> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/docsfab/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/docsfab/_mcp/server. # Installed Execution Compositions in DocsFab > Look up the installed DocsFab model and serving-route records. To select one, follow Select an Installed Composition. To change its defaults, follow Override Model Settings. Look up the installed DocsFab model and serving-route records. To select one, follow [Select an Installed Composition](/docsfab/configure/installed-compositions). To change its defaults, follow [Override Model Settings](/docsfab/configure/override-model-settings). ## Installed Compositions An execution composition binds a model, serving route, authentication route, transport, harness, and exact adapter versions. List the package-installed records before selecting one: ```bash docsfab composition list docsfab composition list --json ``` The executable compositions use Pi as a common harness. The following table is the current installed registry, not a release catalog. | Composition ID | Serving route | Transport | Accepted credential sources | | --- | --- | --- | --- | | `nvidia-llama-3.3-nemotron-super-49b-v1.5-pi` | NVIDIA API Catalog | OpenAI-compatible chat completions | `DOCSFAB_NVIDIA_API_KEY` only; **retired** (provider end-of-life 2026-08-26; listed for provenance, refused for new runs) | | `nvidia-nemotron-3.5-lightning-30b-a3b-pi` | NVIDIA API Catalog | OpenAI-compatible chat completions | `DOCSFAB_NVIDIA_API_KEY` only | | `nvidia-nemotron-3-super-120b-a12b-pi` | NVIDIA API Catalog | OpenAI-compatible chat completions | `DOCSFAB_NVIDIA_API_KEY` only | | `nvidia-nemotron-3-ultra-550b-a55b-pi` | NVIDIA API Catalog | OpenAI-compatible chat completions | `DOCSFAB_NVIDIA_API_KEY` only | | `nvidia-inference-claude-sonnet-5-pi` | NVIDIA Inference Hub | OpenAI-compatible chat completions | `MODEL_API_KEY` only; no installed request policy (model is not reasoning-split) | | `nvidia-inference-claude-opus-5-pi` | NVIDIA Inference Hub | OpenAI-compatible chat completions | `MODEL_API_KEY` only; no installed request policy (model is not reasoning-split) | | `nvidia-inference-gpt-6-sol-pi` | NVIDIA Inference Hub | OpenAI-compatible chat completions | `MODEL_API_KEY` only; no installed request policy (probe verdict `harness-compatible`) | | `openai-gpt-5.6-sol-pi` | Direct OpenAI API | OpenAI Responses | Exactly one of `MODEL_API_KEY` or `OPENAI_API_KEY`; **retired** (superseded by operator decision 2026-09-28; listed for provenance, refused for new runs) | | `anthropic-claude-opus-4.7-pi` | Direct Anthropic API | Anthropic Messages | Exactly one of `MODEL_API_KEY` or `ANTHROPIC_API_KEY` | The supported first-use path configures a model and endpoint that you choose through [Install DocsFab](/docsfab/get-started/installation). DocsFab has no default model. No composition in this table is eligible for release, and each is an explicit execution path with its own credential contract. `nvidia-inference-gpt-6-sol-pi` is the composition that DocsFab's own live-model CI jobs bind. Its recorded evidence is diagnostic only: a bounded probe on September 25, 2026 returned the `harness-compatible` verdict, and diagnostic matrix runs on an operator route, not this sealed composition, scored 24 of 24. No acceptance, cost, or release qualification has run for this sealed composition. Select it with `docsfab setup --profile nvidia-inference-gpt-6-sol-pi`. Public installations omit private Inference Hub endpoint defaults. Set the provider's actual endpoint through `MODEL_BASE_URL` or `host.yaml active.writing.settings.baseUrl` before selecting one of these compositions. Keep an environment-supplied endpoint exported for later commands; `setup --profile` does not save it. Refer to [Select an Installed Composition](/docsfab/configure/installed-compositions) for the persistent configuration procedure. No profile YAML copy is required. `nvidia-inference-claude-sonnet-5-pi` remains installed as a secondary option on the same route and credential. It has known workflow gaps, tracked in issue #1428: provider stops during first-pass decomposition, evaluation steps that do not finish within the acceptance time window, and output truncation at its default 32,768-token output limit. DocsFab sends `thinking: {"type": "disabled"}` on every Claude Sonnet 5 request whose reasoning is off, through the `nvidia-inference-claude-sonnet-5-pi` composition's own route or any other endpoint. It sends `reasoning_effort` only when you set `reasoningEffort`, which turns reasoning on and removes the `thinking` field. With `reasoning` set to `true` and no effort, it sends neither field, so the model's default thinking applies; refer to [Change a Preset's Settings](/docsfab/configure/override-model-settings). On this route, Claude Sonnet 5 thinks by default when a request has no `thinking` field. That thinking counts against the per-request output limit but is not streamed, so one turn can spend its whole limit and return no text. The composition's model profile declares `reasoning: false`, and the field makes each request match that declaration. A probe of the route on September 28, 2026 measured the following behavior: - Without a `thinking` field, a request for a bare integer used all 16,384 output tokens it allowed and returned no visible text. - With `thinking` disabled, the same request used 371 output tokens and returned