/qwen-plus-2025-07-28`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen Plus 2025 09 11	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen-plus-2025-09-11`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen Plus 2025 12 01	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen-plus-2025-12-01`	1
OpenAI: gpt-oss-120b vs Qwen3 Coder Flash	`openai/gpt-oss-120b`	37	`qwen/qwen3-coder-flash`	1
Qwen3 Coder Flash 2025 07 28 vs Qwen: Qwen3.8 27B	`qwen/qwen3-coder-flash-2025-07-28`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen3.5 Flash 2026 02 23	`moonshotai/kimi-k2.6`	27	`qwen/qwen3.5-flash-2026-02-23`	1
Google: Gemma 4 31B vs Qwen3.5 Plus 2026 02 15	`google/gemma-4-31b-it`	26	`qwen/qwen3.5-plus-2026-02-15`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3.6 Flash	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3.6-flash`	1
MiniMax: MiniMax M3 vs Qwen3.6 Flash 2026 04 16	`minimax/minimax-m3`	25	`qwen/qwen3.6-flash-2026-04-16`	1
Qwen3.7 Flash vs Z.ai: GLM 5.3	`qwen/qwen3.7-flash`	1	`z-ai/glm-5.3`	50
Qwen3.7 Flash 2026 07 15 vs Z.ai: GLM 5.2	`qwen/qwen3.7-flash-2026-07-15`	1	`z-ai/glm-5.2`	48
Qwen3.7 Max 2026 05 20 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3.7-max-2026-05-20`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3.7 Max 2026 06 08	`moonshotai/kimi-k3`	45	`qwen/qwen3.7-max-2026-06-08`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.7 Plus 2026 05 26	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3.7-plus-2026-05-26`	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`	37	`reflection/beam-1.0`	2
Qwen: Qwen3.8 27B vs XiaomiMiMo/MiMo-V2.6-Flash-RL	`qwen/qwen3.8-27b`	30	`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
Google: Gemma 4 31B vs Xiaomi MiMo V2.5	`google/gemma-4-31b-it`	26	`xiaomimimo/mimo-v2.5`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Xiaomi MiMo V2.5 Pro	`deepseek/deepseek-v4-pro`	26	`xiaomimimo/mimo-v2.5-pro`	2
MiniMax: MiniMax M3 vs GLM 5.2 Fast	`minimax/minimax-m3`	25	`z-ai/glm-5.2-fast`	2
Z.ai: GLM 5.3 vs zai-org/glm-5.3-p	`z-ai/glm-5.3`	50	`z-ai/glm-5.3-p`	2
Z.ai: GLM 5.2 vs GLM-5.2	`z-ai/glm-5.2`	48	`zai-org/GLM-5.2`	2
OpenAI: GPT-4.1 vs Z.ai: GLM 5.3 Flash	`openai/gpt-4.1`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-4.1 Nano	`moonshotai/kimi-k3`	45	`openai/gpt-4.1-nano`	2
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 Haiku 5.5 vs OpenAI: gpt-oss-120b	`anthropic/claude-haiku-5.5`	2	`openai/gpt-oss-120b`	37
Anthropic: Claude Opus 4.6 vs Qwen: Qwen3.8 27B	`anthropic/claude-opus-4.6`	2	`qwen/qwen3.8-27b`	30
Anthropic: Claude Opus 4.7 vs MoonshotAI: Kimi K2.6	`anthropic/claude-opus-4.7`	2	`moonshotai/kimi-k2.6`	27
Anthropic: Claude Opus 4.8 vs Google: Gemma 4 31B	`anthropic/claude-opus-4.8`	2	`google/gemma-4-31b-it`	26
