diff --git a/README.md b/README.md
index c059ebc11..dd02ecf7d 100644
--- a/README.md
+++ b/README.md
@@ -121,7 +121,7 @@ def load_environment(dataset_name: str = 'gsm8k') -> vf.Environment:
     async def correct_answer(completion, answer) -> float:
         completion_ans = completion[-1]['content']
         return 1.0 if completion_ans == answer else 0.0
-    rubric = Rubric(funcs=[correct_answer])
+    rubric = vf.Rubric(funcs=[correct_answer])
     env = vf.SingleTurnEnv(dataset=dataset, rubric=rubric)
     return env
 ```
@@ -138,7 +138,7 @@ prime env install primeintellect/math-python
 
 To run a local evaluation with any OpenAI-compatible model, do:
 ```bash
-prime eval run my-env -m gpt-5-nano # run and save eval results locally
+prime eval run my-env -m openai/gpt-5-nano # run and save eval results locally
 ```
 Evaluations use [Prime Inference](https://docs.primeintellect.ai/inference/overview) by default; configure your own API endpoints in `./configs/endpoints.toml`.
 
@@ -159,17 +159,17 @@ prime eval run primeintellect/math-python
 
 ## Documentation
 
-**[Environments](environments.md)** — Create datasets, rubrics, and custom multi-turn interaction protocols.
+**[Environments](docs/environments.md)** — Create datasets, rubrics, and custom multi-turn interaction protocols.
 
-**[Evaluation](evaluation.md)** - Evaluate models using your environments.
+**[Evaluation](docs/evaluation.md)** - Evaluate models using your environments.
 
-**[Training](training.md)** — Train models in your environments with reinforcement learning.
+**[Training](docs/training.md)** — Train models in your environments with reinforcement learning.
 
-**[Development](development.md)** — Contributing to verifiers
+**[Development](docs/development.md)** — Contributing to verifiers
 
-**[API Reference](reference.md)** — Understanding the API and data structures
+**[API Reference](docs/reference.md)** — Understanding the API and data structures
 
-**[FAQs](faqs.md)** - Other frequently asked questions.
+**[FAQs](docs/faqs.md)** - Other frequently asked questions.
 
 
 ## Citation
diff --git a/docs/development.md b/docs/development.md
index 311d96934..1d7723363 100644
--- a/docs/development.md
+++ b/docs/development.md
@@ -229,7 +229,7 @@ prime env init my-environment
 prime env install my-environment
 
 # Test your environment
-prime eval run my-environment -m gpt-4.1-mini -n 5
+prime eval run my-environment -m openai/gpt-4.1-mini -n 5
 ```
 
 ### Environment Module Structure
@@ -285,10 +285,10 @@ uv run ty check verifiers               # Type check (matches CI Ty target)
 uv run pre-commit run --all-files     # Run all pre-commit hooks
 
 # Environment tools
-prime env init new-env                       # Create environment
-prime env install new-env                    # Install environment
-prime eval run new-env -m gpt-4.1-mini -n 5  # Test environment
-prime eval tui                               # Browse eval results
+prime env init new-env                              # Create environment
+prime env install new-env                           # Install environment
+prime eval run new-env -m openai/gpt-4.1-mini -n 5  # Test environment
+prime eval tui                                      # Browse eval results
 ```
 
 ### CLI Tools
diff --git a/docs/evaluation.md b/docs/evaluation.md
index f9db26f6f..c5b88bc7e 100644
--- a/docs/evaluation.md
+++ b/docs/evaluation.md
@@ -25,7 +25,7 @@ Environments must be installed as Python packages before evaluation. From a loca
 
 ```bash
 prime env install my-env           # installs ./environments/my_env as a package
-prime eval run my-env -m gpt-4.1-mini -n 10
+prime eval run my-env -m openai/gpt-4.1-mini -n 10
 ```
 
 `prime eval` imports the environment module using Python's import system, calls its `load_environment()` function, runs 5 examples with 3 rollouts each (the default), scores them using the environment's rubric, and prints aggregate metrics.
diff --git a/docs/faqs.md b/docs/faqs.md
index 051cd7736..f085b72b2 100644
--- a/docs/faqs.md
+++ b/docs/faqs.md
@@ -7,7 +7,7 @@
 Use `prime eval run` with a small sample:
 
 ```bash
-prime eval run my-environment -m gpt-4.1-mini -n 5
+prime eval run my-environment -m openai/gpt-4.1-mini -n 5
 ```
 
 The `-s` flag prints sample outputs so you can see what's happening.
@@ -32,7 +32,7 @@ vf.print_prompt_completions_sample(outputs, n=3)
 Set the `VF_LOG_LEVEL` environment variable:
 
 ```bash
-VF_LOG_LEVEL=DEBUG prime eval run my-environment -m gpt-4.1-mini -n 5
+VF_LOG_LEVEL=DEBUG prime eval run my-environment -m openai/gpt-4.1-mini -n 5
 ```
 
 ## Environments
diff --git a/docs/overview.md b/docs/overview.md
index 3eced9817..6d048326c 100644
--- a/docs/overview.md
+++ b/docs/overview.md
@@ -71,7 +71,7 @@ def load_environment(dataset_name: str = 'gsm8k') -> vf.Environment:
     async def correct_answer(completion, answer) -> float:
         completion_ans = completion[-1]['content']
         return 1.0 if completion_ans == answer else 0.0
-    rubric = Rubric(funcs=[correct_answer])
+    rubric = vf.Rubric(funcs=[correct_answer])
     env = vf.SingleTurnEnv(dataset=dataset, rubric=rubric)
     return env
 ```
@@ -88,7 +88,7 @@ prime env install primeintellect/math-python
 
