70 billion dense parameters, 128k context, ~8s p95. The variant the auto-router lands on for most production reasoning — multi-hop cross-package exploit hypothesis, adversarial disproof, auto-fix PR with the full trace attached. Mid-high cost, deep enough for the chains that actually ship.
Reasons across up to ~12 call-graph hops and three or more package boundaries in a single pass. Cites the path, names the sanitiser that would have caught it, and proposes the patch.
Runs the disproof pass against the project's actual sanitiser config, allow-lists, and seccomp profile. Refutes its own hypothesis where the runtime would have stopped the chain, so the queue stays clean.
Drafts the patch, regenerates the unit test, and attaches the full HYPOTHESIS / CITED PATH / DISPROOF / PROPOSED PATCH trace to the PR. Reviewers approve the chain, not just the diff.
When nothing cheaper can carry the chain and nothing larger is required by tier policy, Griffin L is what the router chooses. Most production reasoning work lands here.
Honest list. The auto-router avoids these by design; if you call L directly here, expect to pay for compute you didn't need.
An 8s p95 is wrong for a save-keystroke loop. Use Griffin Lite for IDE-side cloud-burst reasoning where the latency budget is measured in hundreds of milliseconds.
Griffin L runs well on dedicated GPU but the deepest sovereign workloads — 12+ hop chains, agentic coordinated disclosure — should target Griffin Zero on a sovereign cluster.
L tops out at 128k usable context. For repositories where the relevant call graph cannot be cropped under 128k, route to Griffin Zero with 256k usable via retrieval gates.
| Parameters | 70B (dense) |
| Context window | 128k tokens |
| p95 latency | ~8s end-to-end |
| Active params per token | 70B (dense — all weights active) |
| Quantisation | FP16 default · INT8 available · FP8 in beta |
| Deployment tier(s) | Dedicated cluster · VPC-isolated · Sovereign |
| Minimum GPU | 2x H100 80GB |
| Recommended GPU | 4x H100 80GB or 8x A100 80GB |
| Memory footprint | ~140 GB at FP16 · ~80 GB at INT8 |
| Inference cost relative tier | Mid-high |
| Eval — exploit-hypothesis accuracy | 81% |
| Eval — adversarial prompt resistance | 98% |
| Eval — security-Q&A hallucination rate | 0.6% |
| Eval — top-5 candidate-path retention vs known CVE ground truth | 94% |
Sweep a service or repo for a target CWE class. L reasons each candidate, runs the disproof pass, and emits one PR per surviving finding with the full trace attached.
Trace a taint chain that crosses HTTP boundaries between two or three services. L holds the call graph across the boundary in context and cites which service contributed which hop.
Given a confirmed finding in a third-party dependency, L drafts the upstream issue, the suggested patch, and the disclosure thread before the human reviewer touches it.
L is the teacher model for the on-device distillation pipeline. Its traces are the supervision signal that lets a small Lino student reach Lite-class accuracy at IDE latency.
The auto-router will pick L for you on most production traffic. When you want to force the variant — for example during a campaign — pass it explicitly.
$ curl https://api.safeguard.sh/v1/reason \
-H 'Authorization: Bearer $SAFEGUARD_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "griffin-l",
"mode": "multi-hop-reasoning",
"project": "proj_a91f...",
"candidate": {
"cwe": "CWE-502",
"entry": "POST /api/import-config",
"sink": "ObjectMapper.readValue"
},
"context_budget": 128000,
"emit_trace": true,
"run_disproof": true
}'
{
"model": "griffin-l",
"finding_id": "find_4129",
"verdict": "exploitable",
"trace": {
"hypothesis": "CWE-502 via jackson-databind polymorphic typing",
"cited_path_hops": 6,
"disproof_result": "refutation_failed",
"proposed_patch": "constrained-reader + advisory bump"
},
"latency_ms": 7842,
"router_score": 0.83
}Most reasoning work in production lands in this band. Eagle scores the candidate on call-graph depth, sanitiser ambiguity, cross-package edges and sink severity. Scores in the 0.75 – 0.9 range route to Griffin L by default: the chain is deep enough that S/M would under-reason, but not so deep that Zero is required.
model: "griffin-l" explicitly.Pick a CWE class, point Griffin L at the service, and review the surviving PRs with their reasoning traces attached.