LiteLLMModels

Claude Mythos Preview API Pricing

As of October 10, 2026, Claude Mythos Preview costs $10.00 per 1M input tokens and $50.00 per 1M output tokens on Anthropic, with cache reads at $1.00 and cache writes at $12.50 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $10.00 to $27.50. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

By AnthropicModel ID claude-mythos-previewPrices updated Checked
Deprecated: Anthropic lists June 9, 2026 as the deprecation date for claude-mythos-preview.
Input
$10.00 / 1M tokens
Output
$50.00 / 1M tokens
Cache read
$1.00 / 1M tokens
Context window
1,000,000 tokens
Max output
128,000 tokens
Providers
2
Added to LiteLLM
April 2026

Claude Mythos Preview pricing by provider

5 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Anthropicclaude-mythos-preview$10.00$50.00$1.00$12.501M
Amazon Bedrockanthropic.claude-mythos-preview$27.50$137.50$2.75$34.381M
Amazon BedrockAPAC cross-regionapac.anthropic.claude-mythos-preview$27.50$137.50$2.75$34.381M
Amazon BedrockAustralia cross-regionau.anthropic.claude-mythos-preview$27.50$137.50$2.75$34.381M
Amazon BedrockUS cross-regionus.anthropic.claude-mythos-preview$27.50$137.50$2.75$34.381M

Other Claude Mythos Preview prices on Anthropic

Cache write, 1 hour$20.00 per 1M tokens
Web search$10.00 per 1K searches

What Claude Mythos Preview costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Anthropic$45.00
Amazon Bedrock$123.80

100 long-document requests with 100,000 input and 2,000 output tokens each

Anthropic$110.00
Amazon Bedrock$302.50

Claude Mythos Preview features

Use Claude Mythos Preview with LiteLLM

Call Claude Mythos Preview through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="claude-mythos-preview",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: claude-mythos-preview
    litellm_params:
      model: claude-mythos-preview
      api_key: os.environ/ANTHROPIC_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "claude-mythos-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Mythos Preview FAQ

How much does Claude Mythos Preview cost?

Claude Mythos Preview costs $10.00 per 1M input tokens and $50.00 per 1M output tokens on Anthropic, with cache reads at $1.00 and cache writes at $12.50 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $10.00 to $27.50.

What is the context window of Claude Mythos Preview?

Claude Mythos Preview has a 1,000,000-token context window and returns up to 128,000 tokens per response.

Which providers offer Claude Mythos Preview?

Claude Mythos Preview is available from 2 providers through LiteLLM: Anthropic and Amazon Bedrock. The lowest price is on Anthropic.

How do I call Claude Mythos Preview with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="claude-mythos-preview", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Claude Mythos Preview support?

Claude Mythos Preview supports function calling, structured output, image input, PDF input, reasoning, prompt caching and computer use.

When did LiteLLM add Claude Mythos Preview?

Claude Mythos Preview was added to LiteLLM's model price file in April 2026.

Is Claude Mythos Preview being deprecated?

Anthropic deprecated claude-mythos-preview on June 9, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Anthropic, Amazon Bedrock.

Provider pages: Anthropic, Amazon Bedrock.