impulse

Text Embedding 3 Small

Frontier labEmbedding
API id text-embedding-3-small
Input / 1M
$0.02
at OpenAI
Output / 1M
$0.00
at OpenAI
Context window
8K
tokens
Max output
-
tokens per reply
Hosts
4
8 listings
Released
-
date not published

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.02$0.00
Batch
50% off
$0.01$0.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$6.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$9.60
  • Coding agent1,000 requests a day, 40K in / 2K out$24.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$24.00
Use your own numbers

Where to run it

4 hosts serve Text Embedding 3 Small. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
text-embedding-3-small
$0.02 / $0.00
text-embedding-3-small
$0.02 / $0.00
text-embedding-3-small
$0.022 / $0.00
+10% vs headline
Retires 9 Feb 2028
text-embedding-3-small
$0.03 / $0.00
+50% vs headline
GitHub CopilotSubscription
text-embedding-3-small
In the subscription
Show 3 more listings: regions, snapshots and variants
Azure OpenAI
eu
text-embedding-3-small
$0.022 / -
+10% vs headline
Retires 9 Feb 2028
us
text-embedding-3-small
$0.022 / -
+10% vs headline
Retires 9 Feb 2028
us-gov
text-embedding-3-small
$0.025 / $0.00
+25% vs headline

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
Text
Produces
Embeddings

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 OpenAI.

Smaller OpenAI models

No cheaper OpenAI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3 Embedding 8B
    Alibaba Qwen · on Nebius AI Studio
    $0.01 / $0.00
    Has every key capability
    50% less
  • Bge Multilingual Gemma2
    Independent · on Nebius AI Studio
    $0.01 / $0.00
    Has every key capability
    50% less
  • E5 Mistral 7B Instruct
    Independent · on Nebius AI Studio
    $0.01 / $0.00
    Has every key capability
    50% less
  • Nomic Embed Text
    Independent · on Fireworks Ai Embedding Models
    $0.008 / $0.00
    Has every key capability
    60% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="text-embedding-3-small", input="Hello")
print(response.output_text)

Quick answers

How much does Text Embedding 3 Small cost?

On OpenAI, Text Embedding 3 Small costs $0.02 per million input tokens.

Which APIs offer Text Embedding 3 Small?

Text Embedding 3 Small runs on 4 APIs: OpenAI, Vercel AI Gateway, Azure OpenAI and Hostinger Router.

What is Text Embedding 3 Small's context window?

8K tokens.

Is Text Embedding 3 Small being retired?

Azure OpenAI (except US government regions) retires it on 9 Feb 2028. 4 hosts keep serving it.

What are cheaper alternatives to Text Embedding 3 Small?

Models that cost less and keep most of what it can do: Qwen3 Embedding 8B on Nebius AI Studio (50% less).

What is Text Embedding 3 Small's API model id?

Use text-embedding-3-small with OpenAI.

Sources

Raw catalog entry for text-embedding-3-small on OpenAI
{
  "input_cost_per_token": 2e-8,
  "input_cost_per_token_batches": 1e-8,
  "litellm_provider": "openai",
  "max_input_tokens": 8191,
  "mode": "embedding",
  "output_cost_per_token": 0,
  "output_cost_per_token_batches": 0,
  "output_vector_size": 1536,
  "source": "https://developers.openai.com/api/docs/pricing"
}