Gemini model

Gemini 3.1 Flash Image API

gemini/gemini-3.1-flash-image has an image output price of $0.1512 per image. Walk away if you need a published context window, token prices, or a first-party CacheSafety score, because this catalog snapshot does not publish them. Its latency band is 1000-3000ms.

GeminiPlatform curatedCatalog
Image Generation

Price deadline

Gemini Flash prices rise Jan 1, 2027

Per Google's published pricing page, Gemini Flash input prices double on Jan 1, 2027. The same workload runs an order of magnitude cheaper on DeepSeek and GLM. Source: Google pricing Full price breakdown

Budget control

Worried about runaway spend? Every API key supports a monthly hard cap.

Image price$0.151 / image
BillingPer generated image
Context length— tokens
Max output8.2k tokens

What is Gemini 3.1 Flash Image API in NextModel?

gemini/gemini-3.1-flash-image has an image output price of $0.1512 per image. Walk away if you need a published context window, token prices, or a first-party CacheSafety score, because this catalog snapshot does not publish them. Its latency band is 1000-3000ms.

Gemini 3.1 Flash Image (Nano Banana 2) via NextModel: context unpublished; $0.151 / image in / — out per 1M tokens. Capabilities: streaming, vision.

Best use cases

  • Call this id when you need a Gemini catalog image generation model with a published per-image price of $0.1512 and a 1000-3000ms latency band, and when streaming and vision capabilities are enough.
  • You need the listed capabilities on this catalog entry.
  • The listed price fits the workload better than the siblings in the same family.

When not to use

  • Do not call this id if your decision requires a published context window, token prices, or a first-party CacheSafety score.
  • Walk away if any of those facts is missing from the catalog.
  • A required number is unpublished in the catalog snapshot.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"gemini/gemini-3.1-flash-image","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

GeminiCatalog

Gemini 3 Pro Image (Nano Banana Pro) via NextModel: context unpublished; $0.314 / image in / — out per 1M tokens. Capabilities: streaming, vision.

$0.314 / imagePer image—Context
Best forimage understanding, multimodal chat
StreamingVision
Platform curatedCurated and maintained in the NextModel catalog
View details
GeminiCatalog

Gemini 3.1 Flash Lite Image(Nano Banana 2 Lite) via NextModel: context unpublished; $0.0336 / image in / — out per 1M tokens. Capabilities: streaming, vision.

$0.0336 / imagePer image—Context
Best forimage understanding, multimodal chat
StreamingVision
Platform curatedCurated and maintained in the NextModel catalog
View details
AnthropicCatalog

Claude Haiku 4.5 via NextModel: 200k-token context; $1 / 1M tokens in / $5 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1 / 1M tokensInput$5 / 1M tokensOutput200kContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Reading

Articles that explain Gemini 3.1 Flash Image (Nano Banana 2)

FAQ

Gemini 3.1 Flash Image (Nano Banana 2) API questions

What model id do I send for Gemini 3.1 Flash Image?

Send gemini/gemini-3.1-flash-image to https://api.nextmodel.app/v1 with your OpenAI SDK. If that id is missing from /v1/models, the page is stale.

What does the catalog list for price and context?

Gemini 3.1 Flash Image is listed at unpublished input and unpublished output. Context window: not published in catalog.

What should I treat as unverified?

Do not call this id if your decision requires a published context window, token prices, or a first-party CacheSafety score. Walk away if any of those facts is missing from the catalog.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.