Identity
- Status
- active
- Developer ID
meta-llama/Llama-3.1-8B- Released
- Jul 23, 2024
- Version
- Llama-3.1-8B
- License
- llama3.1
MetaLlama 3.1 8B
Llama-3.1-8B is an open-weight language model published by Meta.
- Token context
- 131K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Jul 23, 2024
Providers & Pricing
1 current hosted offerings
No Directly Sourced Provider Price Yet
API pricing is provider-specific and stays unknown until a serving provider publishes an exact offering for this model version.
At a Glance
Model Facts
Capacity
- Token context
- 131K tokens
- Maximum output
- Unknown
- Total parameters
- 8B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- No
- Tool calling
- No
- Capabilities
- generation
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesmeta-llama/Llama-3.1-8B, meta-llama/Llama-3.1-8B
Explicit Unknowns
- Maximum output
- Knowledge cutoff
- Provider pricing
Primary Evidence
Sources and Observation Date
meta-llama/Llama-3.1-8B developer model repositoryMeta · observed Aug 28, 2026meta-llama/Llama-3.1-8B Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026meta-llama/Llama-3.1-8B immutable Hub API metadataMeta · observed Aug 28, 2026meta-llama/Llama-3.1-8B README.md at d04e592bb4f6Meta · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Llama 3.1 8BMeta | vs |  Bolmo 7BAi2 | cross-developer peerstext |
Llama 3.1 8BMeta | vs | cross-developer peerstext | |
Llama 3.1 8BMeta | vs | cross-developer peerstext | |
Llama 3.1 8BMeta | vs | cross-developer peerstext | |
Llama 3.1 8BMeta | vs | Llama 3.1 405BMeta | family variantstext |
Llama 3.1 8BMeta | vs | Llama 3.1 70BMeta | family variantstext |
Llama 3.1 8BMeta | vs | family variantstext | |
Llama 3.1 8BMeta | vs | family variantstext | |
Llama 3.1 8BMeta | vs |  Phi-4 Mini InstructMicrosoft | cross-developer peerstext |
Llama 3.1 8BMeta | vs | Phi-4 Mini ReasoningMicrosoft | cross-developer peerstext |
Llama 3.1 8BMeta | vs |  Codestral 22B v0.1Mistral AI | cross-developer peerstext |
Llama 3.1 8BMeta | vs | cross-developer peerstext |
Questions
Llama 3.1 8B FAQs
What is Llama 3.1 8B?+
Llama-3.1-8B is an open-weight language model published by Meta. It is developed by Meta and its current sourced lifecycle status is active.
What inputs and outputs does Llama 3.1 8B support?+
Llama 3.1 8B's current record lists Text as input and Text as output.
How much context does Llama 3.1 8B support?+
The current record lists a 131K-token context window and does not report a maximum output length.
Is Llama 3.1 8B available through an API?+
Llama 3.1 8B is marked as API-available. The directly sourced provider records currently include Hugging Face.
How large is Llama 3.1 8B?+
The current record lists 8B total parameters and an unknown active parameter count. Its architecture is LlamaForCausalLM.
What capabilities and tasks does Llama 3.1 8B support?+
Llama 3.1 8B's recorded capabilities are generation. Its supported tasks are text.
How much does Llama 3.1 8B cost through an API?+
No directly sourced token price is currently attached to Llama 3.1 8B. Missing prices remain unknown rather than being inferred from another model or provider.
Can Llama 3.1 8B be self-hosted?+
Llama 3.1 8B is an open-weight model. Self-hosting is supported, and the recorded license is llama3.1.
Does Llama 3.1 8B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are meta-llama/Llama-3.1-8B.
Which models can Llama 3.1 8B be compared with?+
The current compatible peer set includes Bolmo 7B, Granite 4.1 8B, Granite 4.2 8B, Granite Guardian 4.1 8B, and Llama 3.1 405B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →