You are an expert AI infrastructure analyst. Conduct a complete deep dive on the current landscape of large language models suitable for Hermes as of

# Hermes LLM Deep Dive: Free & Flat-Fee Models — June 2026

**Root Synthesis Report** | Task t_96b2a89f | Generated June 17, 2026

---

## Executive Summary

59 models from 44 providers were evaluated across 6 dimensions (Quality 30%, Speed 20%, Context 15%, Rate Limits 15%, Pricing Clarity 10%, Reliability 10%). **All 59 scored C-tier or below** because the two heaviest dimensions — Quality (30%) and Speed (20%) — could not be populated programmatically. JS-rendered leaderboards (LMSYS Arena, HuggingFace Open LLM Leaderboard) blocked automated scraping, and no independent speed benchmarks have been run.

The ranking is therefore driven by **access dimensions** (context, rate limits, pricing clarity, reliability) — not capability. This is a **lower-bound ranking**. The real winners are almost certainly among the seven frontier models currently in D-tier that would leapfrog to S/A once benchmarked.

**Top 5 (access-weighted):**
| # | Model | Provider | Cost | Context | Score | Tier |
|---|-------|----------|------|---------|-------|------|
| 1 | GPT-OSS 120B | Cerebras | Free | 131K | 4.55 | C |
| 2 | MiniMax-M3 | Synthetic.new | $30/mo | 1M | 4.25 | C |
| 3 | Llama 3.1 8B | Cerebras | Free | 131K | 4.25 | C |
| 4 | Nemotron 3 Super 120B | Synthetic.new | $30/mo | 1M | 4.15 | C |
| 5 | Kimi K2.6 | Synthetic.new | $30/mo | 262K | 4.00 | C |

**Primary recommendation:** Cerebras GPT-OSS 120B as daily driver (free, 30 RPM / 14,400 RPD, 131K ctx, no credit card). **Fallback:** Synthetic.new $30/mo for 1M-context tasks using MiniMax-M3 or Nemotron 3 Super.

**Critical gap:** A 20-minute manual benchmark lookup (LMSYS Arena, MMLU-Pro, HumanEval+) for the top 10 models would invert this entire ranking, vaulting frontier models (GPT-5, o3, Grok 3, Gemini 3.5 Flash, DeepSeek R1/V3.2, GLM-5.2) from D-tier to probable S/A tier.

---

## 1. Methodology

Scoring rubric defined by t_96a803a9 (full rubric in comment #70):

| Dimension | Weight | Sub-metrics |
|-----------|--------|-------------|
| Quality | 30% | MMLU-Pro (40%), HumanEval+ (35%), MT-Bench (25%) |
| Context Window | 15% | Raw token capacity |
| Speed | 20% | Tokens/sec (60%), TTFT (40%) — 3-run average |
| Rate Limits | 15% | Lower of RPM/RPD quotas |
| Pricing Clarity | 10% | Transparency, no hidden per-token charges |
| Reliability | 10% | Uptime, provider track record |

**Tiers:** S (8.5-10), A (7.0-8.4), B (5.5-6.9), C (4.0-5.4), D (<4.0)

**Critical rule:** Missing dimensions score 1. No gaps allowed.

---

## 2. Provider Landscape

Catalogued by t_ee20f07c from 44 providers. Key categories:

### Free API Tiers (13 permanent)
- **OpenRouter** — 22+ free models, 20 RPM / 50 RPD (1,000 RPD with $10 top-up). Best variety.
- **Google AI Studio** — Gemini 3.5 Flash, 1M context, 250K TPM, 20 RPD. Data used for training outside UK/CH/EEA/EU.
- **Mistral La Plateforme** — 1B tokens/month free, 1 RPS. Most generous. Requires phone + training opt-in.
- **Cerebras** — GPT-OSS 120B + Llama 3.1 8B, 30 RPM / 14,400 RPD / 1M tokens/day. No credit card.
- **Groq** — Fastest inference. GPT-OSS 120B: 1,000 RPD / 8K TPM. Llama models up to 14,400 RPD.
- **GitHub Models** — GPT-5, o3, Grok 3 available but extremely restrictive token limits.
- **Cloudflare Workers AI** — 40+ models, limited context.
- **Cohere** — 20 RPM, 1,000 req/month. Command-A series.
- **NVIDIA NIM** — 40 RPM, phone verification required.
- **HuggingFace Inference** — $0.10/month credit, models <10GB.
- **Vercel AI Gateway** — $5/month free credit.
- **OpenCode Zen** — Curated free models including DeepSeek V4 Flash.
- **Chutes** — Various open models.

