# Claude Fable 5.2 vs GPT-6 Astra

As of November 10, 2026, GPT-6 Astra costs 25% more per input token than Claude Fable 5.2 ($10.00 vs $8.00 per 1M) and has a 922K-token context window versus 1M.

- Page: https://models.litellm.ai/compare/claude-fable-5-2-vs-gpt-6-astra
- Claude Fable 5.2: https://models.litellm.ai/models/claude-fable-5-2
- GPT-6 Astra: https://models.litellm.ai/models/gpt-6-astra

## Side by side

| | Claude Fable 5.2 | GPT-6 Astra |
|---|---|---|
| Input, per 1M tokens | $8.00 | $10.00 |
| Output, per 1M tokens | $40.00 | $50.00 |
| Cache read, per 1M tokens | $0.20 | $1.00 |
| Cache write, per 1M tokens | $10.00 | $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 | 5 | 11 |
| Price shown is from | Anthropic | OpenAI |
| Added to LiteLLM | November 9, 2026 | September 3, 2026 |

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

## Cheapest provider for each

- Claude Fable 5.2: Anthropic at $8.00 input per 1M tokens (`claude-fable-5-2`)
- GPT-6 Astra: Databricks at $10.00 input per 1M tokens (`databricks/databricks-gpt-6-astra`)

## Benchmark scores

| Benchmark | Claude Fable 5.2 | GPT-6 Astra |
|---|---|---|
| Epoch Capabilities Index (Overall) | 174.2 | 169.2 |
| GPQA Diamond (Reasoning and knowledge) | 93.9% (max) | 95.8% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 93.8% (xhigh) | 95.0% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 94.0% (max) | 75.6% (max) |
| FrontierMath (tiers 1-3) (Math) | 95.1% (max) | 93.7% (max) |
| FrontierMath (tier 4) (Math) | 100.0% (max) | 97.6% (high) |
| OTIS Mock AIME 2024-2025 (Math) | 99.7% (max) | 100.0% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of November 9, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- Claude Fable 5.2: Costs 20% less per input token: $8.00 vs $10.00 per 1M.
- GPT-6 Astra: Available from 11 providers through LiteLLM, vs 5.

## FAQ

### Which is cheaper, Claude Fable 5.2 or GPT-6 Astra?

Claude Fable 5.2 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 GPT-6 Astra, as of November 10, 2026.

### Which has the larger context window, Claude Fable 5.2 or GPT-6 Astra?

Claude Fable 5.2 has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-6 Astra.

### Can I switch from Claude Fable 5.2 to GPT-6 Astra without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-fable-5-2" to "gpt-6-astra", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.