---
title: "AI Model Library"
description: "Explore AI models across providers. Discover model capabilities, context limits, supported modes, and pricing for chat, image generation, audio, embeddings, and more."
url: "https://www.getmaxim.ai/bifrost/model-library"
markdown: "https://www.getmaxim.ai/bifrost/model-library.md"
---

# AI Model Library

> Explore AI models across providers. Discover model capabilities, context limits, supported modes, and pricing for chat, image generation, audio, embeddings, and more.

## Important Links

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

## Library Overview

- **4,313 Models.**
- **99 Providers.**
- **13 Modes.**

## Browse by Provider

Explore all models from a specific provider.

- [OpenRouter (513 models)](https://www.getmaxim.ai/bifrost/model-library/provider/openrouter.md)
- [AWS Bedrock (441 models)](https://www.getmaxim.ai/bifrost/model-library/provider/bedrock.md)
- [Fireworks AI (313 models)](https://www.getmaxim.ai/bifrost/model-library/provider/fireworks_ai.md)
- [Azure (308 models)](https://www.getmaxim.ai/bifrost/model-library/provider/azure.md)
- [Hugging Face (212 models)](https://www.getmaxim.ai/bifrost/model-library/provider/huggingface.md)
- [Google Vertex AI (167 models)](https://www.getmaxim.ai/bifrost/model-library/provider/vertex_ai.md)
- [OpenAI (165 models)](https://www.getmaxim.ai/bifrost/model-library/provider/openai.md)
- [Deepinfra (135 models)](https://www.getmaxim.ai/bifrost/model-library/provider/deepinfra.md)
- [Novita (135 models)](https://www.getmaxim.ai/bifrost/model-library/provider/novita.md)
- [Databricks (113 models)](https://www.getmaxim.ai/bifrost/model-library/provider/databricks.md)
- [Vercel AI Gateway (101 models)](https://www.getmaxim.ai/bifrost/model-library/provider/vercel_ai_gateway.md)
- [Mistral AI (84 models)](https://www.getmaxim.ai/bifrost/model-library/provider/mistral.md)
- [Google Gemini (79 models)](https://www.getmaxim.ai/bifrost/model-library/provider/gemini.md)
- [Cloudflare (76 models)](https://www.getmaxim.ai/bifrost/model-library/provider/cloudflare.md)
- [Together AI (73 models)](https://www.getmaxim.ai/bifrost/model-library/provider/together_ai.md)
- [Replicate (71 models)](https://www.getmaxim.ai/bifrost/model-library/provider/replicate.md)
- [Perplexity (66 models)](https://www.getmaxim.ai/bifrost/model-library/provider/perplexity.md)
- [Opencode Zen (65 models)](https://www.getmaxim.ai/bifrost/model-library/provider/opencode-zen.md)
- [Bedrock Mantle (64 models)](https://www.getmaxim.ai/bifrost/model-library/provider/bedrock_mantle.md)
- [Nebius (57 models)](https://www.getmaxim.ai/bifrost/model-library/provider/nebius.md)
- [xAI (51 models)](https://www.getmaxim.ai/bifrost/model-library/provider/xai.md)
- [Oci (44 models)](https://www.getmaxim.ai/bifrost/model-library/provider/oci.md)
- [Workers AI (44 models)](https://www.getmaxim.ai/bifrost/model-library/provider/workers-ai.md)
- [Dashscope (41 models)](https://www.getmaxim.ai/bifrost/model-library/provider/dashscope.md)
- [Qwen AI Platform (41 models)](https://www.getmaxim.ai/bifrost/model-library/provider/qwen_ai_platform.md)
- [Qwencloud (41 models)](https://www.getmaxim.ai/bifrost/model-library/provider/qwencloud.md)
- [Snowflake (37 models)](https://www.getmaxim.ai/bifrost/model-library/provider/snowflake.md)
- [Deepgram (36 models)](https://www.getmaxim.ai/bifrost/model-library/provider/deepgram.md)
- [Wandb (35 models)](https://www.getmaxim.ai/bifrost/model-library/provider/wandb.md)
- [Github Copilot (32 models)](https://www.getmaxim.ai/bifrost/model-library/provider/github_copilot.md)
- [Watsonx (31 models)](https://www.getmaxim.ai/bifrost/model-library/provider/watsonx.md)
- [Ollama (29 models)](https://www.getmaxim.ai/bifrost/model-library/provider/ollama.md)
- [Anthropic (28 models)](https://www.getmaxim.ai/bifrost/model-library/provider/anthropic.md)
- [Voyage (27 models)](https://www.getmaxim.ai/bifrost/model-library/provider/voyage.md)
- [Moonshot (26 models)](https://www.getmaxim.ai/bifrost/model-library/provider/moonshot.md)
- [Stability (23 models)](https://www.getmaxim.ai/bifrost/model-library/provider/stability.md)
- [Cohere (22 models)](https://www.getmaxim.ai/bifrost/model-library/provider/cohere.md)
- [Groq (20 models)](https://www.getmaxim.ai/bifrost/model-library/provider/groq.md)
- [Lambda AI (20 models)](https://www.getmaxim.ai/bifrost/model-library/provider/lambda_ai.md)
- [Sambanova (19 models)](https://www.getmaxim.ai/bifrost/model-library/provider/sambanova.md)
- [Scaleway (19 models)](https://www.getmaxim.ai/bifrost/model-library/provider/scaleway.md)
- [Fal AI (17 models)](https://www.getmaxim.ai/bifrost/model-library/provider/fal_ai.md)
- [Gmi (17 models)](https://www.getmaxim.ai/bifrost/model-library/provider/gmi.md)
- [Hyperbolic (16 models)](https://www.getmaxim.ai/bifrost/model-library/provider/hyperbolic.md)