Anthropic: Claude Opus 5 vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-opus-5`	3	`deepseek/deepseek-v4-pro`	26
Anthropic: Claude Opus 5.5 vs MiniMax: MiniMax M3	`anthropic/claude-opus-5.5`	2	`minimax/minimax-m3`	25
Anthropic: Claude Sonnet 4.5 vs Z.ai: GLM 5.3	`anthropic/claude-sonnet-4.5`	2	`z-ai/glm-5.3`	50
Anthropic: Claude Sonnet 5 vs Z.ai: GLM 5.2	`anthropic/claude-sonnet-5`	2	`z-ai/glm-5.2`	48
Anthropic: Claude Sonnet 5.5 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-sonnet-5.5`	2	`z-ai/glm-5.3-flash`	48
DeepSeek V4.1 Flash vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4-1-flash`	2	`moonshotai/kimi-k3`	45
DeepSeek v4.1 Flash (1017) vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-v4-1-flash-1017`	2	`deepseek/deepseek-v4-flash-0731`	35
DeepSeek: DeepSeek V4.1 Flash vs google/gemini-3.1-pro	`deepseek/deepseek-v4.1-flash`	37	`google/gemini-3.1-pro`	2
Inception: Mercury 3 vs OpenAI: gpt-oss-120b	`inception/mercury-3`	1	`openai/gpt-oss-120b`	37
MiniMax M3.1 Flash vs Qwen: Qwen3.8 27B	`minimax/minimax-m3-1-flash`	2	`qwen/qwen3.8-27b`	30
MiniMax-M3.1-Flash vs MoonshotAI: Kimi K2.6	`minimax/minimax-m3.1-flash`	3	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs MiniMax M1	`google/gemma-4-31b-it`	26	`minimaxai/minimax-m1-80k`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Kimi K3 Fast	`deepseek/deepseek-v4-pro`	26	`moonshotai/kimi-k3-fast-api`	2
MiniMax: MiniMax M3 vs Qwen 3.6 Plus Uncensored	`minimax/minimax-m3`	25	`qwen/qwen-3-6-plus`	2
Qwen 3.7 Max vs Z.ai: GLM 5.3	`qwen/qwen-3-7-max`	2	`z-ai/glm-5.3`	50
Qwen 3.7 Plus vs Z.ai: GLM 5.2	`qwen/qwen-3-7-plus`	2	`z-ai/glm-5.2`	48
Qwen 3.8 Flash vs Z.ai: GLM 5.3 Flash	`qwen/qwen-3-8-flash`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen 3.8 Max	`moonshotai/kimi-k3`	45	`qwen/qwen-3-8-max`	2
DeepSeek: DeepSeek V4 Flash 0731 vs fugu-ultra-v1.1	`deepseek/deepseek-v4-flash-0731`	35	`sakana-ai/fugu-ultra-v1.1`	1
DeepSeek: DeepSeek V4.1 Flash vs ScaleDown Classify	`deepseek/deepseek-v4.1-flash`	37	`scaledown/classify`	1
OpenAI: gpt-oss-120b vs ScaleDown Compress	`openai/gpt-oss-120b`	37	`scaledown/compress`	1
Qwen: Qwen3.8 27B vs ScaleDown Extract	`qwen/qwen3.8-27b`	30	`scaledown/extract`	1
MoonshotAI: Kimi K2.6 vs ScaleDown Summarize	`moonshotai/kimi-k2.6`	27	`scaledown/summarize`	1
Google: Gemma 4 31B vs Dolly 1 Security	`google/gemma-4-31b-it`	26	`zro/dolly1-security`	1
DeepSeek: DeepSeek V4 Pro 0423 vs MiniMax M3 Preview	`deepseek/deepseek-v4-pro`	26	`minimax/minimax-m3-preview`	2
MiniMax: MiniMax M3 vs SpaceXAI: Grok 4.7	`minimax/minimax-m3`	25	`x-ai/grok-4.7`	2
OpenAI: GPT-5 vs Z.ai: GLM 5.3	`openai/gpt-5`	2	`z-ai/glm-5.3`	50
OpenAI: GPT-5 Nano vs Z.ai: GLM 5.2	`openai/gpt-5-nano`	2	`z-ai/glm-5.2`	48
OpenAI: GPT-5.1 vs Z.ai: GLM 5.3 Flash	`openai/gpt-5.1`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-5.2	`moonshotai/kimi-k3`	45	`openai/gpt-5.2`	2
