IMAGE MODEL Google/DeepMind Last updated:

Gemini 1.5 Series

Gemini 1.5 is an API model from Google. It’s positioned for hard reasoning and planning—work that benefits from iteration, not just one-shot answers.

Intelligence
Top 10%
Speed
Slow
47 tok/s output
Cost
Moderate
$1.40 in / $4.40 out
Context
2M
Up to 2,000,000 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out

Core Capabilities

Long Documents
Handles entire codebases, books, and multi-doc RAG.
Reasoning
Solves complex math, logic, and planning tasks.

Context Window

2M tokens
≈ entire codebase
4k Chat 聊天
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
2M

Availability

API
Available
Product / App
Available
Open Source
Not released
Enterprise
Contact sales

Pricing Model

Pay per token
Input and output billed separately.
Pay-per-token

Capability / Performance

Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).

Lower 20% Upper 80% This model
Quality
AA Intelligence Index · scaled to 10
1.7
5.6
7.3
Speed
Output throughput · log-scaled
8.4
Cost efficiency
Input price ($/M tokens) · cheaper scores higher
6.2
10.0
7.2
Consistency
No data reported · placeholder
5.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.

What it feels like

  • First model where 1M-token context was a real product feature, not a benchmark headline
  • 99% needle-in-haystack accuracy at 1M tokens; 99.2% even at 10M in research configurations
  • Multi-needle recall drops to ~60% — single fact retrieval is solid, multi-fact is harder

Best use cases

  • Whole-codebase analysis (30K+ lines) without tedious chunking pipelines
  • Document QA over 1,500-page PDFs / batches of 100 emails
  • Hour-long video summarisation and audio transcription QA

Tools to try

Not ideal for

  • Tasks requiring multi-fact retrieval across long contexts (recall drops sharply)
  • Pure short-context chat — Flash variants are cheaper and faster