OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Pro 0423 vs 0GM-1.0-35B-A3B-SIA

DeepSeek V4 Pro 0423 vs 0GM-1.0-35B-A3B-SIA: 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

DeepSeek: DeepSeek V4 Pro 0423 has the lower cheapest prompt+completion route on TrustedRouter. DeepSeek: DeepSeek V4 Pro 0423 has more provider fallback routes, while DeepSeek: DeepSeek V4 Pro 0423 has the larger context window. Current TrustedRouter probes show DeepSeek: DeepSeek V4 Pro 0423 with the lower p50 TTFT.

$2.75355/1MDeepSeek: DeepSeek V4 Pro 0423 cheapest route

$3.95836/1M0GM-1.0-35B-A3B-SIA cheapest route

1307 msDeepSeek: DeepSeek V4 Pro 0423 fastest measured p50 TTFT via wandb

2512 ms0GM-1.0-35B-A3B-SIA fastest measured p50 TTFT via zero-g

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 04230GM-1.0-35B-A3B-SIA

Model iddeepseek/deepseek-v4-prozero-g/0gm-1.0-35b-a3b-sia

Publisher DeepSeek 0G Private Computer

AI IQ IQ 117#32 —

Context1,048,576 tokens32,768 tokens

Provider routes291

Cheapest route$2.75355/1M$3.95836/1M

Privacy posturehas ZDR routehas confidential-compute route

Fastest measured p50 TTFT1307 ms via wandb2512 ms via zero-g

Highest measured throughputnot enough datanot enough data

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

Modes chat chat

DeepSeek: DeepSeek V4 Pro 0423 routes

Overview29 endpoints
PricingPrompt and completion rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

0GM-1.0-35B-A3B-SIA routes

Overview1 endpoints

Related comparisons

Browse every comparison

DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.283 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K366 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4 Pro 042364 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: gpt-oss-120b64 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.661 combined provider routes
DeepSeek: DeepSeek V4 Flash 0423 vs DeepSeek: DeepSeek V4 Pro 042360 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemma 4 31B58 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs Z.ai: GLM 5.153 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 0GM-1.0-35B-A3B-SIA?

Is DeepSeek: DeepSeek V4 Pro 0423 or 0GM-1.0-35B-A3B-SIA cheaper?

The current cheapest TrustedRouter route is $2.75355/1M for DeepSeek: DeepSeek V4 Pro 0423 and $3.95836/1M for 0GM-1.0-35B-A3B-SIA. The comparison uses current catalog prices and updates as provider pricing changes.

Is DeepSeek: DeepSeek V4 Pro 0423 or 0GM-1.0-35B-A3B-SIA faster?

Current measured p50 time to first token is 1307 ms for DeepSeek: DeepSeek V4 Pro 0423 and 2512 ms for 0GM-1.0-35B-A3B-SIA. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test DeepSeek: DeepSeek V4 Pro 0423 and 0GM-1.0-35B-A3B-SIA 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 zero-g/0gm-1.0-35b-a3b-sia. This makes side-by-side evals possible without maintaining two provider integrations.