gemma 4 31B it turbo
gemma 4 31B it turbo, by Google, answers in the CertuAI chat. These are its numbers on real requests, updated every 10 minutes, with its price and limits.
Summary in 2 facts
- gemma 4 31B it turbo, by Google, answers in the CertuAI chat.
- These are its numbers on real requests, updated every 10 minutes, with its price and limits.
In numbers
| Number | What it means |
|---|---|
| 10 minutes | These are its numbers on real requests, updated every 10 minutes, with its price and limits. |
| 10 answers | Uptime is shown only after 50 requests in the period, and latency only after 10 answers, so a model with three lucky requests never tops the list. |
| 7 days | Today counts from midnight UTC; this week is the last 7 days including today. |
Performance by period
| Period | Tokens | Requests | Latency (avg) | Latency p50 | Latency p90 | First token p50 | Throughput | Uptime |
|---|---|---|---|---|---|---|---|---|
| Today | — | — | — | — | — | — | — | — |
| This week | — | — | — | — | — | — | — | — |
| This month | — | — | — | — | — | — | — | — |
Limits and price
| Provider list price per million tokens | $0.090 input · $0.34 output |
|---|---|
| Credits per million tokens in your CertuAI account | 2,015 input · 7,612 output |
| Context window | 262,144 tokens |
| Longest answer | 16,384 tokens |
| Reads images | Yes |
| Reads PDFs natively | No |
| Served through | DeepInfra |
How these numbers are measured
Every request the chat and the API send to a model is counted the moment it finishes: tokens in and out, total latency (from the request to the last byte), time to first token (streamed answers) and throughput (output tokens per second, counted after the first token, only on answers with at least 20 tokens). Medians are estimated from a latency histogram, so they are close but not exact.
Uptime is 1 minus the share of requests the provider failed (timeouts, rate limits, server errors and network failures). A request rejected for being malformed does not count against the provider. Uptime is shown only after 50 requests in the period, and latency only after 10 answers, so a model with three lucky requests never tops the list.
Days are in UTC. Today counts from midnight UTC; this week is the last 7 days including today. Synthetic checks, when enabled, count for uptime and speed but never for popularity.