Kyma APIKyma API
Alibaba

Alibaba

GTE Base

768-dimension general text embeddings from Alibaba's Tongyi lab, trained on a broader mixture than BGE and often a point or two ahead of it on out-of-domain retrieval. Same size and same price as bge-base-en, so the choice is which one your corpus likes.

Modalities

Text → Text

Usage

How much this model is actually called here.

Rank

#78

of 98 active models

Tokens served

50.0K

all-time

Platform share

0.0%

of all tokens

Tokens · last 15 daysSep 3 → Sep 17

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.00675 /1M input$0.00 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.00/mo
Production1,000 req/day · 2K in / 500 out
~$0.40/mo
Scale20,000 req/day · 2K in / 500 out
~$8.10/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$0.4050

$0.0135 / day on GTE Base

Same workload on:

Qwen 3.8 27B$94.77+23300%
Qwen 3.7 Flash$6.23+1439%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

SpecGTE BaseQwen 3.8 27BQwen 3.7 Flash
Input /1M$0.00675$0.567$0.0498
Output /1M$0.00$4.05$0.2164
Context1K1M1M
ToolsNoYesYes
ReasoningNoYesYes
Throughput449 tok/s46 tok/s118 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers GTE Base. No card required.

    Get API key →
  2. 2

    Make your first request

    Submit a generation job and poll until it succeeds.

    curl https://kymaapi.com/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gte-base",
    "input": ["first document", "second document"]
  }'

FAQ

Common questions about this model.

What is the context window of GTE Base?

GTE Base has a 1K-token context window — roughly 1 pages of text in a single request.

How much does the GTE Base API cost?

$0.00675 per 1M input tokens and $0.00 per 1M output tokens. No subscription; you pay only for what you use.

Does GTE Base support function calling?

No — GTE Base does not support tool calling. For agent workloads, choose a tools-enabled model from the catalog.

How do I use GTE Base?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to gte-base. Signing up is free and includes $0.50 of credit on the free tier, which covers this model — no card required.

Start with $0.50 free credit on the free tier — no card required.Create account →

More models by Alibaba

See all 14 →
ModelContextInputOutput
AlibabaQwen 3.8 Flash1M$0.203$0.635
AlibabaQwen 3.8 27B1M$0.567$4.05
AlibabaQwen 3.8 Max1M$2.2275$6.684
AlibabaQwen 3.7 Flash1M$0.0498$0.2164
AlibabaQwen 3.7 Plus1M$0.4431$1.773
AlibabaQwen 3.7 Max1M$2.304$6.909
AlibabaQwen 3.6 Plus1M$0.4911$2.947
AlibabaQwen 3 Coder131K$0.334$1.519