Llm Prices

data-ai MCP Server

Zero-dependency Python CLI + MCP server for comparing LLM API costs across 144 models and 22 providers (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, Groq...)

Verified
data-aidata-aipythongcp
6 views0 stars1 forksMIT

Why This Matters

Discovered via github-topic:mcp and last synced 3mo ago.

Verified
Source
github-topic:mcp
Stars
0
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
37
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (37)

Context

Notes

claude-sonnet-4-6

Anthropic

Mistral

12

Perplexity

4

AI21

2

gpt-4o

OpenAI

Groq

9

Bedrock

5

calculate_api_cost

Calculate exact cost for input+output tokens

Model

Provider

128k

Latest multimodal flagship

OpenAI

13

Anthropic

8

DeepSeek

3

search_llm_models

Search models by name or filter by provider

gpt-4o-mini

OpenAI

qwen3-235b

Together

7

Qwen3, Kimi K2, Llama, DeepSeek

Cerebras

3

Tool

Description

SOL

`kbghHYeBXr2AcYUyvkofHa9sArgkJcKBC6zZhSdao82`

1023k

1M context, cost-efficient

Output

Total

xAI

8

5

Llama 3.1 8B ($0.02/Mtok — cheapest!), Llama 3.3 70B, Qwen3 235B (262k ctx), Nemotron 253B, DeepSeek-R1-0528

Chain

Address

Google

6

Fireworks

6

SambaNova

5

get_model_pricing

Get pricing for a specific model

Provider

Models

Cohere

3

DeepInfra

4

find_cheapest_models

Find the N cheapest models for your workload

compare_models

Compare cost of a workload across multiple models

4

Llama 4 Maverick (1M ctx), Scout, DeepSeek-R1-0528, Qwen3 235B

list_providers

List all 24 providers with min pricing