grok-4.20-0309-reasoning vs jamba-mini-1.7
jamba-mini-1.7 is 10.0× cheaper on input than grok-4.20-0309-reasoning.
| grok-4.20-0309-reasoning | jamba-mini-1.7 | |
|---|---|---|
| Input / 1M | $2.00 | $0.20 |
| Cached input / 1M | $0.20 | — |
| Output / 1M | $6.00 | $0.40 |
| Context window | 2M | 256K |
| Max output | 2M | 256K |
| Provider | xAI | 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: grok-4.20-0309-reasoning leads jamba-mini-1.7 by 51.5 points on following instructions (IFBench), for 12.0× the price.
Following instructions
extraction, classification, sticking to a format
IFBenchgrok-4.20-0309-reasoning +51.5
Tool use
multi-step agent work against real tools
τ²-benchgrok-4.20-0309-reasoning +83.9
Hard reasoning
graduate-level science and multi-step analysis
GPQA Diamondgrok-4.20-0309-reasoning +56.3
Averaged over the benchmarks both models sat, jamba-mini-1.7 returns 101.6 points of pass rate per dollar of blended price against 29.8 — 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: grok-4.20-0309-reasoning
- Better at following instructions: grok-4.20-0309-reasoning (82.9% vs 31.4% on IFBench)
- Better at tool use: grok-4.20-0309-reasoning (96.5% vs 12.6% on τ²-bench)
- Better at hard reasoning: grok-4.20-0309-reasoning (88.5% 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
grok-4.20-0309-reasoning detail · jamba-mini-1.7 detail · All xAI pricing · All comparisons