- [Llamagate (16 models)](https://www.getmaxim.ai/bifrost/model-library/provider/llamagate.md)
- [Zai (16 models)](https://www.getmaxim.ai/bifrost/model-library/provider/zai.md)
- [Ovhcloud (15 models)](https://www.getmaxim.ai/bifrost/model-library/provider/ovhcloud.md)
- [Nscale (14 models)](https://www.getmaxim.ai/bifrost/model-library/provider/nscale.md)
- [Opencode Go (14 models)](https://www.getmaxim.ai/bifrost/model-library/provider/opencode-go.md)
- [Aiml (13 models)](https://www.getmaxim.ai/bifrost/model-library/provider/aiml.md)
- [Gradient AI (13 models)](https://www.getmaxim.ai/bifrost/model-library/provider/gradient_ai.md)
- [Ai21 (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/ai21.md)
- [Anyscale (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/anyscale.md)
- [Baseten (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/baseten.md)
- [Libertai (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/libertai.md)
- [Runwayml (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/runwayml.md)
- [Volcengine (12 models)](https://www.getmaxim.ai/bifrost/model-library/provider/volcengine.md)
- [Deepseek (11 models)](https://www.getmaxim.ai/bifrost/model-library/provider/deepseek.md)
- [Chatgpt (10 models)](https://www.getmaxim.ai/bifrost/model-library/provider/chatgpt.md)
- [Tensormesh (10 models)](https://www.getmaxim.ai/bifrost/model-library/provider/tensormesh.md)
- [Cerebras (9 models)](https://www.getmaxim.ai/bifrost/model-library/provider/cerebras.md)
- [Publicai (9 models)](https://www.getmaxim.ai/bifrost/model-library/provider/publicai.md)
- [Wafer (9 models)](https://www.getmaxim.ai/bifrost/model-library/provider/wafer.md)
- [Black Forest Labs (8 models)](https://www.getmaxim.ai/bifrost/model-library/provider/black_forest_labs.md)
- [Crusoe (7 models)](https://www.getmaxim.ai/bifrost/model-library/provider/crusoe.md)
- [Gigachat (7 models)](https://www.getmaxim.ai/bifrost/model-library/provider/gigachat.md)
- [Minimax (6 models)](https://www.getmaxim.ai/bifrost/model-library/provider/minimax.md)
- [Palm (6 models)](https://www.getmaxim.ai/bifrost/model-library/provider/palm.md)
- [Pinstripes (6 models)](https://www.getmaxim.ai/bifrost/model-library/provider/pinstripes.md)
- [Sagemaker (6 models)](https://www.getmaxim.ai/bifrost/model-library/provider/sagemaker.md)
- [Text Completion Openai (6 models)](https://www.getmaxim.ai/bifrost/model-library/provider/text-completion-openai.md)
- [Fireworks AI Embedding Models (5 models)](https://www.getmaxim.ai/bifrost/model-library/provider/fireworks_ai-embedding-models.md)
- [Lemonade (5 models)](https://www.getmaxim.ai/bifrost/model-library/provider/lemonade.md)
- [Meta (5 models)](https://www.getmaxim.ai/bifrost/model-library/provider/meta.md)
- [Amazon Nova (4 models)](https://www.getmaxim.ai/bifrost/model-library/provider/amazon_nova.md)
- [Friendliai (4 models)](https://www.getmaxim.ai/bifrost/model-library/provider/friendliai.md)
- [Heroku (4 models)](https://www.getmaxim.ai/bifrost/model-library/provider/heroku.md)
- [Meta Llama (4 models)](https://www.getmaxim.ai/bifrost/model-library/provider/meta_llama.md)
- [Azure Text (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/azure_text.md)
- [Cognition (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/cognition.md)
- [ElevenLabs (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/elevenlabs.md)
- [Nvidia Nim (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/nvidia_nim.md)
- [Runware (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/runware.md)
- [Tencent (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/tencent.md)
- [V0 (3 models)](https://www.getmaxim.ai/bifrost/model-library/provider/v0.md)
- [Assemblyai (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/assemblyai.md)
- [Codestral (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/codestral.md)
- [Darkbloom (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/darkbloom.md)
- [Featherless AI (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/featherless_ai.md)
- [Morph (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/morph.md)
- [Nlp Cloud (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/nlp_cloud.md)
- [Recraft (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/recraft.md)
- [Scx AI (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/scx-ai.md)
- [Soniox (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/soniox.md)
- [Text Completion Codestral (2 models)](https://www.getmaxim.ai/bifrost/model-library/provider/text-completion-codestral.md)
- [Inception (1 models)](https://www.getmaxim.ai/bifrost/model-library/provider/inception.md)
- [Jina AI (1 models)](https://www.getmaxim.ai/bifrost/model-library/provider/jina_ai.md)
- [Sarvam (1 models)](https://www.getmaxim.ai/bifrost/model-library/provider/sarvam.md)
- [Text Completion Inception (1 models)](https://www.getmaxim.ai/bifrost/model-library/provider/text-completion-inception.md)