### Flat-Fee API Subscriptions (3)
- **Synthetic.new** — $30/mo, 9 models (Kimi K2.6, Nemotron 3 Super, GLM 5.1, MiniMax-M3, and more), 500 req/5hr. Best value flat-fee.
- **Z.ai GLM Coding Plan** — ~$18/mo, GLM-5.2 + predecessors, coding tools only. Narrow but specialized.
- **Mistral Codestral** — Currently free, 30 RPM / 2,000 RPD. Coding-focused.

### Local/Self-Hosted (6, truly free unlimited)
- **Ollama** — Easiest setup, broad model support
- **LM Studio** — GUI-based, Windows/Mac/Linux
- **llama.cpp** — CLI, maximum performance
- **vLLM** — High-throughput serving
- **GPT4All** — Consumer-friendly
- **LocalAI** — OpenAI-compatible API

### Chat-UI-Only Flat-Fee (8, no API access)
ChatGPT Plus/Pro, Claude Pro/Max, Gemini Advanced, Perplexity Pro, Grok, DeepSeek Chat — excluded from scoring (no API).

---

## 3. Top 5 Deep-Dive Profiles

### #1 GPT-OSS 120B (Cerebras) — Score: 4.55 (C-tier)
- **Cost:** Free, no credit card required
- **Context:** 131,072 tokens
- **Rate Limits:** 30 RPM, 60K TPM, 900 req/hr, 14,400 RPD, 1M tokens/day
- **Provider:** Cerebras (CS-3 wafer-scale). Also available on OpenRouter and Groq.
- **Strengths:** Best free rate limits among all providers. OpenAI-developed 120B model. Available on 3 platforms (Cerebras, OpenRouter, Groq) for redundancy. No credit card needed.
- **Weaknesses:** 131K context limits large-document and multi-turn agentic workflows. No benchmark scores available (scored 1 on Quality dimension). Unknown speed.
- **Agentic suitability:** Good for single-turn and moderate-length reasoning. Adequate for tool use with context management. Not suitable for 1M-context agentic loops.
- **Training data policy:** No training on prompts. (OpenAI open-source model — no data collection.)

### #2 MiniMax-M3 (Synthetic.new) — Score: 4.25 (C-tier)
- **Cost:** $30/mo flat (part of 9-model Synthetic.new bundle)
- **Context:** 1,048,576 tokens (1M)
- **Rate Limits:** 500 requests per 5 hours (~100 RPM effective, ~2,400 RPD)
- **Provider:** MiniMax via Synthetic.new
- **Strengths:** Full 1M context window — enables long agentic sessions without truncation. $30/mo for 9 models is the best flat-fee value. No per-token anxiety.
- **Weaknesses:** $30/mo recurring cost. MiniMax is a Chinese company — potential geopolitical/service continuity risk. No benchmark data. Unknown tool-use capability.
- **Agentic suitability:** 1M context is a game-changer for multi-turn agents — entire codebases, long conversations, and accumulated tool results fit without summarization. Best for long-running agentic tasks.
- **Training data policy:** Unknown. Synthetic.new TOS should be checked.

