Google LLM Models

13 Google models on WaveSpeedAI — transparent per-token pricing, OpenAI-compatible endpoint, no cold starts.

Gemini 4 Carbon API

google/gemini-4-carbon

$4/M in· $20/M out· 1.0M ctx

Gemini 4 Argon API

google/gemini-4-argon

$4/M in· $20/M out· 1.0M ctx

Gemini 3.8 Flash API

google/gemini-3.8-flash

$1.65/M in· $8.25/M out· 1.0M ctx

Gemini 3 Flash Preview API

google/gemini-3-flash-preview

$0.5/M in· $3/M out· 1.0M ctx

Gemini 3.1 Flash Lite API

google/gemini-3.1-flash-lite

$0.25/M in· $1.5/M out· 1.0M ctx

Gemma 4 31b It API

google/gemma-4-31b-it

$0.15/M in· $0.4/M out· 262K ctx

Gemma 4 26b A4b It API

google/gemma-4-26b-a4b-it

$0.15/M in· $0.6/M out· 262K ctx

Gemini 3.7 Flash API

google/gemini-3.7-flash

$1.5/M in· $7.5/M out· 1.0M ctx

Gemini 3.6 Flash API

google/gemini-3.6-flash

$0.75/M in· $3.75/M out· 1.0M ctx

Gemini 3.5 Flash API

google/gemini-3.5-flash

$1.5/M in· $9/M out· 1.0M ctx

Gemini 3.1 Pro Preview API

google/gemini-3.1-pro-preview

$2/M in· $12/M out· 1.0M ctx

Gemini 3.5 Flash Lite API

google/gemini-3.5-flash-lite

$0.3/M in· $2.5/M out· 1.0M ctx

Gemini 3.1 Pro Preview Customtools API

google/gemini-3.1-pro-preview-customtools

$2/M in· $12/M out· 1.0M ctx

Browse all LLMs

Compare every Claude, GPT, Gemini, Qwen, DeepSeek, Llama, Grok and more.

wavespeed.ai/llm →

Open the Playground

Run any model live, see latency and cost in real time.

wavespeed.ai/llm/playground →

Seedream 5.5 is LIVE | Try in Image Generator →