## All Models

4,313 models across 99 providers. Showing the first 100; open a provider page for the full list.

| Model | Provider | Mode | Max Input Tokens | Input $/1M |
| --- | --- | --- | --- | --- |
| ai21.j2-mid-v1 | AWS Bedrock | Chat | 8,191 | $12.50 |
| ai21.j2-ultra-v1 | AWS Bedrock | Chat | 8,191 | $18.80 |
| ai21.jamba-1-5-large-v1:0 | AWS Bedrock | Chat | 256,000 | $2.00 |
| ai21.jamba-1-5-mini-v1:0 | AWS Bedrock | Chat | 256,000 | $0.20 |
| ai21.jamba-instruct-v1:0 | AWS Bedrock | Chat | 70,000 | $0.50 |
| dall-e-2 | Aiml | Image Generation | - | - |
| dall-e-3 | Aiml | Image Generation | - | - |
| flux-pro | Aiml | Image Generation | - | - |
| v1.1 | Aiml | Image Generation | - | - |
| v1.1-ultra | Aiml | Image Generation | - | - |
| flux-realism | Aiml | Image Generation | - | - |
| dev | Aiml | Image Generation | - | - |
| text-to-image | Aiml | Image Generation | - | - |
| text-to-image | Aiml | Image Generation | - | - |
| schnell | Aiml | Image Generation | - | - |
| imagen-4.0-ultra-generate-001 | Aiml | Image Generation | - | - |
| nano-banana-pro | Aiml | Image Generation | - | - |
| gpt-image-2 | Aiml | Image Generation | - | - |
| us.amazon.nova-canvas-v1:0 | AWS Bedrock | Image Generation | 2,600 | - |
| us.writer.palmyra-x4-v1:0 | AWS Bedrock | Chat | 128,000 | $2.50 |
| us.writer.palmyra-x5-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.60 |
| writer.palmyra-x4-v1:0 | AWS Bedrock | Chat | 128,000 | $2.50 |
| writer.palmyra-x5-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.60 |
| amazon.nova-lite-v1:0 | AWS Bedrock | Chat | 300,000 | $0.06 |
| amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.30 |
| amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | 1,000,000 | $2.19 |
| apac.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.33 |
| apac.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | 1,000,000 | $2.19 |
| eu.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.33 |
| eu.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | 1,000,000 | $2.19 |
| us.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | 1,000,000 | $0.33 |
| us.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | 1,000,000 | $2.19 |
| amazon.nova-2-multimodal-embeddings-v1:0 | AWS Bedrock | Embedding | 8,172 | $0.14 |
| amazon.nova-micro-v1:0 | AWS Bedrock | Chat | 128,000 | $0.04 |
| amazon.nova-pro-v1:0 | AWS Bedrock | Chat | 300,000 | $0.80 |
| amazon.nova-sonic-v1:0 | AWS Bedrock | Realtime | - | $0.06 |
| amazon.nova-2-sonic-v1:0 | AWS Bedrock | Realtime | - | $0.33 |
| amazon.rerank-v1:0 | AWS Bedrock | Rerank | 32,000 | $0.0000 |
| amazon.titan-embed-image-v1 | AWS Bedrock | Embedding | 128 | $0.80 |
| amazon.titan-embed-text-v1 | AWS Bedrock | Embedding | 8,192 | $0.10 |
| amazon.titan-embed-g1-text-02 | AWS Bedrock | Embedding | 8,192 | $0.10 |
| amazon.titan-embed-text-v2:0 | AWS Bedrock | Embedding | 8,192 | $0.02 |
| amazon.titan-image-generator-v1 | AWS Bedrock | Image Generation | - | - |
| amazon.titan-image-generator-v2 | AWS Bedrock | Image Generation | - | - |
| amazon.titan-image-generator-v2:0 | AWS Bedrock | Image Generation | - | - |
| twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | 77 | $70.00 |
| us.twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | 77 | $70.00 |
| eu.twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | 77 | $70.00 |
| twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | - |
