Model information
Released
2024-12-06
Context window
128K
Max output
4.1K
Model parameters
71B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- llama-3.3-70b-instruct
- Knowledge cutoff
- 2023-12
- License
- llama3.3
- Aliases
- Llama-3.3-70B-Instruct
Resources
Capabilities
AttachmentsOpen weightStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| GreenPT | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $1.254/M · output $1.254/M | Yes | ||
| Nvidia | meta/llama-3.3-70b-instruct | custom | 128K | 4.1K | Tool callStructuredTemperature | - | input $0/M · output $0/M | Yes | ||
| LLM Gateway | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | AttachmentsTool callTemperature | - | input $0.13/M · output $0.4/M | Yes | ||
| Helicone | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $0.13/M · output $0.39/M | Yes | ||
| Regolo AI | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $0.6/M · output $2.7/M | Yes | ||
| Azure Cognitive Services | llama-3.3-70b-instruct | custom | 128K | 4.1K | Tool callTemperature | - | input $0.71/M · output $0.71/M | Yes | ||
| Scaleway | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | AttachmentsTool callTemperature | - | input $0.9/M · output $0.9/M | Yes | ||
| Azure | llama-3.3-70b-instruct | openai_responses | 128K | 4.1K | Tool callTemperature | - | input $0.71/M · output $0.71/M | Yes | ||
| Llama | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | AttachmentsTool callTemperature | - | input $0/M · output $0/M | Yes | ||
| Merge Gateway | meta/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $0.22/M · output $0.5/M cache read $0.11/M | Yes | ||
| Charm Hyper | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $0.513/M · output $1.045/M cache write $0.256/M | Yes | ||
| GitHub Models | meta/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | - | - | - | Yes | ||
| Cortecs | llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | ReasoningTool callTemperature | - | input $0.089/M · output $0.275/M | Yes | ||
| OpenRouter | meta-llama/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callStructuredTemperature | Hugging Face: meta-llama/Llama-3.3-70B-Instruct | input $0.13/M · output $0.4/M | Yes | ||
| NanoGPT | meta-llama/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callStructuredTemperature | - | input $0.05/M · output $0.23/M cache read $0.025/M | Yes | ||
| Kilo Gateway | meta-llama/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callStructuredTemperature | - | input $0.1/M · output $0.32/M | Yes | ||
| NovitaAI | meta-llama/llama-3.3-70b-instruct | openai_chat | 128K | 4.1K | Tool callTemperature | - | input $0.135/M · output $0.4/M | Yes | ||
| Meta | llama-3.3-70b-instruct | custom | 128K | 4.1K | - | - | - | Yes |