Free to start

Decision Models s1-fast-2 (GLOBAL) vs Google: Gemma 4 31B

Try both on us. Starter credit covers your first requests, then one key routes Decision Models s1-fast-2 (GLOBAL) and Gemma 4 31B. Switch by changing the model name.

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

Decision Models s1-fast-2 (GLOBAL) has the lower published input-plus-output rate. Google: Gemma 4 31B has more Credits provider routes and the larger context window. There is not enough recent probe data to compare speed.

$0.020045/1MDecision Models s1-fast-2 (GLOBAL) cheapest route

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

not enough dataDecision Models s1-fast-2 (GLOBAL) fastest measured p50 TTFT

665 msGoogle: Gemma 4 31B fastest measured p50 TTFT via crusoe

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.

Decision Models s1-fast-2 (GLOBAL)Google: Gemma 4 31B

Model iddecisionmodelsio/s1-fast-2google/gemma-4-31b-it

Publisherdecisionmodelsio Google AI Studio

AI IQ — IQ 101#116

Context8,192 tokens262,144 tokens

Credits provider routes116

Cheapest route$0.020045/1M$0.45365/1M

Cached inputNot published$0.03798/1M to $0.26375/1M

Privacy postureprovider posture varieshas Confidential route (E2EE + ZDR)

Fastest measured p50 TTFTnot enough data665 ms via crusoe

Highest measured throughputnot enough data146 tok/s via crusoe

Recent route uptime rangenot enough data0.00% to 100.00%

Modes decide chat

Decision Models s1-fast-2 (GLOBAL) routes

Overview1 Credits routes

Google: Gemma 4 31B routes

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

Related comparisons

Browse every comparison

Google: Gemma 4 31B vs Z.ai: GLM 5.349 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.248 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.3 Flash48 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K344 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B42 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 31B40 combined provider routes
Google: Gemma 4 31B vs OpenAI: gpt-oss-120b40 combined provider routes
Google: Gemma 4 31B vs Qwen: Qwen3.8 27B35 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.

POST /api/alpha/decidecurl

curl https://api.trustedrouter.com/api/alpha/decide \
  -H "Authorization: Bearer sk-tr-v1-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "decisionmodelsio/s1-fast-2",
    "state": "Customer: I was charged twice for order A-1.",
    "questions": {
      "refund": {"type": "boolean", "instructions": "Is a refund requested?"}
    }
  }'

Decision models: the API, the models, the numbers

Questions

Which should I use, Decision Models s1-fast-2 (GLOBAL) or Google: Gemma 4 31B?

Is Decision Models s1-fast-2 (GLOBAL) or Google: Gemma 4 31B cheaper?

The current cheapest TrustedRouter route is $0.020045/1M for Decision Models s1-fast-2 (GLOBAL) and $0.45365/1M for Google: Gemma 4 31B. The comparison uses current catalog prices and updates as provider pricing changes.

Is Decision Models s1-fast-2 (GLOBAL) or Google: Gemma 4 31B faster?

Current measured p50 time to first token is not enough data for Decision Models s1-fast-2 (GLOBAL) and 665 ms for Google: Gemma 4 31B. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Decision Models s1-fast-2 (GLOBAL) and Google: Gemma 4 31B with the same API?

Yes. Both take the same request on POST /api/alpha/decide, with the same TrustedRouter base URL and API key, so a side-by-side eval changes only the model id between decisionmodelsio/s1-fast-2 and google/gemma-4-31b-it. Decision Models s1-fast-2 (GLOBAL) does not take chat requests.