---
title: "LLM Cost Calculator"
description: "Calculate and compare LLM API costs across hundreds of AI models and dozens of providers. See input and output pricing per 1M tokens for OpenAI, Anthropic, Google, and more."
url: "https://www.getmaxim.ai/bifrost/llm-cost-calculator"
markdown: "https://www.getmaxim.ai/bifrost/llm-cost-calculator.md"
---

# LLM Cost Calculator

> Calculate and compare LLM API costs across hundreds of AI models and dozens of providers. See input and output pricing per 1M tokens for OpenAI, Anthropic, Google, 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/bifrost/enterprise)
- [Pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/bifrost/book-a-demo)

## Calculator Overview

- **3,241 Models.**
- **72 Providers.**
- **12 Modes.**

## Browse by Provider

Jump to every model and price for a specific provider.

- [OpenRouter (467 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/openrouter.md)
- [AWS Bedrock (360 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/bedrock.md)
- [Fireworks AI (292 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/fireworks_ai.md)
- [Azure (281 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure.md)
- [Hugging Face (203 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/huggingface.md)
- [OpenAI (150 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/openai.md)
- [Vertex AI (133 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/vertex_ai.md)
- [Vercel Ai Gateway (101 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/vercel_ai_gateway.md)
- [Novita (85 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/novita.md)
- [DeepInfra (68 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/deepinfra.md)
- [Cloudflare (61 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cloudflare.md)
- [Databricks (61 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/databricks.md)
- [Together AI (60 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/together_ai.md)
- [Mistral (57 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/mistral.md)
- [Google Gemini (52 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/gemini.md)
- [Opencode-zen (49 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/opencode-zen.md)
- [Oci (44 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/oci.md)
- [xAI (44 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/xai.md)
- [Replicate (40 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/replicate.md)
- [Workers-ai (35 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/workers-ai.md)
- [Nebius (30 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/nebius.md)
- [Bedrock Mantle (29 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/bedrock_mantle.md)
- [IBM watsonx (28 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx.md)
- [Anthropic (26 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/anthropic.md)
- [Moonshot (26 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/moonshot.md)
- [Perplexity (26 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/perplexity.md)
- [Dashscope (25 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/dashscope.md)
- [Voyage (25 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/voyage.md)
- [Snowflake (21 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/snowflake.md)
- [Lambda Ai (20 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/lambda_ai.md)
- [SambaNova (19 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/sambanova.md)
- [Cohere (17 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cohere.md)
- [Gmi (17 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/gmi.md)
- [Hyperbolic (16 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/hyperbolic.md)
- [Llamagate (16 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/llamagate.md)
- [Scaleway (16 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/scaleway.md)
- [Wandb (16 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/wandb.md)
- [Ovhcloud (15 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/ovhcloud.md)
- [Groq (14 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/groq.md)
- [Nscale (14 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/nscale.md)
- [Opencode-go (14 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/opencode-go.md)
- [AI21 (12 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/ai21.md)
- [Anyscale (12 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/anyscale.md)
- [Libertai (12 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/libertai.md)
- [Baseten (11 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/baseten.md)
- [Zai (11 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/zai.md)
- [Gradient Ai (10 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/gradient_ai.md)
- [Tensormesh (10 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/tensormesh.md)
- [Cerebras (8 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cerebras.md)
- [DeepSeek (8 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/deepseek.md)
- [Wafer (8 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/wafer.md)
- [Crusoe (7 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/crusoe.md)
- [Minimax (6 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/minimax.md)
- [PaLM (6 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/palm.md)
- [Pinstripes (6 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/pinstripes.md)
- [Text-completion-openai (6 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/text-completion-openai.md)
- [Amazon Nova (4 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/amazon_nova.md)
- [Azure Text (3 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure_text.md)
- [Cognition (3 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cognition.md)
- [Meta (3 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/meta.md)
- [V0 (3 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/v0.md)
- [Darkbloom (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/darkbloom.md)
- [Fireworks Ai-embedding-models (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/fireworks_ai-embedding-models.md)
- [FriendliAI (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/friendliai.md)
- [Github Copilot (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/github_copilot.md)
- [Morph (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/morph.md)
- [NLP Cloud (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/nlp_cloud.md)
- [Scx-ai (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/scx-ai.md)
- [Tencent (2 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/tencent.md)
- [Inception (1 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/inception.md)
- [Jina AI (1 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/jina_ai.md)
- [Text-completion-inception (1 models)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/text-completion-inception.md)

## All Models

Pricing for 3,241 models across 72 providers. Showing the first 100; open a provider page for the full list.

