OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Pro vs Qwen: Qwen3.5 397B A17B

Compare DeepSeek: DeepSeek V4 Pro and Qwen: Qwen3.5 397B A17B by providers, context, price, and TrustedRouter route support.

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

DeepSeek: DeepSeek V4 Pro has the lower cheapest prompt+completion route on TrustedRouter. DeepSeek: DeepSeek V4 Pro has more provider fallback routes, while DeepSeek: DeepSeek V4 Pro has the larger context window. Probe-backed speed data is shown when enough recent samples exist.

$1.37025/1MDeepSeek: DeepSeek V4 Pro cheapest route

$2.97675/1MQwen: Qwen3.5 397B A17B cheapest route

not enough dataDeepSeek: DeepSeek V4 Pro measured p50 TTFT

not enough dataQwen: Qwen3.5 397B A17B measured p50 TTFT

DeepSeek: DeepSeek V4 ProQwen: Qwen3.5 397B A17B

Model iddeepseek/deepseek-v4-proqwen/qwen3.5-397b-a17b

PublisherDeepSeekDeepInfra

AI IQ IQ 115#30 —

Context1,048,576 tokens262,144 tokens

Provider routes2616

Cheapest route$1.37025/1M$2.97675/1M

Privacy posturehas ZDR routehas confidential-compute route

Modes chat chat

DeepSeek: DeepSeek V4 Pro routes

Overview26 endpoints
PricingPrompt and completion rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

Qwen: Qwen3.5 397B A17B routes

Overview16 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

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://gchircrcif.eu-west-3.awsapprunner.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=messages,
)