OpenAI compatible API · Attested · Public status

Google: Gemma 4 31B vs gpt-oss-120b

Google: Gemma 4 31B vs gpt-oss-120b: 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

gpt-oss-120b has the lower cheapest prompt+completion route on TrustedRouter. Google: Gemma 4 31B has more provider fallback routes, while Google: Gemma 4 31B has the larger context window. Probe-backed speed data is shown when enough recent samples exist.

$0.504/1MGoogle: Gemma 4 31B cheapest route

$0.13125/1Mgpt-oss-120b cheapest route

1351 msGoogle: Gemma 4 31B fastest measured p50 TTFT via crusoe

not enough datagpt-oss-120b fastest measured p50 TTFT

Google: Gemma 4 31Bgpt-oss-120b

Model idgoogle/gemma-4-31b-itlightning-ai/gpt-oss-120b

Publisher Google AI Studio Lightning AI

AI IQ IQ 101#66 IQ 105#53

Context262,144 tokens128,000 tokens

Provider routes242

Cheapest route$0.504/1M$0.13125/1M

Privacy posturehas provider E2EE routeprovider posture varies

Fastest measured p50 TTFT1351 ms via crusoenot enough data

Highest measured throughput191 tok/s via lightningnot enough data

Recent route uptime range88.89% to 100.00%not enough data

Modes chat chat

Google: Gemma 4 31B routes

Overview24 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

gpt-oss-120b routes

Overview2 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

Related comparisons

Browse every comparison

Google: Gemma 4 31B vs Z.ai: GLM 5.271 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K357 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.654 combined provider routes
DeepSeek: DeepSeek V4 Flash 0423 vs Google: Gemma 4 31B53 combined provider routes
DeepSeek: DeepSeek V4 Pro vs Google: Gemma 4 31B51 combined provider routes
Google: Gemma 4 31B vs OpenAI: gpt-oss-120b50 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.148 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B44 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 gpt-oss-120b?

Is Google: Gemma 4 31B or gpt-oss-120b cheaper?

The current cheapest TrustedRouter route is $0.504/1M for Google: Gemma 4 31B and $0.13125/1M for gpt-oss-120b. The comparison uses current catalog prices and updates as provider pricing changes.

Is Google: Gemma 4 31B or gpt-oss-120b faster?

Current measured p50 time to first token is 1351 ms for Google: Gemma 4 31B and not enough data for gpt-oss-120b. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Google: Gemma 4 31B and gpt-oss-120b 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 lightning-ai/gpt-oss-120b. This makes side-by-side evals possible without maintaining two provider integrations.