Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Reka Flash (Sep '24) | Qwen3 30B A3B (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.2 | $0.2 |
| Output ($/M tokens) | $0.8 | $0.8 |
Verdict. Qwen3 30B A3B (Non-reasoning) takes the aggregate benchmark matchup 1–0 across 1 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Qwen3 30B A3B (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Qwen3 30B A3B (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Reka Flash (Sep '24) is strongest on Intelligence Index (6.0). Qwen3 30B A3B (Non-reasoning) leads on Intelligence Index (6.6).
Speed. On throughput, Qwen3 30B A3B (Non-reasoning) generates tokens at 104 tok/s versus 2 tok/s — about 98% faster. On time-to-first-token, Qwen3 30B A3B (Non-reasoning) responds in 2210ms vs 27160ms, which matters most for chat-style UIs.
Provider. Reka AI and Alibaba sell to overlapping but distinct developer audiences: Reka AI tends to ship frontier reasoning models with premium positioning, while Alibaba 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): Reka Flash (Sep '24) costs $18.00 ($216/year); Qwen3 30B A3B (Non-reasoning) costs $18.00 ($216/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Reka Flash (Sep '24) ≈ $2.60/run, Qwen3 30B A3B (Non-reasoning) ≈ $2.60/run. At agent/realtime scale (200M input / 100M output per million requests): Reka Flash (Sep '24) ≈ $120/run, Qwen3 30B A3B (Non-reasoning) ≈ $120/run.
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.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.
Qwen3 30B A3B (Non-reasoning) wins 1 out of 12 benchmarks compared to 0 for Reka Flash (Sep '24). See the detailed benchmark chart above for per-category results.
Qwen3 30B A3B (Non-reasoning) generates tokens faster at 104 tok/s vs 2 tok/s. However, Qwen3 30B A3B (Non-reasoning) has lower time-to-first-token (2.21s vs 27.16s).
Choose based on your priorities: both are similarly priced, Qwen3 30B A3B (Non-reasoning) for stronger benchmark performance, and Qwen3 30B A3B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.