The SDK automatically detects the provider based on the model name. Below is the complete list of supported models.
The Python SDK uses LiteLLM for provider abstraction. All models supported by LiteLLM are available. The list below covers the models with built-in provider detection.
OpenAI
GPT-4o Series
| Model | Description |
|---|
gpt-4o | Latest GPT-4o model |
gpt-4o-2024-05-13 | GPT-4o snapshot |
gpt-4o-2024-08-06 | GPT-4o snapshot |
gpt-4o-2024-11-20 | GPT-4o snapshot |
gpt-4o-mini | Smaller, faster GPT-4o |
gpt-4o-mini-2024-07-18 | GPT-4o mini snapshot |
chatgpt-4o-latest | ChatGPT Plus model |
GPT-4.1 Series
| Model | Description |
|---|
gpt-4.1 | Latest GPT-4.1 model |
gpt-4.1-2025-04-14 | GPT-4.1 snapshot |
gpt-4.1-mini | Smaller GPT-4.1 |
gpt-4.1-mini-2025-04-14 | Mini snapshot |
gpt-4.1-nano | Smallest GPT-4.1 |
gpt-4.1-nano-2025-04-14 | Nano snapshot |
GPT-4 Series
| Model | Description |
|---|
gpt-4 | GPT-4 base model |
gpt-4-turbo | Faster GPT-4 |
gpt-4-turbo-2024-04-09 | Turbo snapshot |
gpt-4-turbo-preview | Preview version |
GPT-5 Series
| Model | Description |
|---|
gpt-5 | GPT-5 base model |
gpt-5-2025-08-07 | GPT-5 snapshot |
gpt-5-mini | Smaller GPT-5 |
gpt-5-pro | Professional tier |
GPT-3.5 Series
| Model | Description |
|---|
gpt-3.5-turbo | Fast, cost-effective |
gpt-3.5-turbo-0125 | January 2024 |
gpt-3.5-turbo-16k | Extended context |
Reasoning Models (o-series)
| Model | Description |
|---|
o1 | Reasoning model |
o1-pro | Professional o1 |
o3 | Latest reasoning |
o3-mini | Smaller o3 |
o4-mini | o4 mini model |
Anthropic
Claude 4 Series
| Model | Description |
|---|
claude-sonnet-4-20250514 | Claude 4 Sonnet |
claude-opus-4-20250514 | Claude 4 Opus |
Claude 4.5 Series
| Model | Description |
|---|
claude-sonnet-4-5 | Claude 4.5 Sonnet |
claude-opus-4-5 | Claude 4.5 Opus |
claude-haiku-4-5 | Claude 4.5 Haiku |
Claude 4.1 Series
| Model | Description |
|---|
claude-opus-4-1 | Claude 4.1 Opus |
Claude 3 Series
| Model | Description |
|---|
claude-3-opus-20240229 | Claude 3 Opus |
claude-3-haiku-20240307 | Claude 3 Haiku |
claude-3-7-sonnet-20250219 | Claude 3.7 Sonnet |
Google
Gemini 2.0 Series
| Model | Description |
|---|
gemini-2.0-flash | Fast Gemini 2.0 |
gemini-2.0-flash-001 | Flash snapshot |
gemini-2.0-flash-exp | Experimental |
gemini-2.0-flash-lite | Lightweight |
Gemini 2.5 Series
| Model | Description |
|---|
gemini-2.5-flash | Gemini 2.5 Flash |
gemini-2.5-flash-lite | Lightweight 2.5 |
gemini-2.5-pro | Gemini 2.5 Pro |
Gemini 3 Series
| Model | Description |
|---|
gemini-3-pro-preview | Gemini 3 Pro preview |
gemini-3-flash-preview | Gemini 3 Flash preview |
Amazon Bedrock
Bedrock hosts models from multiple vendors. Use the full Bedrock model ID. See the Bedrock page for setup and usage details.
Amazon Nova
| Model | Description |
|---|
amazon.nova-micro-v1:0 | Amazon Nova Micro |
amazon.nova-lite-v1:0 | Amazon Nova Lite |
amazon.nova-pro-v1:0 | Amazon Nova Pro |
Anthropic Claude (via Bedrock)
| Model | Description |
|---|
anthropic.claude-haiku-4-5-20251001-v1:0 | Claude 4.5 Haiku |
anthropic.claude-sonnet-4-20250514-v1:0 | Claude 4 Sonnet |
anthropic.claude-sonnet-4-5-20250929-v1:0 | Claude 4.5 Sonnet |
anthropic.claude-opus-4-5-20251101-v1:0 | Claude 4.5 Opus |
anthropic.claude-opus-4-6-v1 | Claude 4.6 Opus |
Mistral (via Bedrock)
| Model | Description |
|---|
mistral.pixtral-large-2502-v1:0 | Pixtral Large |
Using Custom Models
For models not in the built-in list (fine-tuned, preview, or new releases), specify the provider explicitly:
# Fine-tuned OpenAI model
result = client.run_local(
model="ft:gpt-4o:my-org:custom:abc123",
provider="openai",
messages=[{"role": "user", "content": "Hello!"}],
)
# New Anthropic model not yet in the list
result = client.run_local(
model="claude-5-opus-20260101",
provider="anthropic",
messages=[{"role": "user", "content": "Hello!"}],
)
When using custom models, always specify the provider parameter to ensure the correct provider is used.