 To run a local evaluation with any OpenAI-compatible model, do:
 ```bash
-prime eval run my-env -m gpt-5-nano # run and save eval results locally
+prime eval run my-env -m openai/gpt-5-nano # run and save eval results locally
 ```
 Evaluations use [Prime Inference](https://docs.primeintellect.ai/inference/overview) by default; configure your own API endpoints in `./configs/endpoints.toml`.
 
diff --git a/skills/browse-environments/SKILL.md b/skills/browse-environments/SKILL.md
index 1e27cc0c3..b5a47cf5b 100644
--- a/skills/browse-environments/SKILL.md
+++ b/skills/browse-environments/SKILL.md
@@ -48,7 +48,7 @@ For each candidate, collect:
 2. Use install + smoke eval to validate real usability:
 ```bash
 prime env install owner/name
-prime eval run name -m gpt-4.1-mini -n 5
+prime eval run name -m openai/gpt-4.1-mini -n 5
 ```
 3. For examples in the verifiers repository, use repo install path when available:
 ```bash
diff --git a/skills/create-environments/SKILL.md b/skills/create-environments/SKILL.md
index 22b575450..058955ecf 100644
--- a/skills/create-environments/SKILL.md
+++ b/skills/create-environments/SKILL.md
@@ -14,7 +14,7 @@ Build production-quality verifiers environments that work immediately in the Pri
 ```bash
 prime env init my-env
 prime env install my-env
-prime eval run my-env -m gpt-4.1-mini -n 5
+prime eval run my-env -m openai/gpt-4.1-mini -n 5
 ```
 3. Prefer an existing environment as a starting point when possible:
 ```bash
@@ -75,12 +75,12 @@ prime env pull owner/name -t ./tmp-env
 Run these before claiming completion:
 ```bash
 prime env install my-env
-prime eval run my-env -m gpt-4.1-mini -n 5
-prime eval run my-env -m gpt-4.1-mini -n 50 -r 1 -s
+prime eval run my-env -m openai/gpt-4.1-mini -n 5
+prime eval run my-env -m openai/gpt-4.1-mini -n 50 -r 1 -s
 ```
 If multi-turn or tool-heavy, also run with higher rollouts:
 ```bash
-prime eval run my-env -m gpt-4.1-mini -n 30 -r 3 -s
+prime eval run my-env -m openai/gpt-4.1-mini -n 30 -r 3 -s
 ```
 
 ## Publish Gate Before Large Evals Or Training
@@ -96,7 +96,7 @@ prime env push --path ./environments/my_env --visibility PRIVATE
 ```
 4. For hosted or large-scale workflows, prefer running with the Hub slug after push:
 ```bash
-prime eval run owner/my-env -m gpt-4.1-mini -n 200 -r 3 -s
+prime eval run owner/my-env -m openai/gpt-4.1-mini -n 200 -r 3 -s
 ```
 
 ## Deliverable Format
diff --git a/skills/evaluate-environments/SKILL.md b/skills/evaluate-environments/SKILL.md
index ea38e50f9..08a8ee54c 100644
--- a/skills/evaluate-environments/SKILL.md
+++ b/skills/evaluate-environments/SKILL.md
@@ -11,15 +11,15 @@ Run reliable environment evaluations and produce actionable summaries, not raw l
 ## Core Loop
 1. Run a smoke evaluation first (do not require pre-install):
 ```bash
-prime eval run my-env -m gpt-4.1-mini -n 5
+prime eval run my-env -m openai/gpt-4.1-mini -n 5
 ```
 2. Use owner/env slug directly when evaluating Hub environments:
 ```bash
-prime eval run owner/my-env -m gpt-4.1-mini -n 5
+prime eval run owner/my-env -m openai/gpt-4.1-mini -n 5
 ```
 3. Scale only after smoke pass:
 ```bash
-prime eval run owner/my-env -m gpt-4.1-mini -n 200 -r 3 -s
+prime eval run owner/my-env -m openai/gpt-4.1-mini -n 200 -r 3 -s
 ```
 4. Treat ownerless env ids as local-first. If not found locally, rely on Prime resolution for your remote env where applicable.
 
@@ -57,7 +57,7 @@ prime env push --path ./environments/my_env --visibility PRIVATE
 ```
 4. For hosted eval workflows, prefer running large jobs against the Hub slug:
 ```bash
-prime eval run owner/my-env -m gpt-4.1-mini -n 200 -r 3 -s
+prime eval run owner/my-env -m openai/gpt-4.1-mini -n 200 -r 3 -s
 ```
 
 ## Prefer Config-Driven Evals Beyond Smoke Tests
diff --git a/verifiers/scripts/init.py b/verifiers/scripts/init.py
index a86e34866..48ca9d791 100644
--- a/verifiers/scripts/init.py
+++ b/verifiers/scripts/init.py
@@ -34,7 +34,7 @@
 
 ```bash
 prime eval run {env_id_dash} \
-  -m gpt-4.1-mini \
+  -m openai/gpt-4.1-mini \
   -n 20 -r 3 -t 1024 -T 0.7 \
   -a '{{"key": "value"}}'  # env-specific args as JSON
 ```