Skip to content

Supported Models

Shekel includes built-in pricing for popular LLM models and supports 400+ additional models via tokencost.

Built-in Models

These models have zero-dependency pricing built into shekel:

OpenAI Models

Model Input / 1K Output / 1K Use Case
gpt-4o $0.00250 $0.01000 Best for complex tasks, high quality
gpt-4o-mini $0.000150 $0.000600 Fast, cheap, good for most tasks
o1 $0.01500 $0.06000 Advanced reasoning, complex problems
o1-mini $0.00300 $0.01200 Reasoning on a budget
gpt-3.5-turbo $0.000500 $0.001500 Legacy, fast responses

Anthropic Models

Model Input / 1K Output / 1K Use Case
claude-3-5-sonnet-20241022 $0.00300 $0.01500 Latest, best quality
claude-3-haiku-20240307 $0.000250 $0.001250 Fast, cheap, high volume
claude-3-opus-20240229 $0.01500 $0.07500 Most capable, expensive

Google Models

Model Input / 1K Output / 1K Use Case
gemini-2.5-pro $0.00125 $0.01000 Most capable Gemini
gemini-2.5-flash $0.0000750 $0.000300 Fast, cost-efficient
gemini-2.0-flash $0.0000750 $0.000300 Latest flash model
gemini-1.5-pro $0.00125 $0.00500 Balanced quality/cost
gemini-1.5-flash $0.0000750 $0.000300 Fastest, cheapest

Native Gemini SDK support

To track costs when calling Gemini via the google-genai SDK directly (not through LiteLLM), install shekel[gemini]. See Google Gemini Integration.

Version Resolution

Shekel automatically resolves versioned model names:

# All of these resolve to "gpt-4o" pricing
models = [
    "gpt-4o",
    "gpt-4o-2024-08-06",
    "gpt-4o-2024-05-13",
    "gpt-4o-2024-11-20",
]

# All of these resolve to "gpt-4o-mini" pricing
models = [
    "gpt-4o-mini",
    "gpt-4o-mini-2024-07-18",
]

The longest matching prefix wins.

Extended Model Support (400+)

Install shekel[all-models] for 400+ models via tokencost:

pip install shekel[all-models]

This adds support for:

  • Cohere: command-r, command-r-plus, command-light, etc.
  • AI21: j2-ultra, j2-mid, jamba-instruct, etc.
  • Aleph Alpha: luminous-base, luminous-extended, etc.
  • Mistral: mistral-tiny, mistral-small, mistral-medium, etc.
  • Meta: llama-2-70b, llama-2-13b, etc.
  • And many more

See tokencost model list for complete list.

Custom Model Pricing

For unlisted or private models, provide custom pricing:

from shekel import budget

# Custom model
with budget(
    max_usd=1.00,
    price_per_1k_tokens={
        "input": 0.002,   # $0.002 per 1k input tokens
        "output": 0.006,  # $0.006 per 1k output tokens
    }
) as b:
    response = client.chat.completions.create(
        model="my-custom-model",
        messages=[{"role": "user", "content": "Hello"}],
    )

print(f"Cost: ${b.spent:.4f}")

Cost Comparison

Cheapest to Most Expensive (per 1M tokens input)

  1. gemini-1.5-flash: $0.075
  2. gpt-4o-mini: $0.150
  3. claude-3-haiku: $0.250
  4. gpt-3.5-turbo: $0.500
  5. gemini-1.5-pro: $1.250
  6. gpt-4o: $2.500
  7. claude-3-5-sonnet: $3.000
  8. o1-mini: $3.000
  9. o1: $15.000
  10. claude-3-opus: $15.000

Cheapest to Most Expensive (per 1M tokens output)

  1. gemini-1.5-flash: $0.300
  2. gpt-4o-mini: $0.600
  3. claude-3-haiku: $1.250
  4. gpt-3.5-turbo: $1.500
  5. gemini-1.5-pro: $5.000
  6. gpt-4o: $10.000
  7. o1-mini: $12.000
  8. claude-3-5-sonnet: $15.000
  9. o1: $60.000
  10. claude-3-opus: $75.000

Fallback Model Recommendations

Best Fallback Pairs

Primary Model → Fallback Model Savings
gpt-4o → gpt-4o-mini 94% cheaper
o1 → gpt-4o-mini 97% cheaper
claude-3-opus → claude-3-haiku 98% cheaper
claude-3-5-sonnet → claude-3-haiku 92% cheaper

View Pricing in CLI

# All models
shekel models

# By provider
shekel models --provider openai
shekel models --provider anthropic
shekel models --provider google

# Estimate costs
shekel estimate --model gpt-4o --input-tokens 1000 --output-tokens 500

Pricing Updates

Shekel's built-in pricing is updated with each release. To get the latest pricing:

pip install --upgrade shekel

Or use shekel[all-models] for real-time pricing via tokencost.

Next Steps