Gemma 4 31B-it FP8
google/gemma-4-31b-itAvailableChat model
Gemma 4 31B-it FP8 is a chat model created by Google with a 262.1K tokens context window. It accepts text and returns text through the OpenWaya API.
Model typeChat model
ModalitiesText → Text
Input / output per 1M$ 0.39 / $ 0.97
Context window262.1K tokens
Catalog updatedNov 2, 2026
OpenWaya statusAvailable
Best fit
Where this model fits.
These applications are derived from the model's published capabilities and context, not marketing claims about unmeasured quality.
Generation, summarization, and extraction
Long-document and large-context work
Responsive, streaming experiences
Availability and performance
Available now, monitored continuously.
This model accepts OpenWaya API requests. We monitor its serving paths continuously and publish measured latency and uptime after each evidence threshold is met.
API availabilityAvailable
Accepting API requests.
MonitoringContinuous
Serving-path checks and automatic routing remain active.
P50 latencyBuilding baseline
Shown after the minimum sample threshold is met.
Uptime · 24hBuilding baseline
Published once enough production evidence exists.
Capabilities
What the API supports.
Use these declared capabilities to check application compatibility before testing.
ChatStreamingText generation
Pricing and capacity
Know the cost before you route.
Current OpenWaya retail rates are displayed in USD using the governed fallback rate. Display conversion is indicative; checkout confirms settlement currency and final amount.
Input / 1M tokens$ 0.39
Output / 1M tokens$ 0.97
Context window262.1K tokens
Example · 10K input + 2K output$ 0.01
Examples are arithmetic estimates; billed usage follows the measured token ledger.
OpenAI-compatible
Call this exact model.
The creator-qualified model ID is stable. OpenWaya manages credentials, availability checks, and the serving path behind the API boundary.
const result = await client.chat.completions.create({
model: "google/gemma-4-31b-it",
messages: [{ role: "user", content: "Hello" }],
stream: true,
});curl https://api.openwaya.africa/v1/chat/completions \
-H "Authorization: Bearer $OPENWAYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemma-4-31b-it","messages":[{"role":"user","content":"Hello"}]}'Frequently asked questions
Quick answers for builders.
What is Gemma 4 31B-it FP8?
Gemma 4 31B-it FP8 is a chat model created by Google with a 262.1K tokens context window. It accepts text and returns text through the OpenWaya API.
Is Gemma 4 31B-it FP8 available on OpenWaya?
Yes. Gemma 4 31B-it FP8 is currently callable with the model ID google/gemma-4-31b-it.
How much does Gemma 4 31B-it FP8 cost?
Input costs $ 0.39 per million tokens and output costs $ 0.97 per million tokens. These Gemma 4 31B-it FP8rates are displayed in USD.
What does Gemma 4 31B-it FP8 support?
It is classified as a chat model, accepts text, returns text, and has a 262.1K tokens context window.