OpenAI compatible API · Attested · Public status

Qwen: Qwen3.5 397B A17B vs Xiaomi: MiMo-V2.5

Qwen: Qwen3.5 397B A17B vs MiMo-V2.5: compare current API pricing, context, provider routes, privacy, p50 latency, and OpenAI-compatible access.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Compare routesProviders, price, context, and policy posture in one view.

Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.

Same API shapeUse the OpenAI client and set the model you want.

Practical read

Monthly evidence

Xiaomi: MiMo-V2.5 has the lower cheapest prompt+completion route on TrustedRouter. Qwen: Qwen3.5 397B A17B has more provider fallback routes, while Xiaomi: MiMo-V2.5 has the larger context window. Current TrustedRouter probes show Qwen: Qwen3.5 397B A17B with the lower p50 TTFT.

$3.63975/1MQwen: Qwen3.5 397B A17B cheapest route

$0.4431/1MXiaomi: MiMo-V2.5 cheapest route

1112 msQwen: Qwen3.5 397B A17B fastest measured p50 TTFT via digitalocean

3606 msXiaomi: MiMo-V2.5 fastest measured p50 TTFT via xiaomi

Prices and live route measurements can change. Use the monthly reports when you need a stable evidence window, then run a small task-specific eval before choosing a production default.

Qwen: Qwen3.5 397B A17BXiaomi: MiMo-V2.5

Model idqwen/qwen3.5-397b-a17bxiaomi/mimo-v2.5

Publisher DeepInfra Xiaomi MiMo

AI IQ — IQ 108#67

Context262,144 tokens1,050,000 tokens

Credits provider routes105

Cheapest route$3.63975/1M$0.4431/1M

Cached input$0.047475/1M to $0.58025/1M$0.01/1M to $0.10645/1M

Privacy posturehas provider E2EE routeprovider posture varies

Fastest measured p50 TTFT1112 ms via digitalocean3606 ms via xiaomi

Highest measured throughputnot enough datanot enough data

Recent route uptime range33.33% to 100.00%90.00% to 100.00%

Modes chat chat

Qwen: Qwen3.5 397B A17B routes

Overview10 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

Xiaomi: MiMo-V2.5 routes

Overview5 Credits routes
PricingInput, cached input, and output rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

Related comparisons

Browse every comparison

Qwen: Qwen3.5 397B A17B vs Z.ai: GLM 5.238 combined provider routes
Qwen: Qwen3.5 397B A17B vs Z.ai: GLM 5.337 combined provider routes
Qwen: Qwen3.5 397B A17B vs Z.ai: GLM 5.3 Flash36 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen: Qwen3.5 397B A17B34 combined provider routes
MoonshotAI: Kimi K3 vs Qwen: Qwen3.5 397B A17B34 combined provider routes
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5.233 combined provider routes
OpenAI: gpt-oss-120b vs Qwen: Qwen3.5 397B A17B32 combined provider routes
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5.332 combined provider routes

Production choice

Pick a default model. Keep fallback enabled.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

OpenAI clientPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-397b-a17b",
    messages=messages,
)

Questions

Which should I use, Qwen: Qwen3.5 397B A17B or Xiaomi: MiMo-V2.5?

Is Qwen: Qwen3.5 397B A17B or Xiaomi: MiMo-V2.5 cheaper?

The current cheapest TrustedRouter route is $3.63975/1M for Qwen: Qwen3.5 397B A17B and $0.4431/1M for Xiaomi: MiMo-V2.5. The comparison uses current catalog prices and updates as provider pricing changes.

Is Qwen: Qwen3.5 397B A17B or Xiaomi: MiMo-V2.5 faster?

Current measured p50 time to first token is 1112 ms for Qwen: Qwen3.5 397B A17B and 3606 ms for Xiaomi: MiMo-V2.5. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Qwen: Qwen3.5 397B A17B and Xiaomi: MiMo-V2.5 with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between qwen/qwen3.5-397b-a17b and xiaomi/mimo-v2.5. This makes side-by-side evals possible without maintaining two provider integrations.