its answer. - `reasoning_effort: "none"` was accepted and had no effect. `reasoning_effort: "low"` and a request for 64,000 output tokens were refused at once with HTTP 408. No request that allowed more than 32,768 output tokens reached its limit, so the composition's default output limit stays at 32,768 tokens. A `maxOutputTokens` setting replaces it. Inference Hub Metadata reports a 128,000-token output limit for this model, but the route measurement takes precedence. The `nvidia-inference-claude-opus-5-pi` composition does not send the field, because its route behavior has not been measured. ### Inference Hub Token Limits The NVIDIA Inference Hub records seal the context, input, and output limits from each model's Inference Hub Metadata record, read on September 28, 2026. A route measurement that contradicts Metadata takes precedence. The following table lists the sealed limits. | Composition ID | Context and input tokens | Output tokens | Output source | | --- | --- | --- | --- | | `nvidia-inference-gpt-6-sol-pi` | 1,050,000 | 128,000 | Metadata; the route accepted 128,000 | | `nvidia-inference-claude-sonnet-5-pi` | 1,000,000 | 32,768 | Route measurement; Metadata reports 128,000 | | `nvidia-inference-claude-opus-5-pi` | 1,000,000 | 32,768 | Sonnet 5 route measurement on the same gateway; Metadata reports 128,000 | | `nvidia-inference-nemotron-3-super-v3-pi` | 1,048,576 | 32,768 | Metadata; not confirmed on the route | | `nvidia-inference-nemotron-3-ultra-pi` | 1,048,576 | 32,768 | Metadata; not confirmed on the route | | `nvidia-inference-qwen3-5-397b-a17b-pi` | 262,144 | 131,072 | Metadata; not confirmed on the route | | `nvidia-inference-deepseek-v4-pro-pi` | 1,048,576 | 384,000 | Metadata; not confirmed on the route | The package ceiling is the largest value across all records: 1,050,000 context and input tokens and 384,000 output tokens. These limits are each composition's defaults. A `contextWindow`, `maxInputTokens`, or `maxOutputTokens` setting replaces the composition's value, above or below it, and DocsFab records and warns about the difference. `nvidia-inference-deepseek-v4-pro-pi` binds the model ID `nvidia/deepseek-ai/deepseek-v4-pro` and carries no installed request policy. On September 28, 2026, a probe sent that model ID 2 prompts with a 128-token output limit and no tool prompt; both returned content without a reasoning split. The model ID has not been checked with a tool prompt or a longer answer. The former model ID, `azure/deepseek-ai/deepseek-v4-pro`, split its reasoning without a control on August 26, 2026 and returned HTTP 403 on September 28, 2026. The NVIDIA API Catalog records do not take their limits from Inference Hub Metadata, so their sealed limits are unchanged. Select one explicitly on `run` or `do` with `--composition`. Without it, the run takes the model-profile path: ```bash docsfab run review-documentation --repo /absolute/path/to/target-repo \ --composition nvidia-inference-gpt-6-sol-pi ``` A retired composition stays listed so that completed run records keep rebinding to it, but selecting it for a new run stops with `composition-retired` and names its successor. A retirement cites one of two reasons. `provider-end-of-life` quotes the provider's notice. `superseded-by-operator-decision` names the person, date, statement, and record of the decision; DocsFab uses it when the provider still serves the model. The direct OpenAI GPT-5.6 Sol composition is retired for the second reason: the provider notice that retired GPT-5.6 in NVIDIA's Codex environment does not cover the OpenAI API. The `composition-retired` refusal names only the reason code and the effective date. The rest of the retirement record stays in the installed registry as internal audit metadata. `docsfab composition list --json` shows only the retirement `reason`, `effectiveAt`, and optional `successorCompositionId`. The selected model ID, endpoint identity, transport, and credential family must match the installed composition. DocsFab rejects missing or ambiguous credential sources and does not fall back to another composition. Composition-execution writes stay local unless you pass `--draft-mr`. Composition-execution results permanently report `technicalApproval: not-established`, `roleQualification: not-established`, and `releaseEligible: false`. A run that names `--composition` can also use `--release-gate`, `--comment-mr`, and `--resume-from`. Without `--composition`, a run uses the composition that `host.yaml` names, or the configured model profile; it does not make a new approval or release claim. ## Moved Topic Links Earlier section bookmarks lead to the canonical topic below. Refer to [Override Model Settings in DocsFab](/docsfab/configure/override-model-settings). Refer to [Read-Loop Supervision in DocsFab](/docsfab/reference/status-and-configuration/read-loop-supervision#read-loop-supervision). Refer to [Model Setting Precedence in DocsFab](/docsfab/reference/status-and-configuration/model-settings#settings-you-can-change). Refer to [Model Setting Precedence in DocsFab](/docsfab/reference/status-and-configuration/model-settings#what-docsfab-records-and-shows). Refer to [Model Setting Precedence in DocsFab](/docsfab/reference/status-and-configuration/model-settings#what-still-stops-a-run). Refer to [Model Setting Precedence in DocsFab](/docsfab/reference/status-and-configuration/model-settings#which-value-wins).