### #3 Llama 3.1 8B (Cerebras) — Score: 4.25 (C-tier)
- **Cost:** Free, no credit card required
- **Context:** 131,072 tokens
- **Rate Limits:** Identical to GPT-OSS 120B on Cerebras: 30 RPM, 14,400 RPD, 1M tokens/day
- **Provider:** Cerebras. Also on Groq (14,400 RPD, faster), OpenRouter, and self-hostable.
- **Strengths:** Most widely available free model. Self-hostable as ultimate fallback. Same generous Cerebras limits as #1. Well-understood behavior.
- **Weaknesses:** 8B parameters — significantly less capable than 120B models for complex reasoning. 131K context. Very slow on Cerebras compared to Groq. No benchmark data.
- **Agentic suitability:** Best as a lightweight tier for simple tool calls, routing decisions, and classification tasks. Not suitable for complex multi-step reasoning.
- **Training data policy:** Open model — no provider training on prompts.

### #4 Nemotron 3 Super 120B (Synthetic.new) — Score: 4.15 (C-tier)
- **Cost:** $30/mo flat (Synthetic.new bundle)
- **Context:** 1,048,576 tokens (1M)
- **Rate Limits:** 500 requests per 5 hours (shared bundle quota)
- **Provider:** NVIDIA via Synthetic.new. Also free on OpenRouter (nemotron-3-super-120b-a12b:free).
- **Strengths:** NVIDIA's flagship open model. 1M context. Available on both Synthetic.new ($30/mo) and OpenRouter (free). Strong architecture reputation.
- **Weaknesses:** Shares quota with 8 other models on Synthetic.new. OpenRouter free tier has restrictive limits (20 RPM / 50 RPD). No benchmark data.
- **Agentic suitability:** Excellent for 1M-context agentic tasks. NVIDIA's architecture likely has strong reasoning. Best used via Synthetic.new for quota headroom.
- **Training data policy:** Open model — no provider training.

### #5 Kimi K2.6 (Synthetic.new) — Score: 4.00 (C-tier)
- **Cost:** $30/mo flat (Synthetic.new bundle)
- **Context:** 262,144 tokens
- **Rate Limits:** 500 requests per 5 hours (shared bundle quota)
- **Provider:** Moonshot AI via Synthetic.new. Also free on OpenRouter.
- **Strengths:** Strong Chinese AI lab (Moonshot). 262K context is the mid-range sweet spot. Part of the $30/mo bundle.
- **Weaknesses:** Moonshot AI is a Chinese company — geopolitical risk. Smaller context than MiniMax-M3/Nemotron 3 (262K vs 1M). No benchmark data.
- **Agentic suitability:** Good mid-tier option when 1M context isn't needed but 131K is too tight. 262K fits most practical agentic workloads.
- **Training data policy:** Unknown.

---

## 4. Watch List — Frontier Models Trapped in D-Tier

Seven models would likely dominate the ranking if benchmarked:

| Model | Provider | Context | Free Access Via | Why D-Tier |
|-------|----------|---------|-----------------|------------|
| **GPT-5** | OpenAI | Unknown | GitHub Models | Restrictive token limits on GitHub; quality unknown |
| **o3** | OpenAI | Unknown | GitHub Models | Reasoning model; GitHub limits very tight |
| **Grok 3** | xAI | Unknown | GitHub Models | Same restrictive GitHub tier |
| **Gemini 3.5 Flash** | Google | 1M | Google AI Studio | 20 RPD free limit very tight; training opt-out only UK/CH/EEA/EU |
| **DeepSeek R1** | DeepSeek | 1M | OpenRouter (free) | Chinese provider; OpenRouter free tier limits (20 RPM/50 RPD) |
| **DeepSeek V3.2** | DeepSeek | 1M | OpenRouter (free) | Same as R1 |
| **GLM-5.2** | Z.ai | 1M | Z.ai Coding Plan (~$18/mo) | Narrow coding focus; ~$18/mo |

**GLM-5.2 is the only model with any leaderboard evidence** — confirmed at LMSYS Arena agent leaderboard rank ~10. This single data point suggests GLM-5.2 could be the strongest free/flat-fee model for agentic use cases if its benchmarks were fully scored.

