Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemma 4 26B A4B (Non-reasoning) | Jamba 1.5 Mini |
|---|---|---|
| Input ($/M tokens) | $0.13 | $0.2 |
| Output ($/M tokens) | $0.4 | $0.4 |
Verdict. Gemma 4 26B A4B (Non-reasoning) wins the overall benchmark matchup 1–0 across 1 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Jamba 1.5 Mini is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Jamba 1.5 Mini makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Gemma 4 26B A4B (Non-reasoning) is strongest on Intelligence Index (20.4). Jamba 1.5 Mini leads on Intelligence Index (2.3).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. Google and AI21 Labs sell to overlapping but distinct developer audiences: Google tends to ship frontier reasoning models with premium positioning, while AI21 Labs often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Gemma 4 26B A4B (Non-reasoning) costs $9.90 ($119/year); Jamba 1.5 Mini costs $12.00 ($144/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Gemma 4 26B A4B (Non-reasoning) ≈ $1.45/run, Jamba 1.5 Mini ≈ $1.80/run. At agent/realtime scale (200M input / 100M output per million requests): Gemma 4 26B A4B (Non-reasoning) ≈ $66/run, Jamba 1.5 Mini ≈ $80/run. Gemma 4 26B A4B (Non-reasoning) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
Gemma 4 26B A4B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.20/M tokens vs $0.25/M for Jamba 1.5 Mini.
Gemma 4 26B A4B (Non-reasoning) wins 1 out of 12 benchmarks compared to 0 for Jamba 1.5 Mini. See the detailed benchmark chart above for per-category results.
Gemma 4 26B A4B (Non-reasoning) generates tokens faster at 75 tok/s vs — tok/s. Gemma 4 26B A4B (Non-reasoning) also has lower time-to-first-token (1.18s vs —s).
Choose based on your priorities: Gemma 4 26B A4B (Non-reasoning) for lower cost, Gemma 4 26B A4B (Non-reasoning) for stronger benchmark performance, and Gemma 4 26B A4B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.