Access gemini-2.5-flashthrough PromptShuttle's OpenAI-compatible API via GeminiVertex / Gemini. It offers a 1,048,576-token context window and up to 65,536 output tokens, priced at $0.3 per million input tokens and $2.5 per million output tokens. It accepts image input for multimodal prompts.
Scheduled shutdown: October 16, 2026
Recommended replacement: gemini-3.5-flash
Provider
GeminiVertex, Gemini
Context window
1,048,576 tokens
Max output
65,536 tokens
Input price
$0.3 / 1M
Output price
$2.5 / 1M
Input modalities
Text, Audio, Image, Video
Output modalities
Text
Structured output
Yes
USD per 1,000,000 tokens.
| Input | Output | Cached input |
|---|---|---|
| $ 0.3 | $ 2.5 | $ 0.03 |
Point your OpenAI SDK at PromptShuttle and call gemini-2.5-flash with a single base-URL change — with cost tracking, model routing and agent orchestration built in.