nvidia No sharer online

google/gemma-4-31b-it on Nvidia.

Nvidia serves google/gemma-4-31b-it at $0.1000 per million input tokens and $0.340 per million output. Context window: 256K tokens. No sharer is online for it at the moment. 5 requests in the last 30 days.

Input /Mtok

$0.1000

Output /Mtok

$0.340

Context

256K

Sharers online

0

01Overview

Nvidia serves google/gemma-4-31b-it at $0.1000 per million input tokens and $0.340 per million output. Context window: 256K tokens. No sharer is online for it at the moment. 5 requests in the last 30 days.

02Pricing

Per million tokens, in USD. This is the rate you are charged.
Input$0.1000
Output$0.340
Cache read$0.1000

03Capabilities

You can attach an image to a request and ask about it.This model can reason at length before it answers.This model can call tools and functions you define.
Context window256K tokens
Maximum output16K tokens
Knowledge cutoff2025-01
Released2026-04-02
Supported parametersmax_tokens, temperature, top_p, stop, frequency_penalty, presence_penalty, seed, logit_bias, logprobs, top_logprobs, tools, tool_choice, response_format, structured_outputs, reasoning, reasoning_effort

06Call it

Any OpenAI- or Anthropic-compatible SDK works. Use this exact model id:

curlTerminal
curl https://aile.sh/v1/chat/completions \
  -H "Authorization: Bearer $AILE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/google/gemma-4-31b-it",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Quickstart · API reference

07Alternatives

Other providers serve google/gemma-4-31b-it too, at their own rates — compare every provider for google/gemma-4-31b-it.

Other models from Nvidia:

ModelProviderInput /MtokOutput /MtokStatus
deepseek-ai/deepseek-v4.1-flashnvidia$0.0141$1.76Offline
moonshotai/kimi-k3nvidia$0.182$9.34Offline
z-ai/glm-5.3-flashnvidia$0.0457$0.0742Offline
moonshotai/kimi-k2.6nvidia$0.390$1.80Offline
openai/gpt-oss-20bnvidia$0.0180$0.0900Offline
meta/muse-glimmer-30bnvidia$0.300$1.20Offline
nvidia/nemotron-3.5-lightning-30b-a3bnvidia——Offline
google/diffusiongemma-26b-a4b-itnvidia——Offline
poolside/laguna-xs-2.1nvidia$0.1000$0.200Offline
meta/llama-3.2-11b-vision-instructnvidia——Offline
meta/llama-3.2-90b-vision-instructnvidia——Offline
meta/llama-guard-4-12bnvidia$0.180$0.180Offline

Similar published rates elsewhere:

ModelProviderInput /MtokOutput /MtokStatus
deepseek-v4.1-flashalibaba$0.300$1.20Offline
deepseek-v4.1-flashalibaba-cn$0.299$1.20Offline
deepseek-ai/DeepSeek-V4.1-Flashbaseten$0.300$1.20Offline
deepseek-v4.1-flashbazaarlink$0.225$0.900Offline
cline-pass/deepseek-v4.1-flashclinepass$0.300$1.20Offline
deepseek/deepseek-v4.1-flashclinepass$0.300$1.20Offline