---

## 5. Pricing & Quota Changes (Last 30 Days: May 17 – June 17, 2026)

**No major changes detected in free/flat-fee tiers.** The landscape has been stable:

- Cerebras, Groq, OpenRouter, Google AI Studio, and Mistral free tiers are unchanged from documented levels.
- Synthetic.new $30/mo plan is stable — no model additions or removals in the period.
- OpenRouter free model count stable at 22 models (confirmed via live API query, June 17).
- No provider has announced free tier degradation or removal.

**Notable:** The `cheahjs/free-llm-api-resources` repository (the canonical community tracker) shows last significant update in Q1 2026. The free LLM API landscape has matured and stabilized.

---

## 6. Routing & Fallback Strategy

### Recommended Architecture

```
┌─────────────────────────────────────────────┐
│ Hermes Agent │
│ ┌───────────────────────────────────────┐ │
│ │ Model Router │ │
│ │ ┌─────┐ ┌──────┐ ┌────────────┐ │ │
│ │ │Tier1│ │Tier2 │ │Self-Hosted │ │ │
│ │ │GPT- │ │Synth.│ │Ollama │ │ │
│ │ │OSS │ │.new │ │(fallback) │ │ │
│ │ │120B │ │1M ctx│ │ │ │ │
│ │ └─────┘ └──────┘ └────────────┘ │ │
│ └───────────────────────────────────────┘ │
└─────────────────────────────────────────────┘
```

### Tier 1: Primary — GPT-OSS 120B via Cerebras (Free)
- **Use for:** All standard agentic tasks — reasoning, tool use, code generation, planning
- **Rate limits:** 30 RPM, 14,400 RPD, 1M tokens/day
- **Context:** 131K — use context window management (see caching below)
- **Fallback within Tier 1:** GPT-OSS 120B via Groq (1,000 RPD, 8K TPM) or OpenRouter (20 RPM, 50 RPD) if Cerebras is down.

### Tier 2: Extended Context — Synthetic.new ($30/mo)
- **Use for:** Tasks requiring >131K context — large codebase analysis, long multi-turn agentic sessions, document Q&A over large corpora
- **Primary model:** MiniMax-M3 (1M ctx) for general tasks, Nemotron 3 Super 120B (1M ctx) for reasoning-heavy tasks
- **When to escalate:** Context estimate >100K tokens, or task explicitly requires long-context reasoning
- **Rate limits:** 500 req/5hr across all 9 models — ample for agentic use

### Tier 3: Self-Hosted — Ollama (Free, Unlimited)
- **Use for:** Ultimate fallback when all APIs are down or rate-limited
- **Recommended models:** Llama 3.1 8B (fast, lightweight), Qwen 3 32B (better reasoning)
- **Hardware:** Already runs on Scott's system
- **Cost:** Electricity only — no API costs, no rate limits
- **When to use:** API outage, rate limit exhaustion, offline operation, privacy-sensitive tasks

### Model Tiering by Task Type

| Task Type | Primary Model | Fallback | Context Strategy |
|-----------|--------------|----------|-----------------|
| Simple tool calls / routing | Llama 3.1 8B (Cerebras) | GPT-OSS 120B | Trim to last 5 turns |
| Code generation / review | GPT-OSS 120B | Nemotron 3 Super | Retain full file + diff |
| Multi-step reasoning | GPT-OSS 120B | Nemotron 3 Super | Summarize intermediate steps |
| Large codebase analysis | MiniMax-M3 (1M ctx) | Nemotron 3 Super | Full context |
| Long agentic sessions | MiniMax-M3 (1M ctx) | Nemotron 3 Super | Accumulate freely |
| Quick classification | Llama 3.1 8B | GPT-OSS 120B | Last message only |
| Privacy-sensitive | Ollama local | Ollama local | No data leaves device |

### Caching Strategy

1. **Prompt prefix caching:** Both Cerebras and Groq support automatic prompt caching — structure prompts with a stable system message + tool definitions prefix that gets cached across turns. This can reduce token costs by 50-80% for multi-turn conversations.

