Gemini 2.5 Flash Image
Google logo

Gemini 2.5 Flash Image

gemini-2.5-flash-image
Google
Aihubmix supports the gemini-2.5-flash-image model (known on social media as nano-banana); you can add the extra parameter modalities=["text", "image"] via the OpenAI-compatible chat interface. This model allows adjustment of the generated image’s aspect ratio through parameters, but requires using the native Gemini SDK.

Pricing

0.04$/image ;2.49m/tokens

Input Modalities

  • Text
  • Vision

Output Modalities

  • Image

Context length

  • 65.5K tokens

Max output

  • 32.8K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Multimodal output
  • Structured outputs
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

VertexAI gemini-2.5-flash-image
Pricing$0.3$2.499
Input Image$0.3/M tokens
Output Image$30/M tokens
Context32K
Max output8K
Latency8.3S
Throughput1314.0TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today
Google AI Studio gemini-2.5-flash-image
Pricing$0.3$2.499
Input Image$0.3/M tokens
Output Image$30/M tokens
Context32K
Max output8K
Latency5.8S
Throughput214.3TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for gemini-2.5-flash-image

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Frequently asked questions

What is Gemini 2.5 Flash Image?

Aihubmix supports the gemini-2.5-flash-image model (known on social media as nano-banana); you can add the extra parameter modalities=["text", "image"] via the OpenAI-compatible chat interface. This model allows adjustment of the generated image’s aspect ratio through parameters, but requires using the native Gemini SDK.