| us.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | - |
| eu.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | - |
| amazon.titan-text-express-v1 | AWS Bedrock | Chat | 42,000 | $1.30 |
| amazon.titan-text-lite-v1 | AWS Bedrock | Chat | 42,000 | $0.30 |
| amazon.titan-text-premier-v1:0 | AWS Bedrock | Chat | 42,000 | $0.50 |
| anthropic.claude-3-5-haiku-20241022-v1:0 | AWS Bedrock | Chat | 200,000 | $0.80 |
| anthropic.claude-haiku-4-5-20251001-v1:0 | AWS Bedrock | Chat | 200,000 | $1.00 |
| anthropic.claude-haiku-4-5@20251001 | AWS Bedrock | Chat | 200,000 | $1.00 |
| anthropic.claude-3-5-sonnet-20240620-v1:0 | AWS Bedrock | Chat | 1,000,000 | $3.00 |
| anthropic.claude-3-5-sonnet-20241022-v2:0 | AWS Bedrock | Chat | 1,000,000 | $3.00 |
| anthropic.claude-3-7-sonnet-20240620-v1:0 | AWS Bedrock | Chat | 200,000 | $3.60 |
| anthropic.claude-3-7-sonnet-20250219-v1:0 | AWS Bedrock | Chat | 200,000 | $3.00 |
| anthropic.claude-3-haiku-20240307-v1:0 | AWS Bedrock | Chat | 200,000 | $0.25 |
| anthropic.claude-3-opus-20240229-v1:0 | AWS Bedrock | Chat | 200,000 | $15.00 |
| anthropic.claude-3-sonnet-20240229-v1:0 | AWS Bedrock | Chat | 200,000 | $3.00 |
| anthropic.claude-instant-v1 | AWS Bedrock | Chat | 100,000 | $0.80 |
| anthropic.claude-opus-4-1-20250805-v1:0 | AWS Bedrock | Chat | 200,000 | $15.00 |
| anthropic.claude-opus-4-20250514-v1:0 | AWS Bedrock | Chat | 200,000 | $15.00 |
| anthropic.claude-opus-4-5-20251101-v1:0 | AWS Bedrock | Chat | 200,000 | $5.00 |
| anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| global.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| us.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| eu.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| au.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| anthropic.claude-mythos-preview | AWS Bedrock | Chat | 1,000,000 | $0.0000 |
| global.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| us.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| eu.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| au.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| anthropic.claude-fable-5 | AWS Bedrock | Chat | 1,000,000 | $10.00 |
| anthropic.claude-fable-5-1 | AWS Bedrock | Chat | 1,000,000 | $10.00 |
| global.anthropic.claude-fable-5 | AWS Bedrock | Chat | 1,000,000 | $10.00 |
| global.anthropic.claude-fable-5-1 | AWS Bedrock | Chat | 1,000,000 | $10.00 |
| us.anthropic.claude-fable-5 | AWS Bedrock | Chat | 1,000,000 | $11.00 |
| us.anthropic.claude-fable-5-1 | AWS Bedrock | Chat | 1,000,000 | $10.00 |
| eu.anthropic.claude-fable-5 | AWS Bedrock | Chat | 1,000,000 | $11.00 |
| anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| global.anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| us.anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| eu.anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| au.anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| jp.anthropic.claude-opus-5 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| global.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.00 |
| us.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| eu.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| au.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| jp.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| jp.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | 1,000,000 | $5.50 |
| anthropic.claude-sonnet-5 | AWS Bedrock | Chat | 1,000,000 | $2.00 |