2. **Response caching:** Cache model responses for deterministic or low-temperature queries. Key candidates:
- Tool capability lookups ("what tools are available?")
- Configuration queries
- Repeated code analysis of unchanged files

3. **Context window management:**
- **Sliding window with summarization:** Keep last N turns verbatim, summarize older context. Use Llama 3.1 8B for cheap summarization.
- **Selective retention:** Retain tool outputs and code artifacts; drop conversational fillers.
- **Compression threshold:** When estimated token count exceeds 100K, switch to Tier 2 (1M context) instead of compressing.

4. **Embedding-based retrieval:** For very long agentic sessions, store tool outputs and reasoning steps in a local vector store (ChromaDB or sqlite-vec), retrieve relevant context by similarity rather than keeping everything in the prompt.

### When to Self-Host

Self-hosting makes sense when:
- **Privacy required:** Medical, financial, or personal data that shouldn't leave the device
- **API outage:** All three free providers are down simultaneously (rare but possible)
- **Rate limit exhaustion:** 14,400 RPD from Cerebras is usually sufficient, but burst usage could exhaust it
- **Offline operation:** No internet connectivity
- **Cost sensitivity over quality:** Free APIs are already $0, but self-hosting has zero dependency risk

**Recommended self-host stack:**
```bash
# Install Ollama (already on system)
ollama pull llama3.1:8b # ~4.7GB, fast on CPU
ollama pull qwen3:32b # ~19GB, needs GPU for good speed
ollama pull nomic-embed-text # For embedding-based retrieval
```

### Multi-Provider Resilience

```
Priority order for each model family:
GPT-OSS 120B: Cerebras → Groq → OpenRouter
Llama 3.1 8B: Cerebras → Groq → OpenRouter → Ollama (local)
Nemotron 3 Super: Synthetic.new → OpenRouter (free)
MiniMax-M3: Synthetic.new → (no free fallback)
Kimi K2.6: Synthetic.new → OpenRouter (free)
```

### Token Budget Allocation (Daily: 1M free tokens)

| Allocation | Tokens/Day | Purpose |
|-----------|-----------|---------|
| System prompt + tools | ~2K per turn × 100 turns = 200K | Cached prefix — actual cost much lower |
| Reasoning + generation | 500K | Main agentic work |
| Context retention | 200K | Sliding window history |
| Buffer | 100K | Unexpected spikes |

With Cerebras's 1M tokens/day free tier: ~100 turns/day at 10K tokens/turn. Supplement with OpenRouter free tier (50 RPD) and Groq (1,000 RPD for GPT-OSS 120B) for additional headroom.

---

## 7. Critical Gaps & Next Steps

### Gap 1: Quality Benchmarks (30% of composite score)
**Impact:** All 59 models scored 1/10 on the heaviest dimension. This inverts the ranking — models with good access dimensions dominate regardless of actual capability.

**Fix:** Manual lookup of LMSYS Arena rankings, MMLU-Pro scores, and HumanEval+ results for the top 10 models. Estimated time: 20 minutes. Expected result: Frontier models (GPT-5, o3, Gemini 3.5 Flash, DeepSeek R1/V3.2, GLM-5.2) vault from D-tier to S/A.

### Gap 2: Speed Benchmarks (20% of composite score)
**Impact:** All 59 models scored 1/10. No independent measurements of tokens/sec or TTFT.

**Fix:** Run 3-sample speed tests against the top 5 models using a standard prompt. Can be automated with a Python script. Expected result: Groq and Cerebras will dominate (hardware-accelerated); Synthetic.new and OpenRouter likely slower due to routing overhead.

### Gap 3: Agentic Tool-Use Evaluation
**Impact:** No dimension in the rubric specifically measures tool-use capability — critical for Hermes.

**Fix:** Add a Tool-Use dimension (e.g., BFCL — Berkeley Function Calling Leaderboard scores) or run a custom agentic benchmark against the top 5.

