---
title: "gte-base - Model Details & Comparison"
description: "gte-base from Fireworks AI Embedding Models: capabilities, context limits, pricing, and side-by-side comparisons with alternative models."
url: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/fireworks_ai-embedding-models/gte-base"
markdown: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/fireworks_ai-embedding-models/gte-base.md"
---

# gte-base - Model Details & Comparison

> gte-base from Fireworks AI Embedding Models: capabilities, context limits, pricing, and side-by-side comparisons with alternative models.

## Important Links

- [View MCP Gateway](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources/mcp-gateway.md)
- [Features](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/#features)
- [Enterprise](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/enterprise)
- [Pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/book-a-demo)

## About gte-base

gte-base is an embedding model from Fireworks Ai-embedding-models, one of 5 embedding models they offer. It is priced at $0.0080 per 1M input tokens and $0.0080 per 1M output tokens, ranking 14 out of 145 embedding models by cost and cheaper than 88% of models in this category. It accepts up to 1K input tokens.

## Specifications

- **Fireworks AI Embedding Models Provider.**
- **Embedding Mode.**
- **512 Max Input Tokens.**
- **512 Max Tokens.**
- **$0.0080 / 1M tokens Input Price.**
- **$0.0080 / 1M tokens Output Price.**

## gte-base Pricing Overview

At $0.0080 per 1M input tokens and $0.0080 per 1M output tokens, gte-base ranks 14 out of 145 embedding models by input cost. It is more affordable compared to the median of $0.10 for embedding models, and is cheaper than 88% of models in this category.

## Models to Compare

Alternatives to gte-base with comparable capabilities.

| Model | Provider | Input $/1M | Output $/1M |
| --- | --- | --- | --- |
| bge-en-icl | Nebius | $0.01 | $0.0000 |
| bge-multilingual-gemma2 | Nebius | $0.01 | $0.0000 |
| e5-mistral-7b-instruct | Nebius | $0.01 | $0.0000 |
| together-ai-embedding-up-to-150m | Together AI | $0.0080 | $0.0000 |
| bge-base-en-v1.5 | Together AI | $0.0080 | $0.0000 |

- [Compare bge-en-icl](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/nebius/bge-en-icl.md)
- [Compare bge-multilingual-gemma2](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/nebius/bge-multilingual-gemma2.md)
- [Compare e5-mistral-7b-instruct](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/nebius/e5-mistral-7b-instruct.md)
- [Compare together-ai-embedding-up-to-150m](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/together_ai/together-ai-embedding-up-to-150m.md)
- [Compare bge-base-en-v1.5](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/together_ai/bge-base-en-v1.5.md)

## Related Resources

- [Calculate gte-base costs](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/fireworks_ai-embedding-models/model/gte-base.md)
- [All Fireworks Ai-embedding-models pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/fireworks_ai-embedding-models.md)

## FAQ

### Is gte-base cheaper than bge-en-icl?

Yes. gte-base costs $0.0080 per 1M input tokens compared to bge-en-icl's $0.01 per 1M input tokens, making it 25% more affordable. Both are embedding models.

### How does gte-base pricing compare to the average embedding model?

gte-base input pricing is $0.0080 per 1M tokens, which is 92% below the median of $0.10 for embedding models. It ranks 14 out of 145 embedding models by input cost, making it cheaper than 88% of models in this category. For output, it costs $0.0080 per 1M tokens compared to the median of $0.0090.

### What makes gte-base different from other Fireworks Ai-embedding-models models?

Among Fireworks Ai-embedding-models's 5 embedding models, gte-base ranks 3 by input cost.

### What are the best alternatives to gte-base?

The most comparable embedding models to gte-base are: bge-en-icl from Nebius ($0.01/1M input tokens); bge-multilingual-gemma2 from Nebius ($0.01/1M input tokens); e5-mistral-7b-instruct from Nebius ($0.01/1M input tokens); together-ai-embedding-up-to-150m from Together AI ($0.0080/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

### How do I calculate gte-base costs?

gte-base is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.0080 and generating 1M output tokens costs $0.0080.

## Related Resources

- [Fireworks AI Embedding Models models](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/provider/fireworks_ai-embedding-models.md)
- [Model library](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library.md)
- [LLM cost calculator](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/pricing.md)
- [Enterprise: Bifrost enterprise](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/enterprise)
- [Book a Demo: Bifrost demo](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/book-a-demo)
- [Resources: Bifrost resources](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources.md)

---

*This is a markdown version of [https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/fireworks_ai-embedding-models/gte-base](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/fireworks_ai-embedding-models/gte-base) for AI/LLM consumption.*