---
title: "Gemini 2.5 Flash — API access"
description: "Gemini 2.5 Flash API pricing: official $0.30/$2.50 per 1M tokens, $0.15/$1.25 with the flat 50% apiToken.sale discount. Proven previous-generation Flash."
url: "https://apitoken.sale/models/gemini-2-5-flash"
language: "en"
---
# Gemini 2.5 Flash

Gemini 2.5 Flash is the proven previous-generation Flash — a stable workhorse for production pipelines evaluated against the 2.5 line.

- **Model ID:** `gemini-2.5-flash`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.3 input / $2.5 output
- **Your price (per 1M):** input $0.15, output $1.25 (flat 50% off)
- **Base URL:** `https://gemini.api.apitoken.sale` · **Endpoint:** `POST /v1beta/models/gemini-2.5-flash:generateContent` (x-goog-api-key)

## Best for

- Pipelines tuned and evaluated against Gemini 2.5 Flash.
- Balanced coding and content workloads.
- Teams migrating gradually to the Gemini 3 line.

## Notes

- Cached input bills at 10% of input; caching is automatic on repeated prefixes.
- Same 1M-token context and 64K max output as the newer Flash models.

## Call it

```bash
curl https://gemini.api.apitoken.sale/v1beta/models/gemini-2.5-flash:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**How much does the Gemini 2.5 Flash API cost?**

Officially $0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.03. With the flat 50% apiToken.sale discount that is $0.15/$1.25.

**What is the model ID for Gemini 2.5 Flash?**

gemini-2.5-flash. Use it unchanged with the Google GenAI SDK or any Gemini-compatible tool pointed at https://gemini.api.apitoken.sale, with the key sent as x-goog-api-key.

**Gemini 2.5 Flash or 3.5 Flash?**

2.5 Flash is far cheaper per token and proven in production; 3.5 Flash is the stronger current model. Keep 2.5 Flash where prompts and evals are pinned to it, default to the 3.x line for new work.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models