OpenAI compatible API · Attested · Public status

Google: Gemma 4 31B vs ScaleDown Compress

Google: Gemma 4 31B vs ScaleDown Compress: 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

Google: Gemma 4 31B has more Credits provider routes and the lower measured p50 time to first token. ScaleDown Compress has the lower published input-plus-output rate and the larger context window.

$0.45365/1MGoogle: Gemma 4 31B cheapest route

$0.05275/1MScaleDown Compress cheapest route

673 msGoogle: Gemma 4 31B fastest measured p50 TTFT via pearl

1400 msScaleDown Compress fastest measured p50 TTFT via scaledown

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.

Google: Gemma 4 31BScaleDown Compress

Model idgoogle/gemma-4-31b-itscaledown/compress

Publisher Google AI Studio ScaleDown

AI IQ IQ 101#99 —

Context262,144 tokens1,000,000 tokens

Credits provider routes151

Cheapest route$0.45365/1M$0.05275/1M

Cached input$0.03798/1M to $0.26375/1MNot published

Privacy posturehas provider E2EE routehas ZDR route

Fastest measured p50 TTFT673 ms via pearl1400 ms via scaledown

Highest measured throughput308 tok/s via lightningnot enough data

Recent route uptime range0.00% to 100.00%100.00%

Modes chat chat

Google: Gemma 4 31B routes

Overview15 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

ScaleDown Compress routes

Overview1 Credits routes

Related comparisons

Browse every comparison

Google: Gemma 4 31B vs Z.ai: GLM 5.243 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.341 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.3 Flash40 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B39 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K339 combined provider routes
Google: Gemma 4 31B vs OpenAI: gpt-oss-120b37 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.634 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 31B33 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="google/gemma-4-31b-it",
    messages=messages,
)

Questions

Which should I use, Google: Gemma 4 31B or ScaleDown Compress?

Google: Gemma 4 31B has more Credits provider routes and the lower measured p50 time to first token. ScaleDown Compress has the lower published input-plus-output rate and the larger context window.

Is Google: Gemma 4 31B or ScaleDown Compress cheaper?

The current cheapest TrustedRouter route is $0.45365/1M for Google: Gemma 4 31B and $0.05275/1M for ScaleDown Compress. The comparison uses current catalog prices and updates as provider pricing changes.

Is Google: Gemma 4 31B or ScaleDown Compress faster?

Current measured p50 time to first token is 673 ms for Google: Gemma 4 31B and 1400 ms for ScaleDown Compress. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Google: Gemma 4 31B and ScaleDown Compress with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between google/gemma-4-31b-it and scaledown/compress. This makes side-by-side evals possible without maintaining two provider integrations.