impulse

Bge M3

Embedding
API id bge-m3
Input / 1M
$0.01
at Novita AI
Output / 1M
$0.01
at Novita AI
Context window
8K
tokens
Max output
96K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.01$0.01

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$3.75
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$5.16
  • Coding agent1,000 requests a day, 40K in / 2K out$12.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$26.40
Use your own numbers

Where to run it

2 hosts serve Bge M3. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
bge-m3
$0.01 / $0.00
Novita AIInference
bge-m3
$0.01 / $0.01

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 Novita AI.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Nomic Embed Text
    Independent · on Fireworks Ai Embedding Models
    $0.008 / $0.00
    Has every key capability
    20% less

Call it

Using Novita AI's API.

Python
from litellm import completion

response = completion(
    model="novita/bge-m3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Bge M3 cost?

On Novita AI, Bge M3 costs $0.01 per million input tokens and $0.01 per million output tokens.

Which APIs offer Bge M3?

Bge M3 runs on 2 APIs: LibertAI and Novita AI.

What is Bge M3's context window?

8K tokens, with up to 96K tokens in one reply.

Is Bge M3 being retired?

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

What are cheaper alternatives to Bge M3?

Models that cost less and keep most of what it can do: Nomic Embed Text on Fireworks Ai Embedding Models (20% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Bge M3's API model id?

Use bge-m3 with Novita AI.

Sources

Raw catalog entry for bge-m3 on Novita AI
{
  "litellm_provider": "novita",
  "mode": "embedding",
  "input_cost_per_token": 1e-8,
  "output_cost_per_token": 1e-8,
  "max_input_tokens": 8192,
  "max_output_tokens": 96000
}