Update documentation with new models

.claude/skills/opengradient/SKILL.md

@@ -61,10 +61,10 @@ client.llm.ensure_opg_approval(opg_amount=5)
 
 | Provider   | Models |
 |------------|--------|
-| OpenAI     | `GPT_4_1_2025_04_14`, `GPT_4O`, `O4_MINI` |
-| Anthropic  | `CLAUDE_3_7_SONNET`, `CLAUDE_3_5_HAIKU`, `CLAUDE_4_0_SONNET` |
-| Google     | `GEMINI_2_5_FLASH`, `GEMINI_2_5_PRO`, `GEMINI_2_0_FLASH`, `GEMINI_2_5_FLASH_LITE` |
-| xAI        | `GROK_3_MINI_BETA`, `GROK_3_BETA`, `GROK_2_1212`, `GROK_4_1_FAST`, `GROK_4_1_FAST_NON_REASONING` |
+| OpenAI     | `GPT_4_1_2025_04_14`, `O4_MINI`, `GPT_5`, `GPT_5_MINI`, `GPT_5_2` |
+| Anthropic  | `CLAUDE_SONNET_4_5`, `CLAUDE_SONNET_4_6`, `CLAUDE_HAIKU_4_5`, `CLAUDE_OPUS_4_5`, `CLAUDE_OPUS_4_6` |
+| Google     | `GEMINI_2_5_FLASH`, `GEMINI_2_5_PRO`, `GEMINI_2_5_FLASH_LITE`, `GEMINI_3_PRO`, `GEMINI_3_FLASH` |
+| xAI        | `GROK_4`, `GROK_4_FAST`, `GROK_4_1_FAST`, `GROK_4_1_FAST_NON_REASONING` |
 
 ## Settlement Modes (`og.x402SettlementMode`)
 
@@ -117,7 +117,7 @@ tools = [{
 }]
 
 result = client.llm.chat(
-    model=og.TEE_LLM.GPT_4O,
+    model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Weather in NYC?"}],
     tools=tools,
     max_tokens=200,
@@ -138,7 +138,7 @@ messages = [
 
 for _ in range(max_iterations):
     result = client.llm.chat(
-        model=og.TEE_LLM.GPT_4O,
+        model=og.TEE_LLM.GPT_5,
         messages=messages,
         tools=tools,
         tool_choice="auto",

.claude/skills/opengradient/api-reference.md

@@ -106,25 +106,28 @@ Returned by `client.alpha.infer()`.
 
 ### OpenAI
 - `GPT_4_1_2025_04_14`
-- `GPT_4O`
 - `O4_MINI`
+- `GPT_5`
+- `GPT_5_MINI`
+- `GPT_5_2`
 
 ### Anthropic
-- `CLAUDE_3_7_SONNET`
-- `CLAUDE_3_5_HAIKU`
-- `CLAUDE_4_0_SONNET`
+- `CLAUDE_SONNET_4_5`
+- `CLAUDE_SONNET_4_6`
+- `CLAUDE_HAIKU_4_5`
+- `CLAUDE_OPUS_4_5`
+- `CLAUDE_OPUS_4_6`
 
 ### Google
 - `GEMINI_2_5_FLASH`
 - `GEMINI_2_5_PRO`
-- `GEMINI_2_0_FLASH`
 - `GEMINI_2_5_FLASH_LITE`
+- `GEMINI_3_PRO`
+- `GEMINI_3_FLASH`
 
 ### xAI (Grok)
-- `GROK_3_MINI_BETA`
-- `GROK_3_BETA`
-- `GROK_2_1212`
-- `GROK_2_VISION_LATEST`
+- `GROK_4`
+- `GROK_4_FAST`
 - `GROK_4_1_FAST`
 - `GROK_4_1_FAST_NON_REASONING`
 

Makefile

@@ -1,7 +1,7 @@
 # OpenGradient SDK Makefile
 
-# Default model for testing (override with: make chat MODEL=openai/gpt-4o)
-MODEL ?= anthropic/claude-3.7-sonnet
+# Default model for testing (override with: make chat MODEL=google/gemini-3-pro-preview)
+MODEL ?= google/gemini-3-pro-preview
 
 # ============================================================================
 # Development
@@ -67,24 +67,31 @@ infer:
 
 completion:
 	python -m opengradient.cli completion \
-		--model $(MODEL) --mode TEE \
+		--model $(MODEL) \
 		--prompt "Hello, how are you?" \
 		--max-tokens 50
 
 chat:
 	python -m opengradient.cli chat \
 		--model $(MODEL) \
 		--messages '[{"role":"user","content":"Tell me a fun fact"}]' \
-		--max-tokens 150
+		--max-tokens 350
 
 chat-stream:
 	python -m opengradient.cli chat \
 		--model $(MODEL) \
 		--messages '[{"role":"user","content":"Tell me a short story"}]' \
-		--max-tokens 250 \
+		--max-tokens 1250 \
 		--stream
 
 chat-tool:
+	python -m opengradient.cli chat \
+		--model $(MODEL) \
+		--messages '[{"role":"user","content":"What is the weather in Tokyo?"}]' \
+		--tools '[{"type":"function","function":{"name":"get_weather","description":"Get weather for a location","parameters":{"type":"object","properties":{"location":{"type":"string"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}]' \
+		--max-tokens 100
+
+chat-stream-tool:
 	python -m opengradient.cli chat \
 		--model $(MODEL) \
 		--messages '[{"role":"user","content":"What is the weather in Tokyo?"}]' \
@@ -93,4 +100,4 @@ chat-tool:
 		--stream
 