---

## 8. Final Recommendation

### Immediate (This Week)
1. **Configure Cerebras GPT-OSS 120B as primary** in Hermes config. Free, best rate limits, no credit card.
2. **Sign up for Synthetic.new $30/mo** as fallback for 1M-context tasks. 9 models including MiniMax-M3 and Nemotron 3 Super.
3. **Keep DeepSeek as backup** — already configured, strong reasoning, but Chinese provider risk.

### Short-Term (This Month)
4. **Manual benchmark lookup** — spend 20 minutes on LMSYS Arena to get Quality scores. This alone will invert the ranking and likely promote GLM-5.2, DeepSeek R1/V3.2, or Gemini 3.5 Flash to #1.
5. **Run speed benchmarks** — 3-sample test against Cerebras, Groq, and Synthetic.new endpoints.
6. **Test MiniMax-M3 1M context** with a real agentic workload — load an entire codebase and see if quality holds.

### Long-Term (Q3 2026)
7. **Monitor GitHub Models** — if they loosen token limits, GPT-5 and o3 become accessible for free.
8. **Evaluate self-hosted Qwen 3 32B** as a local fallback tier.
9. **Re-score** when benchmark data is available — the real ranking is almost certainly different from what access dimensions alone suggest.

### Monthly Cost
- **Minimum:** $0 (Cerebras free + OpenRouter free)
- **Recommended:** $30/mo (add Synthetic.new for 1M context)
- **Maximum useful:** $48/mo (add Z.ai GLM Coding Plan for specialized coding)

---

## Appendix: Data Sources

- **OpenRouter API** — live model list and pricing (queried June 17, 2026)
- **cheahjs/free-llm-api-resources** — canonical community tracker (GitHub)
- **LMSYS Chatbot Arena** — leaderboard data (lmarena.ai)
- **Provider docs:** Cerebras, Groq, Google AI Studio, Mistral, OpenRouter, Synthetic.new, Z.ai, DeepSeek, NVIDIA, Cohere, Cloudflare
- **Child task outputs:** t_96a803a9 (rubric), t_ee20f07c (providers), t_ecfffe88 (data), t_9c7034ea (scoring), t_1b1aaf2c (report)

---

*Report generated by Hermes Kanban root orchestrator t_96b2a89f. All child task findings synthesized. Workshop files from children were GC'd — metadata preserved in comments.*

# Free & Flat-Fee LLMs for AI Infrastructure — June 2026
## Top 5 Models | What You Get vs What You Don't Get

---

## Executive Summary

59 free and flat-fee LLMs from 44 providers were scored across 6 dimensions. **No model scored above C-tier** because the two heaviest dimensions — Quality (30%) and Speed (20%) — have zero benchmark data. This is a **lower-bound ranking** driven by access terms, not capability. The real winners (GPT-5, o3, Grok 3, Gemini 3.5 Flash, DeepSeek R1/V3.2, GLM-5.2) are almost certainly S/A-tier models trapped in D-tier by the data gap.

**Recommendation:** Cerebras GPT-OSS 120B (free, 30 RPM / 14,400 RPD, no credit card) as daily driver. Synthetic.new ($30/mo) for 1M-context tasks.

---

## Top 5 Ranking

| # | Model | Provider | Cost | Context | Rate Limits | Score |
|---|-------|----------|------|---------|-------------|-------|
| 1 | GPT-OSS 120B | Cerebras | $0 | 131K | 30 RPM / 14,400 RPD | 4.55 |
| 2 | MiniMax-M3 | Synthetic.new | $30/mo | 1M | 500 req/5hr | 4.25 |
| 3 | Llama 3.1 8B | Cerebras | $0 | 131K | 30 RPM / 14,400 RPD | 4.25 |
| 4 | Nemotron 3 Super 120B | Synthetic.new | $30/mo | 1M | 500 req/5hr | 4.15 |
| 5 | Kimi K2.6 | Synthetic.new | $30/mo | 262K | 500 req/5hr | 4.00 |

