impulse

Gemini Embedding 2

Frontier labEmbedding
API id gemini-embedding-2
Input / 1M
$0.20
at Google AI Studio
Output / 1M
$0.00
at Google AI Studio
Context window
8K
tokens
Max output
-
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

List prices at Google AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$0.00
Batch
50% off
$0.10

What it costs a month

At Google AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$60.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$96.00
  • Coding agent1,000 requests a day, 40K in / 2K out$240
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$240
Use your own numbers

Where to run it

2 hosts serve Gemini Embedding 2. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gemini-embedding-2
$0.20 / $0.00
gemini-embedding-2
$0.20 / $0.00
Show 1 more listings: regions, snapshots and variants
Vertex AI
Alias
gemini-embedding-2
$0.20 / $0.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesAudio
Produces
Embeddings
Features
Audio input

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Google AI Studio.

Smaller Google models

No cheaper Google model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Google AI Studio's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-embedding-2", contents="Hello")
print(response.text)

Quick answers

How much does Gemini Embedding 2 cost?

On Google AI Studio, Gemini Embedding 2 costs $0.20 per million input tokens.

Which APIs offer Gemini Embedding 2?

Gemini Embedding 2 runs on 2 APIs: Google AI Studio and Vertex AI.

What is Gemini Embedding 2's context window?

8K tokens.

Is Gemini Embedding 2 being retired?

No retirement date is scheduled for it on any API we track.

What is Gemini Embedding 2's API model id?

Use gemini-embedding-2 with Google AI Studio.

Sources

Raw catalog entry for gemini-embedding-2 on Google AI Studio
{
  "input_cost_per_audio_token": 0.0000065,
  "input_cost_per_audio_token_batches": 0.00000325,
  "input_cost_per_image_token": 4.5e-7,
  "input_cost_per_image_token_batches": 2.25e-7,
  "input_cost_per_token": 2e-7,
  "input_cost_per_token_batches": 1e-7,
  "input_cost_per_video_token": 0.000012,
  "input_cost_per_video_token_batches": 0.000006,
  "litellm_provider": "gemini",
  "max_input_tokens": 8192,
  "mode": "embedding",
  "output_cost_per_token": 0,
  "output_vector_size": 3072,
  "rpm": 10000,
  "source": "https://ai.google.dev/gemini-api/docs/pricing",
  "supports_audio_input": true,
  "supports_embedding_image_input": true,
  "supports_multimodal": true,
  "supports_vision": true,
  "tpm": 10000000
}