claude-fable-5 vs jamba-mini-1.7
jamba-mini-1.7 is 50.0× cheaper on input than claude-fable-5.
| claude-fable-5 | jamba-mini-1.7 | |
|---|---|---|
| Input / 1M | $10.00 | $0.20 |
| Cached input / 1M | $1.00 | — |
| Output / 1M | $50.00 | $0.40 |
| Context window | 1M | 256K |
| Max output | 128K | 256K |
| Provider | Anthropic | AI21 |
| Vision | Yes | No |
| Tool calling | Yes | No |
| Token count | estimated | estimated |
Capability for the money
Independent measurement · Artificial Analysis · read 2026-08-11Not the same tier: claude-fable-5 leads jamba-mini-1.7 by 60.4 points on hard reasoning (GPQA Diamond), for 80.0× the price.
Following instructions
extraction, classification, sticking to a format
IFBenchclaude-fable-5 +32.1
Tool use
multi-step agent work against real tools
τ²-benchclaude-fable-5 +85.9
Hard reasoning
graduate-level science and multi-step analysis
GPQA Diamondclaude-fable-5 +60.4
Averaged over the benchmarks both models sat, jamba-mini-1.7 returns 101.6 points of pass rate per dollar of blended price against 4.2 — the ratio that decides whether the dearer model earns its rate.
Each figure is a pass rate: the share of that test set the model answered correctly, measured by a third party rather than self-reported by the lab. Rows are different tests of different difficulty, so compare a model against the other model, not one row against the next. No published coding score for one of these models, so that lens is omitted. And a benchmark is not your workload — it narrows the shortlist, it does not pick for you.
Which to pick
- Cheaper input: jamba-mini-1.7
- Cheaper output: jamba-mini-1.7
- Larger context: claude-fable-5
- Better at following instructions: claude-fable-5 (63.5% vs 31.4% on IFBench)
- Better at tool use: claude-fable-5 (98.5% vs 12.6% on τ²-bench)
- Better at hard reasoning: claude-fable-5 (92.6% vs 32.2% on GPQA Diamond)
List price is not production cost. Output length, cache hit rate, retries and task quality move the real number more than the headline rate does — price your own prompt on the token ledger before deciding.
Related comparisons
claude-fable-5 detail · jamba-mini-1.7 detail · All Anthropic pricing · All comparisons