OpenAI compatible API · Attested · Public status

Google: Gemma 4 31B vs meta/llama-3.2-90b-vision-instruct

Google: Gemma 4 31B has the lower published input-plus-output rate, more Credits provider routes and the lower measured p50 time to first token. Compare price, speed, context, and privacy.

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 the lower published input-plus-output rate, more Credits provider routes and the lower measured p50 time to first token.

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

$12.66/1Mmeta/llama-3.2-90b-vision-instruct cheapest route

1073 msGoogle: Gemma 4 31B fastest measured p50 TTFT via friendli

2255 msmeta/llama-3.2-90b-vision-instruct fastest measured p50 TTFT via nvidia-nim

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 31Bmeta/llama-3.2-90b-vision-instruct

Model idgoogle/gemma-4-31b-itmeta-llama/llama-3.2-90b-vision-instruct

Publisher Google AI Studio Meta

AI IQ IQ 101#110 —

Context262,144 tokens0 tokens

Credits provider routes171

Cheapest route$0.45365/1M$12.66/1M

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

Privacy posturehas Confidential route (E2EE + ZDR)provider posture varies

Fastest measured p50 TTFT1073 ms via friendli2255 ms via nvidia-nim

Highest measured throughput57 tok/s via crusoenot enough data

Recent route uptime range0.00% to 100.00%66.67%

Modes chat chat

Google: Gemma 4 31B routes

Overview17 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

meta/llama-3.2-90b-vision-instruct routes

Overview1 Credits routes

Related comparisons

Browse every comparison

Google: Gemma 4 31B vs Z.ai: GLM 5.3 Flash51 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.350 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.249 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K346 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B44 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 31B41 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.

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 meta/llama-3.2-90b-vision-instruct?

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

Is Google: Gemma 4 31B or meta/llama-3.2-90b-vision-instruct cheaper?

The current cheapest TrustedRouter route is $0.45365/1M for Google: Gemma 4 31B and $12.66/1M for meta/llama-3.2-90b-vision-instruct. The comparison uses current catalog prices and updates as provider pricing changes.

Is Google: Gemma 4 31B or meta/llama-3.2-90b-vision-instruct faster?

Current measured p50 time to first token is 1073 ms for Google: Gemma 4 31B and 2255 ms for meta/llama-3.2-90b-vision-instruct. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Google: Gemma 4 31B and meta/llama-3.2-90b-vision-instruct 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 meta-llama/llama-3.2-90b-vision-instruct. This makes side-by-side evals possible without maintaining two provider integrations.