Last refreshed 2026-05-17. Next refresh: weekly.
Why use Gemini 3 Flash on Replicate API?
Replicate API offers Gemini 3 Flash with pay-as-you-go pricing at $0.50/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Gemini 3 Flash across 4 providers to find the best fit for your use caseInput / 1M
$0.50
Output / 1M
$3.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"google/gemini-3-flash",
input={"prompt": "Hello"}Model ID
google/gemini-3-flashRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# google/gemini-3-flash format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"google/gemini-3-flash",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "google/gemini-3-flash", not the LLMReference slug "gemini-3-flash".
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare Gemini 3 Flash Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Replicate API | $0.50 | $3.00 |
| GCP Vertex AI | $0.50 | $3.00 |
| Google AI Studio | $0.50 | $3.00 |
| Vercel AI Gateway | $0.50 | $3.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.50 |
| Output tokens | $3.00 |
Capabilities
VisionMultimodalJSON / Tool useCode ExecutionAudio
About Gemini 3 Flash
Gemini 3 Flash is Google's speed-optimized Gemini 3 model, available in public preview via the Gemini API and Vertex AI. It supports text, image, audio, and video inputs with a 1M token context window and is priced at $0.50 per 1M input tokens and $3.00 per 1M output tokens.
Get Started
Model Specs
Released2025-12-17
Context1m
ArchitectureDecoder Only
Knowledge cutoff2025-01