Claude Fable 5 vs Claude Haiku 4.5
Anthropic's Claude Fable 5 and Anthropic's Claude Haiku 4.5 both target production language workloads, but they price and behave differently. Here is the side-by-side.
Pricing checked against provider documentation on . How we verify
The short answer
Claude Haiku 4.5 is the cheaper option — roughly 10.0x less on a blended workload, and it suits lowest-latency claude responses. Claude Fable 5 justifies its premium when you need long-horizon agentic engineering.
Anthropic • Claude 5
$10.00 / $50.00
/ 1M tokens (input / output)
Anthropic's most capable widely released model, built for agents that run for hours rather than seconds. Adaptive thinking is always on and cannot be disabled, which is part of why it tops the Artificial Analysis Intelligence Index — and why its cost per task runs roughly triple GPT-5.6 Sol's for a one-point intelligence lead.
Anthropic • Claude 4.5
$1.00 / $5.00
/ 1M tokens (input / output)
The fastest model Anthropic ships, still on the Claude 4.5 generation with a 200K window and an early-2025 knowledge cutoff. Worth it when response latency is the product requirement; otherwise Sonnet 5 offers more capability and five times the context for twice the price.
Input price
Claude Haiku 4.5 is 90% cheaper than Claude Fable 5 on input tokens.
Output price
Claude Haiku 4.5 is 90% cheaper than Claude Fable 5 on output tokens — usually the side that dominates the bill.
Monthly cost at three workload sizes
Standard (non-batch, non-cached) rates. Reasoning models will exceed these figures because thinking tokens bill as output.
| Workload | Claude Fable 5 | Claude Haiku 4.5 | Difference |
|---|---|---|---|
| Light — 1M in / 200K out | $20 | $2 | $18 |
| Moderate — 10M in / 2M out | $200 | $20 | $180 |
| Heavy — 100M in / 20M out | $2,000 | $200 | $1,800 |
Specification comparison
| Attribute | Claude Fable 5 | Claude Haiku 4.5 |
|---|---|---|
| Input (/ 1M tokens) | $10.00 | $1.00 |
| Output (/ 1M tokens) | $50.00 | $5.00 |
| Cached input | $1.00 | $0.10 |
| Context window | 1,000,000 tokens | 200,000 tokens |
| Max output | 128,000 tokens | 64,000 tokens |
| Native reasoning | Yes | Yes |
| Knowledge cutoff | 2026-01 | 2025-02 |
| Relative latency | high | low |
| Open weights | No | No |
| API model ID | claude-fable-5 | claude-haiku-4-5 |
| Status | stable | stable |
Claude Fable 5: 5-minute cache writes $12.50/MTok, 1-hour $20/MTok. Requires 30-day data retention, so not available under zero-data-retention terms.
Choose Claude Fable 5 if…
- Multi-hour autonomous coding runs
- Large codebase migrations
- Hard scientific workflows
- High-stakes legal and medical analysis
Choose Claude Haiku 4.5 if…
- Real-time chat suggestions
- Lightweight extraction and tagging
- Guardrail and routing calls
- High-frequency background jobs
Frequently asked
Is Claude Fable 5 or Claude Haiku 4.5 cheaper?
Claude Haiku 4.5 is cheaper. On a blended 3:1 input-to-output workload it costs about 10.0x less than Claude Fable 5.
Which has the larger context window, Claude Fable 5 or Claude Haiku 4.5?
Claude Fable 5 has the larger window at 1M tokens versus 200K.
Should I use Claude Fable 5 or Claude Haiku 4.5?
Pick Claude Fable 5 for long-horizon agentic engineering. Pick Claude Haiku 4.5 for lowest-latency claude responses. If cost dominates the decision, Claude Haiku 4.5 wins; if you need the capability ceiling, benchmark both on your own evals before committing.