AionLabs: Aion 3.5 vs DeepSeek: DeepSeek V4 Flash 0731	`aion-labs/aion-3.5`	1	`deepseek/deepseek-v4-flash-0731`	35
AionLabs: Aion 3.5 Mini vs DeepSeek: DeepSeek V4.1 Flash	`aion-labs/aion-3.5-mini`	1	`deepseek/deepseek-v4.1-flash`	37
Trinity Large Thinking vs OpenAI: gpt-oss-120b	`arcee-ai/trinity-large-thinking`	1	`openai/gpt-oss-120b`	37
ByteDance Seed: Seed 2.1 Turbo vs Qwen: Qwen3.8 27B	`bytedance-seed/seed-2-1-turbo`	1	`qwen/qwen3.8-27b`	30
dola-seed-2-1-turbo vs MoonshotAI: Kimi K2.6	`bytedance/dola-seed-2-1-turbo-260628`	1	`moonshotai/kimi-k2.6`	27
Doubao Seed 1.6 vs Google: Gemma 4 31B	`bytedance/doubao-seed-1.6-251015`	1	`google/gemma-4-31b-it`	26
Doubao Seed 1.6 Flash vs DeepSeek: DeepSeek V4 Pro 0423	`bytedance/doubao-seed-1.6-flash-250828`	1	`deepseek/deepseek-v4-pro`	26
Doubao Seed 1.8 vs MiniMax: MiniMax M3	`bytedance/doubao-seed-1.8-251228`	1	`minimax/minimax-m3`	25
Doubao Seed 2.0 Code Preview vs Z.ai: GLM 5.3	`bytedance/doubao-seed-2.0-code-preview-260215`	1	`z-ai/glm-5.3`	50
Doubao Seed 2.0 Lite vs Z.ai: GLM 5.2	`bytedance/doubao-seed-2.0-lite-260428`	1	`z-ai/glm-5.2`	48
Doubao Seed 2.0 Mini vs Z.ai: GLM 5.3 Flash	`bytedance/doubao-seed-2.0-mini-260428`	1	`z-ai/glm-5.3-flash`	48
Doubao Seed 2.0 Pro vs MoonshotAI: Kimi K3	`bytedance/doubao-seed-2.0-pro-260215`	1	`moonshotai/kimi-k3`	45
Doubao Seed 2.1 Pro vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/doubao-seed-2.1-pro-260628`	1	`deepseek/deepseek-v4-flash-0731`	35
Doubao Seed 2.1 Turbo vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/doubao-seed-2.1-turbo-260628`	1	`deepseek/deepseek-v4.1-flash`	37
Doubao Seed Evolving vs OpenAI: gpt-oss-120b	`bytedance/doubao-seed-evolving`	1	`openai/gpt-oss-120b`	37
seed-2-0-code vs Qwen: Qwen3.8 27B	`bytedance/seed-2-0-code-preview-260328`	1	`qwen/qwen3.8-27b`	30
seed-2-0-lite vs MoonshotAI: Kimi K2.6	`bytedance/seed-2-0-lite-260428`	1	`moonshotai/kimi-k2.6`	27
seed-2-0-mini vs Google: Gemma 4 31B	`bytedance/seed-2-0-mini-260428`	1	`google/gemma-4-31b-it`	26
seed-2-0-pro vs DeepSeek: DeepSeek V4 Pro 0423	`bytedance/seed-2-0-pro-260328`	1	`deepseek/deepseek-v4-pro`	26
google/gemma-4-31B-it-turbo vs MiniMax: MiniMax M3	`google/gemma-4-31b-it-turbo`	2	`minimax/minimax-m3`	25
inclusionAI: Ling 3.1 Flash vs Z.ai: GLM 5.3	`inclusionai/ling-3.1-flash`	2	`z-ai/glm-5.3`	50
KAT Coder Air V2.5 vs Z.ai: GLM 5.2	`kwaipilot/kat-coder-air-v2.5`	1	`z-ai/glm-5.2`	48
KAT Coder Pro V2.5 vs Z.ai: GLM 5.3 Flash	`kwaipilot/kat-coder-pro-v2.5`	1	`z-ai/glm-5.3-flash`	48
Macaron V1 Tall vs MoonshotAI: Kimi K3	`mindai/macaron-v1-tall`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Mistral: Ministral 3 14B 2512	`deepseek/deepseek-v4-flash-0731`	35	`mistralai/ministral-14b-2512`	2