Llama3.1 8B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.
llama3.1-8b-instructReleased 23 Jul 2024 (Jul 2024)Pricing
List prices at Lambda AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.025 | $0.04 |
What it costs a month
At Lambda AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$10.50
- RAG over documents2,000 requests a day, 8K in / 0.6K out$13.44
- Coding agent1,000 requests a day, 40K in / 2K out$32.40
- Overnight batch20,000 requests a day, 4K in / 0.4K out$69.60
Where to run it
2 hosts serve Llama3.1 8B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Lambda AIInference llama3.1-8b-instruct | $0.025 / $0.04 | llama3.1-8b-instruct | |
Amazon BedrockCloud meta.llama3-1-8b-instruct-v1:0 | $0.22 / $0.22 +665% vs headline Retires 30 Mar 2027 | meta.llama3-1-8b-instruct-v1:0 | Retires 30 Mar 2027 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| us us.meta.llama3-1-8b-instruct-v1:0 | $0.22 / $0.22 +665% vs headline Retires 30 Mar 2027 | us.meta.llama3-1-8b-instruct-v1:0 | Retires 30 Mar 2027 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Parallel tool calls
- Open weights
- License: Llama Community LicenseRuns in about 19.3 GB of GPU memoryRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Lambda AI.
Smaller Meta models
No cheaper Meta model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 1% less
- 13% less
- 30% less
Model line
Newer and older versions, at each lab's own price.
- UndatedLlama 3.3 8B InstructLatestNot listed
- Jul 2024Llama 3.1 8B Instruct$0.02 / $0.05
- Jul 2024Llama3.1 8B InstructThis page$0.025 / $0.04
- UndatedLlama 3 8B Instruct$0.04 / $0.04
- UndatedLlama3 8B Instruct$0.30 / $0.60
Call it
Using Lambda AI's API.
from litellm import completion
response = completion(
model="lambda_ai/llama3.1-8b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama3.1 8B Instruct cost?
On Lambda AI, Llama3.1 8B Instruct costs $0.025 per million input tokens and $0.04 per million output tokens.
Which APIs offer Llama3.1 8B Instruct?
Llama3.1 8B Instruct runs on 2 APIs: Lambda AI and Amazon Bedrock.
What is Llama3.1 8B Instruct's context window?
131K tokens, with up to 131K tokens in one reply.
Is Llama3.1 8B Instruct being retired?
Amazon Bedrock retires it on 30 Mar 2027. 1 host keeps serving it.
Is there a newer version of Llama3.1 8B Instruct?
Yes. Llama 3.3 8B Instruct is the newest model in this line.
What are cheaper alternatives to Llama3.1 8B Instruct?
Models that cost less and keep most of what it can do: gpt-oss-20b on Darkbloom (1% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Llama3.1 8B Instruct released?
Meta released it on 23 Jul 2024.
What is Llama3.1 8B Instruct's API model id?
Use llama3.1-8b-instruct with Lambda AI. Other hosts use their own ids: meta.llama3-1-8b-instruct-v1:0 on Amazon Bedrock.
Sources
Raw catalog entry for llama3.1-8b-instruct on Lambda AI
{
"input_cost_per_token": 2.5e-8,
"litellm_provider": "lambda_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4e-8,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
}