Gemini 2.5 Flash is Google DeepMind's price-performance workhorse model, built for speed and low cost while handling text, audio, image and video input. It has a 1M-token context window, supports tool use and function calling, and lets developers control how much the model reasons to balance latency and cost. Google reports improvements across reasoning, multimodality, code and long context, with 20 to 30% fewer tokens used in evaluations, plus more expressive native audio output. Ideal for high-volume, latency-sensitive applications, assistants and general-purpose multimodal tasks needing a strong quality-to-cost ratio.
$0.2317 in · $1.9305 out · $0.0232 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.2317 | per 1M tokens |
| Cached input (cache hit) | $0.0232 | per 1M tokens |
| Output tokens | $1.9305 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gemini-2.5-flash", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: gemini-2.5-flash · works with OpenAI SDKs — just point base_url at api.tunerouter.com