diff --git a/docs/my-website/docs/providers/deepinfra.md b/docs/my-website/docs/providers/deepinfra.md index dad7f5d2cd..3c6506308c 100644 --- a/docs/my-website/docs/providers/deepinfra.md +++ b/docs/my-website/docs/providers/deepinfra.md @@ -1,5 +1,12 @@ # DeepInfra https://deepinfra.com/ + +## API Key +```python +# env variable +os.environ['DEEPINFRA_API_KEY'] +``` + ## Sample Usage ```python from litellm import completion @@ -29,10 +36,15 @@ for chunk in response: ``` ## Chat Models -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------|-------------------------| -| meta-llama/Llama-2-70b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-70b-chat-hf", messages)` | `os.environ['DEEPINFRA_API_KEY']` | -| meta-llama/Llama-2-7b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-7b-chat-hf", messages)` | `os.environ['DEEPINFRA_API_KEY']` | -| codellama/CodeLlama-34b-Instruct-hf | `completion(model="deepinfra/codellama/CodeLlama-34b-Instruct-hf", messages)` | `os.environ['DEEPINFRA_API_KEY']` | +| Model Name | Function Call | +|------------------|--------------------------------------| +| meta-llama/Llama-2-70b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-70b-chat-hf", messages)` | +| meta-llama/Llama-2-7b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-7b-chat-hf", messages)` | +| meta-llama/Llama-2-13b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-13b-chat-hf", messages)` | +| codellama/CodeLlama-34b-Instruct-hf | `completion(model="deepinfra/codellama/CodeLlama-34b-Instruct-hf", messages)` | +| mistralai/Mistral-7B-Instruct-v0.1 | `completion(model="deepinfra/mistralai/Mistral-7B-Instruct-v0.1", messages)` | +| jondurbin/airoboros-l2-70b-gpt4-1.4.1 | `completion(model="deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1", messages)` | + + diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 35fde6c0e2..4782021d0b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -570,5 +570,47 @@ "output_cost_per_token": 0.0, "litellm_provider": "ollama", "mode": "completion" - } + }, + "deepinfra/meta-llama/Llama-2-70b-chat-hf": { + "max_tokens": 6144, + "input_cost_per_token": 0.000001875, + "output_cost_per_token": 0.000001875, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "deepinfra/codellama/CodeLlama-34b-Instruct-hf": { + "max_tokens": 4096, + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.0000006, + "litellm_provider": "deepinfra", + "mode": "chat" + }, + "deepinfra/meta-llama/Llama-2-13b-chat-hf": { + "max_tokens": 4096, + "input_cost_per_token": 0.00000035, + "output_cost_per_token": 0.00000035, + "litellm_provider": "deepinfra", + "mode": "chat" + }, + "deepinfra/meta-llama/Llama-2-7b-chat-hf": { + "max_tokens": 4096, + "input_cost_per_token": 0.0000002, + "output_cost_per_token": 0.0000002, + "litellm_provider": "deepinfra", + "mode": "chat" + }, + "deepinfra/mistralai/Mistral-7B-Instruct-v0.1": { + "max_tokens": 4096, + "input_cost_per_token": 0.0000002, + "output_cost_per_token": 0.0000002, + "litellm_provider": "deepinfra", + "mode": "chat" + }, + "deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1": { + "max_tokens": 4096, + "input_cost_per_token": 0.0000007, + "output_cost_per_token": 0.00000095, + "litellm_provider": "deepinfra", + "mode": "chat" + } }