Ricursive: Ripple 65B Preview vs Upstage Solar Pro 2 — API Pricing, 150K Cache & Latency Benchmark
Side-by-side unit economics audit comparing Ricursive: Ripple 65B Preview (ricursiveai/ripple-65b-preview: Input $0.1/1M, Output $0.3/1M, Warm Cache Read $0.025/1M) against Upstage Solar Pro 2 (upstage-solar-pro-2: Input $0.25/1M, Output $0.75/1M, Warm Cache Read $0.25/1M).
Activate 4-breakpoint prefix caching on Ricursive: Ripple 65B Preview to cut input token costs from $0.1/1M down to $0.025/1M, or route async workloads via Batch API for 50% off.
Lock static system prompt prefixes on Upstage Solar Pro 2 to pay $0.25/1M warm cache rates instead of $0.25/1M uncached input, plus eligible startup cloud credits.
In Etuki FinOps telemetry comparing Ricursive: Ripple 65B Preview (API ID: ricursiveai/ripple-65b-preview) vs Upstage Solar Pro 2 (API ID: upstage-solar-pro-2), Ricursive: Ripple 65B Preview offers lower standard uncached input pricing at $0.1/1M tokens, while Ricursive: Ripple 65B Preview leads in 10-turn 150K cache-pinned coding economics at $0.0548 per 10 turns (saving $0.3352 over Upstage Solar Pro 2). For latency-sensitive interactive agents, Upstage Solar Pro 2 delivers 156ms faster P90 time-to-first-token (360ms vs 516ms).
| Specification / FinOps Dimension | Ricursive: Ripple 65B Preview (ricursiveai/ripple-65b-preview) | Upstage Solar Pro 2 (upstage-solar-pro-2) | Verified Advantage |
|---|---|---|---|
| Official Vendor API ID | ricursiveai/ripple-65b-preview | upstage-solar-pro-2 | UMCE 563-Registry Locked |
| 563-Registry & Routing Eligibility | is_known: true | routable: true | is_known: true | routable: true | Both Merkle Verified |
| Standard Uncached Input (/1M tokens) | $0.1 / 1M | $0.25 / 1M | Ricursive: Ripple 65B Preview |
| Warm Prefix Cache Read (/1M tokens) | $0.025 / 1M | $0.25 / 1M | Ricursive: Ripple 65B Preview |
| Standard Output (/1M tokens) | $0.3 / 1M | $0.75 / 1M | Ricursive: Ripple 65B Preview |
| Context Window Capacity | 1049K Tokens | 128K Tokens | Ricursive: Ripple 65B Preview |
| 150K Prompt × 10 Turns (Unpinned Cold + 2K Out) | $0.1560 | $0.3900 | Ricursive: Ripple 65B Preview |
| 150K × 10 Turns Case A (100% Static Pinned) | $0.0548 (saves $0.1012) | $0.3900 (saves $0.0000) | Ricursive: Ripple 65B Preview (-$0.3352) |
| 150K × 10 Turns Case B (90% Static + 10% Tail) | $0.0649 (saves $0.0911) | $0.3900 (saves $0.0000) | Ricursive: Ripple 65B Preview |
| P50 / P90 First-Token Latency | 351ms / 516ms (133 tok/s) | 245ms / 360ms (82 tok/s) | Upstage Solar Pro 2 (-156ms) |
1. Full-Turn Rate-Card Substitution for Ricursive: Ripple 65B Preview: At an uncached input rate of $0.1/1M, output rate of $0.3/1M, and warm cache read rate of $0.025/1M, running 10 consecutive 150,000-token coding agent turns (with 2,000 output tokens/turn) without prefix pinning costs $0.1560. Locking 100% static prefixes (Case A: 1 cold turn + 9 warm cached turns + 20K total output) reduces 10-turn spend to $0.0548 (saving $0.1012); under a 90% static prefix + 10% dynamic tail workload (Case B), 10-turn spend is $0.0649.
2. Full-Turn Rate-Card Substitution for Upstage Solar Pro 2 & Winner Verdict: On Upstage Solar Pro 2 ($0.25/1M input, $0.75/1M output, $0.25/1M warm cache), 10 unpinned 150K turns cost $0.3900, dropping to $0.3900 in Case A and $0.3900 in Case B. Across every 10-turn 150K coding loop (including output tokens), Ricursive: Ripple 65B Preview delivers an additional $0.3352 Case-A cost advantage.
Production Workload TCO: 25,000 MAU • 50M Tokens/Mo (50% Cache Hit) • 2,000 GB Egress
💡 Optimal FinOps Verdict: Deploying Ricursive: Ripple 65B Preview saves $12.00/month ($144/year) at 25,000 MAU & 50M monthly tokens (80% input / 20% output split with 50% prefix cache hit rate).