gemini-2.5-flash-nothink

Google

Gemini-2.5-flash defaults to thinking enabled; to disable thinking, request the name gemini-2.5-flash-nothink, which only supports OpenAI-compatible format calls and does not support Gemini SDK; for the native Gemini SDK, please set the parameter budget=0 directly.

API Pricing

Input$0.3 / 1M tokens
Output$2.499 / 1M tokens
Cache read$0.03 / 1M tokens

Specifications

Context1.05M tokens
Modalitiestext, image, video, audio, PDF
CapabilitiesThinking, Tool calling, Web search, URL context, Code interpreter, File search, Structured outputs, Prompt caching

Frequently asked questions

What is gemini-2.5-flash-nothink?

Gemini-2.5-flash defaults to thinking enabled; to disable thinking, request the name gemini-2.5-flash-nothink, which only supports OpenAI-compatible format calls and does not support Gemini SDK; for the native Gemini SDK, please set the parameter budget=0 directly.

What is the context length of gemini-2.5-flash-nothink?

gemini-2.5-flash-nothink has a 1,048,576 token context window.

How much does gemini-2.5-flash-nothink cost?

On AIHubMix, gemini-2.5-flash-nothink costs $0.3 per million input tokens and $2.499 per million output tokens. Cached input reads are billed at $0.03 per million tokens.

What modalities does gemini-2.5-flash-nothink support?

gemini-2.5-flash-nothink accepts text, image, video, audio and PDF input.

What capabilities does gemini-2.5-flash-nothink support?

gemini-2.5-flash-nothink supports tool calling, function calling, structured outputs and long context. Per-protocol parameter support is listed in the capability table on this page.

How do I call gemini-2.5-flash-nothink via API?

gemini-2.5-flash-nothink is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gemini-2.5-flash-nothink — no other code changes needed.

Who created gemini-2.5-flash-nothink?

gemini-2.5-flash-nothink is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was gemini-2.5-flash-nothink released?

gemini-2.5-flash-nothink was released on June 24, 2025 by Google.

More models from Google

See all Google models →

Gemini Nano Banana 2.1

by Google

Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest high-efficiency image…

$1.5/1M in · $7.5/1M out
65,536 tokens context

Gemini 3.8 Flash Lite Tts

by Google

Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) is Google's fast and affordable…

$1/1M in · $1/1M out
8,192 tokens context

Gemini 3.8 Flash Tts

by Google

Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) is Google's 3.8 Flash text-to-speech audio…

$0.5/1M in · $9/1M out
8,192 tokens context

Gemini 3.8 Flash

by Google

Gemini 3.8 Flash is Google's most intelligent Flash-series model, designed for…

$0.75/1M in · $3.75/1M out
1,048,576 tokens context

Gemini 3.7 Flash

by Google

Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web…

$0.75/1M in · $3.75/1M out
1,048,576 tokens context

Gemini 3.6 Flash

by Google

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world…

$1.5/1M in · $7.5/1M out
1,048,576 tokens context

Use gemini-2.5-flash-nothink via the AIHubMix unified API — one interface for every major LLM.