# Claude Fable 5 vs GPT-6.2 Astra Law

As of November 17, 2026, Claude Fable 5 costs 25% more per input token than GPT-6.2 Astra Law ($10.00 vs $8.00 per 1M) and has a 1M-token context window versus 922K.

- Page: https://models.litellm.ai/compare/claude-fable-5-vs-gpt-6.2-astra-law
- Claude Fable 5: https://models.litellm.ai/models/claude-fable-5
- GPT-6.2 Astra Law: https://models.litellm.ai/models/gpt-6.2-astra-law

## Side by side

| | Claude Fable 5 | GPT-6.2 Astra Law |
|---|---|---|
| Input, per 1M tokens | $10.00 | $8.00 |
| Output, per 1M tokens | $50.00 | $40.00 |
| Cache read, per 1M tokens | $1.00 | $0.40 |
| Cache write, per 1M tokens | $12.50 | $10.00 |
| 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 | 12 | 2 |
| Price shown is from | Anthropic | OpenAI |
| Added to LiteLLM | June 2026 | November 17, 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-6.2 Astra Law: OpenAI at $8.00 input per 1M tokens (`gpt-6.2-astra-law`)

## When to pick which

- Claude Fable 5: Available from 12 providers through LiteLLM, vs 2.
- GPT-6.2 Astra Law: Costs 20% less per input token: $8.00 vs $10.00 per 1M.

## FAQ

### Which is cheaper, Claude Fable 5 or GPT-6.2 Astra Law?

GPT-6.2 Astra Law is cheaper at 3 input tokens per output token: $16.00 per 1M tokens blended ($8.00 input, $40.00 output), versus $20.00 ($10.00 and $50.00) for Claude Fable 5, as of November 17, 2026.

### Which has the larger context window, Claude Fable 5 or GPT-6.2 Astra Law?

Claude Fable 5 has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-6.2 Astra Law.

### Can I switch from Claude Fable 5 to GPT-6.2 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-6.2-astra-law", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.