## FAQ

### What is the AI model library?

The model library is a browsable catalog of AI models across every major provider, showing capabilities, context limits, supported modes, and pricing in one place. Use it to discover and compare models for chat, image generation, audio, embeddings, and more.

### How do I compare two models?

Open any model to see its full specification, then add a second model to view a side-by-side comparison of context windows, capabilities, and pricing. This makes it easy to pick the right model for a given workload.

### What details does each model page show?

Each model page lists the mode, maximum input and output tokens, supported capabilities (function calling, vision, reasoning, audio, and more), and input/output pricing per 1M tokens, alongside comparable alternatives from other providers.

### How current is the model data?

Model specifications and pricing are regenerated from the upstream datasheet on every build, so they reflect the latest published capabilities and rates for hundreds of models.

### How does Bifrost help me use multiple models?

Bifrost AI Gateway gives you a single, unified API across every provider in this library, with automatic failover, load balancing, and cost-based routing so you can switch or combine models without rewriting your application.

## Related Resources

- [Model library](https://www.getmaxim.ai/bifrost/model-library.md)
- [LLM cost calculator](https://www.getmaxim.ai/bifrost/llm-cost-calculator.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/pricing)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo)
- [Resources: Bifrost resources](https://www.getmaxim.ai/bifrost/resources.md)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/model-library](https://www.getmaxim.ai/bifrost/model-library) for AI/LLM consumption.*