| Model | Provider | Mode | Input $/1M | Output $/1M |
| --- | --- | --- | --- | --- |
| ai21.j2-mid-v1 | AWS Bedrock | Chat | $12.50 | $12.50 |
| ai21.j2-ultra-v1 | AWS Bedrock | Chat | $18.80 | $18.80 |
| ai21.jamba-1-5-large-v1:0 | AWS Bedrock | Chat | $2.00 | $8.00 |
| ai21.jamba-1-5-mini-v1:0 | AWS Bedrock | Chat | $0.20 | $0.40 |
| ai21.jamba-instruct-v1:0 | AWS Bedrock | Chat | $0.50 | $0.70 |
| us.writer.palmyra-x4-v1:0 | AWS Bedrock | Chat | $2.50 | $10.00 |
| us.writer.palmyra-x5-v1:0 | AWS Bedrock | Chat | $0.60 | $6.00 |
| writer.palmyra-x4-v1:0 | AWS Bedrock | Chat | $2.50 | $10.00 |
| writer.palmyra-x5-v1:0 | AWS Bedrock | Chat | $0.60 | $6.00 |
| amazon.nova-lite-v1:0 | AWS Bedrock | Chat | $0.06 | $0.24 |
| amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | $0.30 | $2.50 |
| amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | $2.19 | $17.50 |
| apac.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | $0.33 | $2.75 |
| apac.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | $2.19 | $17.50 |
| eu.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | $0.33 | $2.75 |
| eu.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | $2.19 | $17.50 |
| us.amazon.nova-2-lite-v1:0 | AWS Bedrock | Chat | $0.33 | $2.75 |
| us.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | Chat | $2.19 | $17.50 |
| amazon.nova-2-multimodal-embeddings-v1:0 | AWS Bedrock | Embedding | $0.14 | $0.0000 |
| amazon.nova-micro-v1:0 | AWS Bedrock | Chat | $0.04 | $0.14 |
| amazon.nova-pro-v1:0 | AWS Bedrock | Chat | $0.80 | $3.20 |
| amazon.titan-embed-image-v1 | AWS Bedrock | Embedding | $0.80 | $0.0000 |
| amazon.titan-embed-text-v1 | AWS Bedrock | Embedding | $0.10 | $0.0000 |
| amazon.titan-embed-g1-text-02 | AWS Bedrock | Embedding | $0.10 | $0.0000 |
| amazon.titan-embed-text-v2:0 | AWS Bedrock | Embedding | $0.02 | $0.0000 |
| twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | $70.00 | $0.0000 |
| us.twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | $70.00 | $0.0000 |
| eu.twelvelabs.marengo-embed-2-7-v1:0 | AWS Bedrock | Embedding | $70.00 | $0.0000 |
| twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | $7.50 |
| us.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | $7.50 |
| eu.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Chat | - | $7.50 |
| amazon.titan-text-express-v1 | AWS Bedrock | Chat | $1.30 | $1.70 |
| amazon.titan-text-lite-v1 | AWS Bedrock | Chat | $0.30 | $0.40 |
| amazon.titan-text-premier-v1:0 | AWS Bedrock | Chat | $0.50 | $1.50 |
| anthropic.claude-3-5-haiku-20241022-v1:0 | AWS Bedrock | Chat | $0.80 | $4.00 |
| anthropic.claude-haiku-4-5-20251001-v1:0 | AWS Bedrock | Chat | $1.00 | $5.00 |
| anthropic.claude-haiku-4-5@20251001 | AWS Bedrock | Chat | $1.00 | $5.00 |
| anthropic.claude-3-5-sonnet-20240620-v1:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-3-5-sonnet-20241022-v2:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-3-7-sonnet-20240620-v1:0 | AWS Bedrock | Chat | $3.60 | $18.00 |
| anthropic.claude-3-7-sonnet-20250219-v1:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-3-haiku-20240307-v1:0 | AWS Bedrock | Chat | $0.25 | $1.25 |
| anthropic.claude-3-opus-20240229-v1:0 | AWS Bedrock | Chat | $15.00 | $75.00 |
| anthropic.claude-3-sonnet-20240229-v1:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-instant-v1 | AWS Bedrock | Chat | $0.80 | $2.40 |
| anthropic.claude-opus-4-1-20250805-v1:0 | AWS Bedrock | Chat | $15.00 | $75.00 |
| anthropic.claude-opus-4-20250514-v1:0 | AWS Bedrock | Chat | $15.00 | $75.00 |
| anthropic.claude-opus-4-5-20251101-v1:0 | AWS Bedrock | Chat | $5.00 | $25.00 |
| anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | $5.00 | $25.00 |
| global.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | $5.00 | $25.00 |
| us.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | $5.50 | $27.50 |
| eu.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | $5.50 | $27.50 |
| au.anthropic.claude-opus-4-6-v1 | AWS Bedrock | Chat | $5.50 | $27.50 |
| anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.00 | $25.00 |
| global.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.00 | $25.00 |
| us.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.50 | $27.50 |
| eu.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.50 | $27.50 |
| au.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.50 | $27.50 |
| anthropic.claude-fable-5 | AWS Bedrock | Chat | $10.00 | $50.00 |
| global.anthropic.claude-fable-5 | AWS Bedrock | Chat | $10.00 | $50.00 |
| us.anthropic.claude-fable-5 | AWS Bedrock | Chat | $11.00 | $55.00 |
| eu.anthropic.claude-fable-5 | AWS Bedrock | Chat | $11.00 | $55.00 |
| anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.00 | $25.00 |
| global.anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.00 | $25.00 |
| us.anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.50 | $27.50 |
| eu.anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.50 | $27.50 |
| au.anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.50 | $27.50 |
| jp.anthropic.claude-opus-5 | AWS Bedrock | Chat | $5.50 | $27.50 |
| anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.00 | $25.00 |
| global.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.00 | $25.00 |
| us.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.50 | $27.50 |
| eu.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.50 | $27.50 |
| au.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.50 | $27.50 |
| jp.anthropic.claude-opus-4-8 | AWS Bedrock | Chat | $5.50 | $27.50 |
| jp.anthropic.claude-opus-4-7 | AWS Bedrock | Chat | $5.50 | $27.50 |
| anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.00 | $10.00 |
| global.anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.00 | $10.00 |
| us.anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.20 | $11.00 |
| eu.anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.20 | $11.00 |
| au.anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.20 | $11.00 |
| jp.anthropic.claude-sonnet-5 | AWS Bedrock | Chat | $2.20 | $11.00 |
| anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.00 | $15.00 |
| global.anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.00 | $15.00 |
| us.anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.30 | $16.50 |
| eu.anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.30 | $16.50 |
| au.anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.30 | $16.50 |
| jp.anthropic.claude-sonnet-4-6 | AWS Bedrock | Chat | $3.30 | $16.50 |
| anthropic.claude-sonnet-4-20250514-v1:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-sonnet-4-5-20250929-v1:0 | AWS Bedrock | Chat | $3.00 | $15.00 |
| anthropic.claude-v1 | AWS Bedrock | Chat | $8.00 | $24.00 |
| anthropic.claude-v2:1 | AWS Bedrock | Chat | $8.00 | $24.00 |
| zephyr-7b-beta | Anyscale | Chat | $0.15 | $0.15 |
| CodeLlama-34b-Instruct-hf | Anyscale | Chat | $1.00 | $1.00 |
| CodeLlama-70b-Instruct-hf | Anyscale | Chat | $1.00 | $1.00 |
| gemma-7b-it | Anyscale | Chat | $0.15 | $0.15 |
| Llama-2-13b-chat-hf | Anyscale | Chat | $0.25 | $0.25 |
| Llama-2-70b-chat-hf | Anyscale | Chat | $1.00 | $1.00 |
| Llama-2-7b-chat-hf | Anyscale | Chat | $0.15 | $0.15 |
| Meta-Llama-3-70B-Instruct | Anyscale | Chat | $1.00 | $1.00 |
| Meta-Llama-3-8B-Instruct | Anyscale | Chat | $0.15 | $0.15 |

