Интерфейс моделей ИИ

Gemini Embedding 001

google/gemini-embedding-001

От Google · семейство: gemini · выпуск 2025-05-20 · дата знаний: 2025-05

$0.150
Вход / 1M токенов
Unknown
Выход / 1M токенов
2K
Окно контекста
3K
Макс. вывод

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Возможности

✗ Tool calling✗ Рассуждение? Структурированный вывод✗ Вложения✗ Открытые веса✗ Управление температурой
Модальности: вход text · выход text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding3
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability3/10
Agents3
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit0/15
  • Provider availability3/10
JSON / structured output20
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control0/10
  • Price-friendly for high-volume20/20
Cost efficiency82
  • Headline price (log-scaled)82/95
  • Has prompt-cache pricing0/5
Long context0
  • Context ≥ 100K0/100
Production-readiness58
  • Number of independent providers15/40
  • Has published per-token price20/20
  • Context window ≥ 8K0/15
  • No data inconsistencies across providers8/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$0.75
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$1.50
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$0.30
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$1.20
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$1.80
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Детализация цен

Рекомендованная цена от google · gemini-embedding-001

$0.150
Вход
Unknown
Выход

Доступна у 3 провайдеров

ПровайдерID модели провайдераВход / 1MВыход / 1MКонтекстВыпуск
Google
google
gemini-embedding-001$0.150Unknown2K2025-05-20
Vertex
google-vertex
gemini-embedding-001$0.150Unknown2K2025-05-20
Vercel AI Gateway
vercel
google/gemini-embedding-001$0.150Unknown8K2025-05-20

Расхождения данных между провайдерами

  • context_window varies: 2048, 8192

Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.

Frequently asked questions

How much does Gemini Embedding 001 cost?

Gemini Embedding 001 costs $0.150 per 1M input tokens and Unknown per 1M output tokens, sourced from google. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of Gemini Embedding 001?

Gemini Embedding 001 has a context window of 2K tokens, with a max output of 3K tokens per reply. This is the total combined size of prompt + completion.

Does Gemini Embedding 001 support tool calling?

No. Gemini Embedding 001 does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does Gemini Embedding 001 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for Gemini Embedding 001 in our data source. Verify with Google's official documentation before relying on it in production.

Can Gemini Embedding 001 accept image input?

No. Gemini Embedding 001 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is Gemini Embedding 001 open-weight?

No. Gemini Embedding 001 is a proprietary model — only Google (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to Gemini Embedding 001?

If Gemini Embedding 001 doesn't fit, consider Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3 Flash Preview. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More Google models

See also

Последнее обновление:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.