# Claude Fable 5 vs GPT-6 Astra Law

As of November 10, 2026, Claude Fable 5 and GPT-6 Astra Law cost the same: $10.00 per 1M input tokens and $50.00 per 1M output tokens. Claude Fable 5 has the larger context window: 1M tokens versus 922K.

- Page: https://models.litellm.ai/compare/claude-fable-5-vs-gpt-6-astra-law
- Claude Fable 5: https://models.litellm.ai/models/claude-fable-5
- GPT-6 Astra Law: https://models.litellm.ai/models/gpt-6-astra-law

## Side by side

| | Claude Fable 5 | GPT-6 Astra Law |
|---|---|---|
| Input, per 1M tokens | $10.00 | $10.00 |
| Output, per 1M tokens | $50.00 | $50.00 |
| Cache read, per 1M tokens | $1.00 | $1.00 |
| Cache write, per 1M tokens | $12.50 | – |
| Context window | 1,000,000 tokens | 922,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 10 | 2 |
| Price shown is from | Anthropic | OpenAI |
| Added to LiteLLM | June 2026 | October 31, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Claude Fable 5: Databricks at $10.00 input per 1M tokens (`databricks/databricks-claude-fable-5`)
- GPT-6 Astra Law: OpenAI at $10.00 input per 1M tokens (`gpt-6-astra-law`)

## When to pick which

- Claude Fable 5: Available from 10 providers through LiteLLM, vs 2.

## FAQ

### Which is cheaper, Claude Fable 5 or GPT-6 Astra Law?

They cost the same: $10.00 per 1M input tokens and $50.00 per 1M output tokens, as of November 10, 2026.

### Which has the larger context window, Claude Fable 5 or GPT-6 Astra Law?

Claude Fable 5 has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-6 Astra Law.

### Can I switch from Claude Fable 5 to GPT-6 Astra Law without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-fable-5" to "gpt-6-astra-law", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.