## FAQ

### How does the LLM cost calculator work?

Enter your expected input and output token volumes (or images, audio seconds, or pages depending on the model mode) and the calculator multiplies them by each model’s published per-token pricing to estimate your total cost. Pricing is sourced from each provider’s official rate card and normalized to a per-1M-token basis for easy comparison.

### Is the pricing data up to date?

Model pricing is regenerated from the upstream datasheet on every build, so the figures reflect the latest published rates for hundreds of models across dozens of providers. Always confirm against the provider’s own pricing page before committing to production spend.

### How can I compare costs across providers?

Use the provider pages to see every model from a given provider with input and output pricing side by side, or open an individual model page to view alternatives ranked by price. Bifrost AI Gateway can then route traffic to the most cost-effective provider automatically.

### Why do input and output tokens cost different amounts?

Most providers charge more for output (generated) tokens than input (prompt) tokens because generation is more compute-intensive. For generation-heavy workloads, output pricing dominates your bill; for retrieval or long-context workloads, input pricing matters more.

### How can I reduce my LLM API costs?

Route each request to the cheapest model that meets your quality bar, cache repeated prompts, and fail over to alternative providers during outages or price spikes. Bifrost AI Gateway provides this multi-provider routing, load balancing, and caching out of the box.

## Related Resources

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

---

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