llmburn.

← All models

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

Last Verified 2026-10-01 ⚠ sources disagree — shown side by side context 65,536 JSON ↓
⚠ 字段 output 在数据源之间存在分歧——我们不取平均、不抹平,原值并列展示在下方。

Pricing matrix USD per 1M tokens

FieldConsensusEvidence
Input $2 ✓ 3 independent sources 3 sources
Output Unverified(未验证,不填 0) disputed ×10.00 3 sources
Cache read $0.2 ✓ 2 independent sources 2 sources
Cache write (5m) $0.375 single source 2 sources
Cache write (1h) Unverified(未验证,不填 0) not published
Reasoning tokens $12 single source 1 source
证据链:各源原值并列(audit trail,点击展开)
FieldSourceRaw value (USD/1M)IndependentObserved
input openrouter 2.0000 yes 2026-10-01 08:00
input litellm 2.0000 yes 2026-10-01 08:00
input litellm <span class="badge mute">mirror</span> 2.0000 no 2026-10-01 08:00
input modelsdev 2.0000 yes 2026-10-01 08:00
output openrouter 12.0000 yes 2026-10-01 08:00
output litellm 12.0000 yes 2026-10-01 08:00
output litellm <span class="badge mute">mirror</span> 12.0000 no 2026-10-01 08:00
output modelsdev 120.0000 yes 2026-10-01 08:00
cache_read openrouter 0.2000 yes 2026-10-01 08:00
cache_read litellm 0.2000 yes 2026-10-01 08:00
cache_read litellm <span class="badge mute">mirror</span> 0.2000 no 2026-10-01 08:00
cache_write openrouter 0.3750 yes 2026-10-01 08:00
cache_write litellm <span class="badge mute">mirror</span> 0.3750 no 2026-10-01 08:00
reasoning_out openrouter 12.0000 yes 2026-10-01 08:00

Long-context tier jumps ⚠

When prompt tokens cross a threshold, the entire request is re-priced at the higher tier — not just the excess. This is the #1 hidden cost on long-context workloads.

$0.44220K tokens200K跨过 200,000 tokens:$0.4000 / 请求(整请求重算)
Prompt ≥ tokensinputoutputcache read
0 (base)$2未验证$0.2
200,000未验证未验证未验证

Run this model through the real-bill calculator →

Sources

This is an estimate based on public sticker prices, not your invoice. Machine-readable: /data/v1/pricing/google-gemini-3-pro-image-preview.json