 .PHONY: install build publish check docs test utils_test client_test langchain_adapter_test opg_token_test integrationtest examples \
-	infer completion chat chat-stream chat-tool
+	infer completion chat chat-stream chat-tool chat-stream-tool

README.md

@@ -100,7 +100,7 @@ See [Payment Settlement](#payment-settlement) for details on settlement modes.
 OpenGradient provides secure, verifiable inference through Trusted Execution Environments. All supported models include cryptographic attestation verified by the OpenGradient network:
 ```python
 completion = client.llm.chat(
-    model=og.TEE_LLM.GPT_4O,
+    model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Hello!"}],
 )
 print(f"Response: {completion.chat_output['content']}")
@@ -112,7 +112,7 @@ print(f"Transaction hash: {completion.transaction_hash}")
 For real-time generation, enable streaming:
 ```python
 stream = client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_7_SONNET,
+    model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "Explain quantum computing"}],
     max_tokens=500,
     stream=True,
@@ -133,7 +133,7 @@ import opengradient as og
 
 llm = og.agents.langchain_adapter(
     private_key=os.environ.get("OG_PRIVATE_KEY"),
-    model_cid=og.TEE_LLM.GPT_4O,
+    model_cid=og.TEE_LLM.GPT_5,
 )
 
 @tool
@@ -154,25 +154,28 @@ The SDK provides access to models from multiple providers via the `og.TEE_LLM` e
 
 #### OpenAI
 - GPT-4.1 (2025-04-14)
-- GPT-4o
 - o4-mini
+- GPT-5
+- GPT-5 Mini
+- GPT-5.2
 
 #### Anthropic
-- Claude 3.7 Sonnet
-- Claude 3.5 Haiku
-- Claude 4.0 Sonnet
+- Claude Sonnet 4.5
+- Claude Sonnet 4.6
+- Claude Haiku 4.5
+- Claude Opus 4.5
+- Claude Opus 4.6
 
 #### Google
 - Gemini 2.5 Flash
 - Gemini 2.5 Pro
-- Gemini 2.0 Flash
 - Gemini 2.5 Flash Lite
+- Gemini 3 Pro
+- Gemini 3 Flash
 
 #### xAI
-- Grok 3 Beta
-- Grok 3 Mini Beta
-- Grok 2 (1212)
-- Grok 2 Vision
+- Grok 4
+- Grok 4 Fast
 - Grok 4.1 Fast (reasoning and non-reasoning)
 
 For a complete list, reference the `og.TEE_LLM` enum or consult the [API documentation](https://docs.opengradient.ai/api_reference/python_sdk/).
@@ -262,7 +265,7 @@ opengradient infer -m QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ \
 
 Run a chat completion:
 ```bash
-opengradient chat --model anthropic/claude-3.5-haiku \
+opengradient chat --model anthropic/claude-haiku-4-5 \
     --messages '[{"role":"user","content":"Hello"}]' \
     --max-tokens 100
 ```
@@ -297,7 +300,7 @@ OpenGradient supports multiple settlement modes through the x402 payment protoco
 Specify settlement mode in your requests:
 ```python
 result = client.llm.chat(
-    model=og.TEE_LLM.GPT_4O,
+    model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Hello"}],
     x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
 )

docs/CLAUDE_SDK_USERS.md

@@ -25,7 +25,7 @@ client = og.Client(
 
 # LLM Chat (TEE-verified with x402 payments)
 result = client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_5_HAIKU,
+    model=og.TEE_LLM.CLAUDE_HAIKU_4_5,
     messages=[{"role": "user", "content": "Hello!"}],
     max_tokens=100,
 )
@@ -108,25 +108,28 @@ All LLM models are TEE-verified. `og.LLM` and `og.TEE_LLM` contain the same mode
 ```python
 # OpenAI
 og.TEE_LLM.GPT_4_1_2025_04_14
-og.TEE_LLM.GPT_4O
 og.TEE_LLM.O4_MINI
+og.TEE_LLM.GPT_5
+og.TEE_LLM.GPT_5_MINI
+og.TEE_LLM.GPT_5_2
 
 # Anthropic
-og.TEE_LLM.CLAUDE_3_7_SONNET
-og.TEE_LLM.CLAUDE_3_5_HAIKU
-og.TEE_LLM.CLAUDE_4_0_SONNET
+og.TEE_LLM.CLAUDE_SONNET_4_5
+og.TEE_LLM.CLAUDE_SONNET_4_6
+og.TEE_LLM.CLAUDE_HAIKU_4_5
+og.TEE_LLM.CLAUDE_OPUS_4_5
+og.TEE_LLM.CLAUDE_OPUS_4_6
 
