Compare verified pricing and model limits for cost-gated routing across Anthropic capability tiers. The cost example uses a long-context research workload and does not assume equal model quality.
Fable 5 carries a materially higher token rate than Sonnet 4.6. A practical rollout starts with the failure cases that matter, then routes to Fable only where measured task outcomes justify the premium.
| Decision factor | Claude Fable 5 | Claude Sonnet 4.6 |
|---|---|---|
| Standard token price | $10 input and $50 output per million tokens | $3 input and $15 output per million tokens |
| Tracked limits | 1M context and 128k maximum output | 1M context and 128k maximum output |
| Provider positioning | Anthropic positions Fable 5 for its most demanding reasoning and long-horizon agentic work | Lower-priced Sonnet-tier baseline in the currently tracked catalog |
Prices are USD per 1M tokens under each model's verified default profile.
| Field | Claude Fable 5 | Claude Sonnet 4.6 |
|---|---|---|
| API access provider | Anthropic | Anthropic |
| API model ID | claude-fable-5 | claude-sonnet-4-6 |
| Input / 1M | $10.00 | $3.00 |
| Cached input / 1M | $1.00 | $0.30 |
| Output / 1M | $50.00 | $15.00 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Maximum output | 128,000 tokens | 128,000 tokens |
| Accepted input | text, image | text, image |
150,000 input and 5,000 output tokens per request, 2,000 monthly requests, and 10% cached input.
Cost result: Claude Sonnet 4.6 is $2,261.00 lower per month for these assumptions. This is a price comparison, not a model-quality ranking.
Models whose tracked context window is below the scenario input are excluded from the compatible-model table.
Latency, reliability, output quality, retries, regional processing, and provider-specific tool charges can change the practical decision.
These comparisons share a model or provider decision with this page.