---

## What You Get vs What You Don't Get

### #1 GPT-OSS 120B (Cerebras) — Free

| What You Get | What You Don't Get |
|---|---|
| **Best free rate limits** — 30 RPM, 14,400 RPD, 1M tokens/day | Benchmark scores (MMLU-Pro, HumanEval+, MT-Bench) — unknown quality |
| **No credit card required** — zero friction signup | 1M context — capped at 131K tokens |
| **OpenAI-developed 120B model** — strong architecture heritage | Speed measurements — never independently benchmarked |
| **No training on your data** — privacy-preserving | A fallback if Cerebras has an outage (use Groq or OpenRouter mirror) |
| **Multi-provider availability** — also on Groq and OpenRouter | Tool-use capability scores (no BFCL data) |

### #2 MiniMax-M3 (Synthetic.new) — $30/mo

| What You Get | What You Don't Get |
|---|---|
| **Full 1M context window** — entire codebases, long agentic sessions fit without truncation | Benchmark scores — unknown reasoning/coding quality |
| **9-model bundle** — MiniMax-M3, Nemotron 3 Super, Kimi K2.6, GLM 5.1, and more for one price | Per-token pricing — it's flat-fee, no surprise bills, but also no per-token granularity |
| **$30/mo flat** — best value flat-fee subscription on the market | A US-based provider — MiniMax is a Chinese company |
| **500 requests per 5 hours** — ample for agentic workloads | A free tier — $30/mo is the minimum |
| **Embeddings included** — free and unlimited | An SLA or uptime guarantee |

### #3 Llama 3.1 8B (Cerebras) — Free

| What You Get | What You Don't Get |
|---|---|
| **Same generous limits as #1** — 30 RPM, 14,400 RPD, 1M tokens/day | 120B-level reasoning — 8B parameters ceiling on complex tasks |
| **Most widely available model** — Cerebras, Groq, OpenRouter, self-hostable | Benchmark scores — same data gap as every other model |
| **Self-hostable as ultimate fallback** — download via Ollama, zero dependency | 1M context — same 131K cap |
| **Meta ecosystem** — well-understood behavior, broad tool support | Competitive coding scores vs frontier models (likely much lower) |
| **Fast inference** on Groq's LPU hardware | Privacy on Groq — Groq's data policy differs from Cerebras |

### #4 Nemotron 3 Super 120B (Synthetic.new) — $30/mo

| What You Get | What You Don't Get |
|---|---|
| **NVIDIA's flagship open model** — 120B params with strong architecture reputation | Benchmark scores — no MMLU-Pro, HumanEval+, or MT-Bench data |
| **1M context window** — same ceiling as MiniMax-M3 | Dedicated rate limits — shares the 500 req/5hr quota with 8 other models |
| **Also free on OpenRouter** — available without the $30/mo subscription (but 20 RPM / 50 RPD limits) | The full OpenRouter free quota — 50 RPD is very tight for agentic use |
| **Part of $30/mo bundle** — no additional cost if you already have Synthetic.new | A long track record — NVIDIA is newer to the LLM space than OpenAI/Meta |
| **Open model** — no provider training on your prompts | Speed benchmarks — never measured independently |

### #5 Kimi K2.6 (Synthetic.new) — $30/mo

| What You Get | What You Don't Get |
|---|---|
| **262K context** — mid-range sweet spot between 131K and 1M | 1M context — MiniMax-M3 and Nemotron 3 Super offer 4× more |
| **Moonshot AI architecture** — strong Chinese AI lab reputation | A US-based provider — Beijing-based company |
| **Part of $30/mo bundle** — included with Synthetic.new subscription | Benchmark scores — no quality data available |
| **Also free on OpenRouter** — backup access path | Full rate limits on OpenRouter — 20 RPM / 50 RPD free tier |
| **262K fits most practical workloads** — good step-up from 131K | Competitive differentiation vs MiniMax-M3 — both in same bundle, MiniMax has 4× the context |