 # Google
 og.TEE_LLM.GEMINI_2_5_FLASH
 og.TEE_LLM.GEMINI_2_5_PRO
-og.TEE_LLM.GEMINI_2_0_FLASH
 og.TEE_LLM.GEMINI_2_5_FLASH_LITE
+og.TEE_LLM.GEMINI_3_PRO
+og.TEE_LLM.GEMINI_3_FLASH
 
 # xAI
-og.TEE_LLM.GROK_3_BETA
-og.TEE_LLM.GROK_3_MINI_BETA
-og.TEE_LLM.GROK_2_1212
-og.TEE_LLM.GROK_2_VISION_LATEST
+og.TEE_LLM.GROK_4
+og.TEE_LLM.GROK_4_FAST
 og.TEE_LLM.GROK_4_1_FAST
 og.TEE_LLM.GROK_4_1_FAST_NON_REASONING
 ```
@@ -137,7 +140,7 @@ All models are accessed through the OpenGradient TEE infrastructure with x402 pa
 
 ```python
 result = client.llm.chat(
-    model=og.TEE_LLM.GPT_4O,
+    model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Hello"}],
 )
 ```
@@ -163,7 +166,7 @@ tools = [{
 }]
 
 result = client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_7_SONNET,
+    model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "What's the weather in NYC?"}],
     tools=tools,
     tool_choice="auto",
@@ -178,7 +181,7 @@ if result.chat_output.get("tool_calls"):
 
 ```python
 stream = client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_7_SONNET,
+    model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "Tell me a story"}],
     stream=True,
 )
@@ -197,7 +200,7 @@ from langgraph.prebuilt import create_react_agent
 # Create LangChain-compatible LLM
 llm = og.agents.langchain_adapter(
     private_key=os.environ["OG_PRIVATE_KEY"],
-    model_cid=og.LLM.CLAUDE_3_7_SONNET,
+    model_cid=og.LLM.CLAUDE_SONNET_4_6,
     max_tokens=300,
 )
 

examples/README.md

@@ -169,7 +169,7 @@ LLM chat pattern:
 
 ```python
 completion = og_client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_5_HAIKU,
+    model=og.TEE_LLM.CLAUDE_HAIKU_4_5,
     messages=[{"role": "user", "content": "Your message"}],
 )
 print(f"Response: {completion.chat_output['content']}")

integrationtest/agent/test_agent.py

@@ -20,7 +20,7 @@ def setUp(self):
             raise ValueError("PRIVATE_KEY environment variable is not set")
 
         self.client = og.Client(private_key=private_key)
-        self.llm = OpenGradientChatModel(private_key=private_key, model_cid=LLM.CLAUDE_3_7_SONNET)
+        self.llm = OpenGradientChatModel(private_key=private_key, model_cid=LLM.CLAUDE_SONNET_4_6)
 
     def test_simple_completion(self):
         message = self.llm.invoke("say 'hello'. literally")

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opengradient"
-version = "0.7.4"
+version = "0.7.5"
 description = "Python SDK for OpenGradient decentralized model management & inference services"
 authors = [{name = "OpenGradient", email = "adam@vannalabs.ai"}]
 readme = "README.md"
@@ -27,7 +27,7 @@ dependencies = [
     "langchain>=0.3.7",
     "openai>=1.58.1",
     "pydantic>=2.9.2",
-    "og-test-v2-x402==0.0.9"
+    "og-test-v2-x402==0.0.11"
 ]
 
 [project.scripts]

requirements.txt

@@ -7,4 +7,4 @@ requests>=2.32.3
 langchain>=0.3.7
 openai>=1.58.1
 pydantic>=2.9.2
-og-test-v2-x402==0.0.9
+og-test-v2-x402==0.0.11

src/opengradient/__init__.py

@@ -24,15 +24,15 @@
 
 # Chat with an LLM (TEE-verified)
 response = client.llm.chat(
-    model=og.TEE_LLM.CLAUDE_3_5_HAIKU,
+    model=og.TEE_LLM.CLAUDE_HAIKU_4_5,
     messages=[{"role": "user", "content": "Hello!"}],
     max_tokens=200,
 )
 print(response.chat_output)
 
 # Stream a response
 for chunk in client.llm.chat(
-    model=og.TEE_LLM.GPT_4O,
+    model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Explain TEE in one paragraph."}],
     max_tokens=300,
     stream=True,
@@ -141,7 +141,7 @@ def init(
         import opengradient as og
         client = og.init(private_key="0x...")
         client.llm.ensure_opg_approval(opg_amount=5)
-        response = client.llm.chat(model=og.TEE_LLM.GPT_4O, messages=[...])
+        response = client.llm.chat(model=og.TEE_LLM.GPT_5, messages=[...])
     """
     global global_client
     global_client = Client(