📡 AI API Radar

Google Gemini Unknown

Gemini 3.5 Flash — pricing & price history

Bottom line: Gemini 3.5 Flash costs $1.5 per 1M input tokens and $9 per 1M output tokens on Google Gemini, with a 1.048576M-token context window.

API model id: gemini-3.5-flash · Verified against the provider's pricing page as of 2026-06-22.

Input / 1M tokens
$1.5
Output / 1M tokens
$9
Context window
1.048576M
Provider status
Unknown

Price history

DateInput /1MOutput /1M
2026-08-20$1.5$9
2026-08-19$1.5$9
2026-08-18$1.5$9
2026-08-17$1.5$9
2026-08-16$1.5$9
2026-08-15$1.5$9
2026-08-14$1.5$9
2026-08-13$1.5$9
2026-08-12$1.5$9
2026-08-11$1.5$9
2026-08-10$1.5$9
2026-08-09$1.5$9

Cheaper alternatives with similar context

ModelProviderInput /1MOutput /1MContext
DeepSeek V4 Flash DeepSeek $0.14 $0.28 1M
GPT-4.1 nano OpenAI $0.1 $0.4 1M
DeepSeek V4 Pro DeepSeek $0.44 $0.87 1M
GPT-4.1 mini OpenAI $0.4 $1.6 1M
Grok 4.3 (≤200K) xAI (Grok) $1.25 $2.5 1M
DeepSeek V4 Pro (via OpenRouter) OpenRouter $1.6 $3.2 1.048576M

Routing agents: call price_history("google--gemini-3-5-flash") or cheapest_model(min_context=1048576) over our MCP/x402 API to use this programmatically. Docs →