OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Pro 0423 vs apertus-70b

DeepSeek V4 Pro 0423 has the lower published input-plus-output rate, more Credits provider routes and the larger context window. There is not enough recent probe data to compare speed. Compare price, speed, context, and privacy.

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

DeepSeek V4 Pro 0423 has the lower published input-plus-output rate, more Credits provider routes and the larger context window. There is not enough recent probe data to compare speed.

$0.79125/1MDeepSeek: DeepSeek V4 Pro 0423 cheapest route

$2.950836/1Mapertus-70b cheapest route

1152 msDeepSeek: DeepSeek V4 Pro 0423 fastest measured p50 TTFT via crusoe

not enough dataapertus-70b fastest measured p50 TTFT

The price comparison adds each route's rate for one million input tokens and one million output tokens; your cost depends on your input/output mix. 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: DeepSeek V4 Pro 0423apertus-70b

Model iddeepseek/deepseek-v4-proswiss-ai/apertus-70b-instruct

Publisher DeepSeek Swiss AI

AI IQ IQ 124#29 —

Context1,048,576 tokens30,000 tokens

Credits provider routes161

Cheapest route$0.79125/1M$2.950836/1M

Cached input$0.01/1M to $0.739555/1MNot published

Privacy posturehas ZDR routehas ZDR route

Fastest measured p50 TTFT1152 ms via crusoenot enough data

Highest measured throughputnot enough datanot enough data

Recent route uptime range83.33% to 100.00%100.00%

Modes chat chat

DeepSeek: DeepSeek V4 Pro 0423 routes

Overview16 Credits routes
PricingInput, cached input, and output rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

apertus-70b routes

Overview1 Credits routes

Related comparisons

Browse every comparison

DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.3 Flash50 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.349 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.248 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K345 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4 Pro 042343 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs DeepSeek: DeepSeek V4.1 Flash40 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: gpt-oss-120b39 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3.8 27B34 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",
    messages=messages,
)

Questions

Which should I use, DeepSeek: DeepSeek V4 Pro 0423 or apertus-70b?

DeepSeek V4 Pro 0423 has the lower published input-plus-output rate, more Credits provider routes and the larger context window. There is not enough recent probe data to compare speed.

Is DeepSeek: DeepSeek V4 Pro 0423 or apertus-70b cheaper?

The current cheapest TrustedRouter route is $0.79125/1M for DeepSeek: DeepSeek V4 Pro 0423 and $2.950836/1M for apertus-70b. The comparison uses current catalog prices and updates as provider pricing changes.

Is DeepSeek: DeepSeek V4 Pro 0423 or apertus-70b faster?

Current measured p50 time to first token is 1152 ms for DeepSeek: DeepSeek V4 Pro 0423 and not enough data for apertus-70b. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test DeepSeek: DeepSeek V4 Pro 0423 and apertus-70b 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 and swiss-ai/apertus-70b-instruct. This makes side-by-side evals possible without maintaining two provider integrations.