firefrost-gaming/firefrost-operations-manual
3
0
Fork 0
Code Issues 146 Pull Requests Packages Projects Releases Wiki Activity

docs: Correct Gemini free tier — prepay required, 250 req/day since Apr 1 2026

Browse Source
This commit is contained in:
Claude
2026-04-16 00:47:54 +00:00
parent 16ea1f94f3
commit 191018f1e3
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/reference/ai-api-cost-analysis-2026-04-15.md
View File

@@ -47,11 +47,11 @@ Gemini is our architectural partner. Strong candidate for fallback.
| Model | Input /1M | Output /1M | Context | Notes |
|-------|-----------|------------|---------|-------|
| **2.5 Flash-Lite** | $0.10 | $0.40 | 1M | Cheapest paid option |
| **2.5 Flash (FREE)** | $0 | $0 | 1M | 1,500 req/day free |
| **2.5 Flash** | $0.15 | $0.60 | 1M | ⚠️ "Free" tier now ~250 req/day, prepay required since Apr 1 2026 |
| 2.5 Pro | $1.25 | $10.00 | 1M | Premium reasoning |
| 3 Flash | $0.50 | $3.00 | 1M | Balanced |
**Key advantage:** Gemini 2.5 Flash has **1M token context** — entire ops manual fits in one prompt without RAG during emergency. 1,500 free requests/day is more than enough for fallback use.
**Key advantage:** Gemini 2.5 Flash has **1M token context** — entire ops manual fits in one prompt without RAG during emergency. ⚠️ Free tier reduced to ~250 req/day as of Apr 2026, prepay billing required. Paid is $0.15/$0.60 per 1M tokens — still very cheap.
**Batch discount:** 50% off all paid models for async work.
@@ -70,7 +70,7 @@ Edge GPU inference via Cloudflare's network. Since firefrostgaming.com already r
| Provider | Model | Cost/month (emergency) | Context | Reliability |
|----------|-------|----------------------|---------|-------------|
| **Anthropic** (primary) | Sonnet 4.6 | ~$2-5 | 1M | ⚠️ 9 outages in April |
| **Gemini Free** (fallback) | 2.5 Flash | $0 | 1M | ✅ Different infrastructure |
| **Gemini Paid** (fallback) | 2.5 Flash | ~$0.50/month | 1M | ✅ Different infrastructure, cheap paid tier |
| **OpenRouter Free** (backup) | Llama 3.3 70B | $0 | 65K | ✅ Routes to multiple providers |
| **Cloudflare Workers AI** | Various | ~$0-1 | Varies | ✅ Edge network |
| **Local Ollama** (TX1) | Llama 3.1 8B | $0 | 16K | ❌ CPU too slow for real-time |
@@ -83,7 +83,7 @@ Edge GPU inference via Cloudflare's network. Since firefrostgaming.com already r
2. **The outage problem is real** — 9 outages in April 2026 alone, including today where both claude.ai AND the API went down simultaneously. A fallback that also uses Anthropic infrastructure doesn't help.
3. **Gemini free tier is the obvious answer** for emergency fallback — different company, different infrastructure, 1,500 req/day free, 1M context window means no RAG needed in an emergency.
3. **Gemini paid tier is still very cheap** for emergency fallback — $0.15/$0.60 per 1M tokens, different infrastructure from Anthropic, 1M context. "Free" tier is misleading — prepay required since April 1 2026, only 250 req/day.
4. **OpenRouter free tier** as a secondary backup — routes through multiple providers, if one goes down it tries another.