---

## Watch List — Frontier Models That Would Dominate If Scored

| Model | Provider | Context | Why It's Trapped in D-Tier |
|-------|----------|---------|---------------------------|
| GPT-5 | GitHub Models | 128K | Restrictive GitHub IO limits + no benchmark data |
| o3 | GitHub Models | 128K | Frontier reasoning, same GitHub constraints |
| Grok 3 | GitHub Models | 128K | Same restrictive GitHub tier |
| Gemini 3.5 Flash | Google AI Studio | 1M | 20 RPD free limit; trains on data outside EU |
| DeepSeek R1 | OpenRouter (free) | 1M | Chinese provider; 20 RPM / 50 RPD OpenRouter limits |
| DeepSeek V3.2 | OpenRouter (free) | 1M | Same as R1 |
| **GLM-5.2** | Z.ai ($18/mo) | 1M | **Only model with leaderboard evidence — LMSYS Arena agent rank ~10** |

---

## What You Get vs What You Don't Get — Provider Tiers

### Free Tier (Cerebras, Groq, OpenRouter)

| What You Get | What You Don't Get |
|---|---|
| $0 cost — truly free, no credit card for Cerebras | 1M context models (max 131K on Cerebras) |
| 14,400 requests/day on Cerebras — generous for agentic use | Frontier model access (GPT-5, o3 are on GitHub Models with tight limits) |
| Multi-provider redundancy — Cerebras + Groq + OpenRouter | Quality guarantees — no benchmark data for any free model |
| No training on data (Cerebras, most OpenRouter models) | Speed consistency — providers may throttle free users during peak |

### Flat-Fee Tier (Synthetic.new $30/mo)

| What You Get | What You Don't Get |
|---|---|
| 1M context models — MiniMax-M3, Nemotron 3 Super | Per-token billing — flat fee means you pay $30 even in light months |
| 9 models for one price — best bundle value | US-based provider — all models are Chinese (MiniMax, Moonshot, Zhipu, NVIDIA) |
| Unlimited embeddings — included at no extra cost | An SLA or uptime commitment |
| 500 requests per 5 hours — ~2,400 RPD | The absolute fastest inference (Groq's LPU hardware is faster) |
| No per-token anxiety — use as much as you want | Frontier models — GPT-5, o3, Grok 3 not available |

### Self-Hosted (Ollama, llama.cpp, vLLM)

| What You Get | What You Don't Get |
|---|---|
| Completely free — electricity only | Frontier model quality — best local models are Llama 3.1 8B / Qwen 3 32B |
| Unlimited rate — no RPM, RPD, or token caps | 1M context (most local models cap at 128K) |
| Total privacy — data never leaves your machine | GPU acceleration without a GPU — CPU-only is slow for 32B+ models |
| Offline operation — works without internet | Easy setup for non-technical users |
| No provider dependency — immune to API outages or pricing changes | Automatic model updates — you manage versions yourself |

---

## Monthly Cost Comparison

| Option | Cost | What You Get |
|--------|------|-------------|
| **Minimum** | $0 | Cerebras GPT-OSS 120B (daily driver) + OpenRouter free (22 models) |
| **Recommended** | $30/mo | Above + Synthetic.new (1M context, 9 models, unlimited embeddings) |
| **Maximum useful** | $48/mo | Above + Z.ai GLM Coding Plan (GLM-5.2, only model with proven leaderboard rank) |

---

## Next Actions (Priority Order)

1. **Fill benchmark gaps (20 min)** — Manual lookup of LMSYS Arena + HuggingFace for top 5 + 7 watch-list models. Will invert the entire ranking.
2. **Run speed benchmarks (2-3 hrs)** — 3-run protocol against Cerebras, Groq, and Synthetic.new endpoints.
3. **Test GLM-5.2** — Only model with real leaderboard evidence (LMSYS Arena agent rank ~10). Z.ai $18/mo.
4. **Configure Cerebras GPT-OSS 120B** as primary in Hermes config — free, best limits, no credit card.

---

*Report reformatted per new standard (June 17, 2026). Original data from Kanban task t_96b2a89f — 59 models scored across 6 dimensions.*