OpenAI compatible API · Attested · Public status

DeepSeek V4 Pro 0813 vs Xiaomi: MiMo-V2.5

DeepSeek V4 Pro 0813 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. Xiaomi: MiMo-V2.5 has more provider fallback routes, while Xiaomi: MiMo-V2.5 has the larger context window. Current TrustedRouter probes show DeepSeek V4 Pro 0813 with the lower p50 TTFT.

$2.7852/1MDeepSeek V4 Pro 0813 cheapest route

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

1714 msDeepSeek V4 Pro 0813 fastest measured p50 TTFT via baseten

3397 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.

DeepSeek V4 Pro 0813Xiaomi: MiMo-V2.5

Model iddeepseek/deepseek-v4-pro-0813xiaomi/mimo-v2.5

Publisher DeepSeek Xiaomi MiMo

AI IQ — IQ 109#59

Context1,024,000 tokens1,048,576 tokens

Credits provider routes35

Cheapest route$2.7852/1M$0.4431/1M

Cached input$0.02321/1M to $0.13926/1M$0.01/1M to $0.102019/1M

Privacy posturehas ZDR routeprovider posture varies

Fastest measured p50 TTFT1714 ms via baseten3397 ms via xiaomi

Highest measured throughputnot enough datanot enough data

Recent route uptime range100.00%100.00%

Modes chat chat

DeepSeek V4 Pro 0813 routes

Overview3 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

Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5.236 combined provider routes
DeepSeek V4 Pro 0813 vs Z.ai: GLM 5.234 combined provider routes
MoonshotAI: Kimi K3 vs Xiaomi: MiMo-V2.528 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Xiaomi: MiMo-V2.527 combined provider routes
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 5.327 combined provider routes
DeepSeek V4 Pro 0813 vs MoonshotAI: Kimi K326 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek V4 Pro 081325 combined provider routes
DeepSeek V4 Pro 0813 vs Z.ai: GLM 5.325 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="deepseek/deepseek-v4-pro-0813",
    messages=messages,
)

Questions

Which should I use, DeepSeek V4 Pro 0813 or Xiaomi: MiMo-V2.5?

Is DeepSeek V4 Pro 0813 or Xiaomi: MiMo-V2.5 cheaper?

The current cheapest TrustedRouter route is $2.7852/1M for DeepSeek V4 Pro 0813 and $0.4431/1M for Xiaomi: MiMo-V2.5. The comparison uses current catalog prices and updates as provider pricing changes.

Is DeepSeek V4 Pro 0813 or Xiaomi: MiMo-V2.5 faster?

Current measured p50 time to first token is 1714 ms for DeepSeek V4 Pro 0813 and 3397 ms for Xiaomi: MiMo-V2.5. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test DeepSeek V4 Pro 0813 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 deepseek/deepseek-v4-pro-0813 and xiaomi/mimo-v2.5. This makes side-by-side evals possible without maintaining two provider integrations.