Llama3.3 70B Instruct
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
llama3.3-70b-instruct-fp8Released 6 Dec 2024 (Dec 2024)Pricing
List prices at Lambda AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.12 | $0.30 |
What it costs a month
At Lambda AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$58.50
- RAG over documents2,000 requests a day, 8K in / 0.6K out$68.40
- Coding agent1,000 requests a day, 40K in / 2K out$162
- Overnight batch20,000 requests a day, 4K in / 0.4K out$360
Where to run it
3 hosts serve Llama3.3 70B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Lambda AIInference llama3.3-70b-instruct-fp8 | $0.12 / $0.30 | llama3.3-70b-instruct-fp8 | |
GradientAICloud llama3.3-70b-instruct | $0.65 / $0.65 +294% vs headline | llama3.3-70b-instruct | |
Amazon BedrockCloud meta.llama3-3-70b-instruct-v1:0 | $0.72 / $0.72 +336% vs headline Retires 30 Mar 2027 | meta.llama3-3-70b-instruct-v1:0 | Retires 30 Mar 2027 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| us us.meta.llama3-3-70b-instruct-v1:0 | $0.72 / $0.72 +336% vs headline Retires 30 Mar 2027 | us.meta.llama3-3-70b-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 169.3 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
- 24% less
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 3% less
- 9% less
- 14% less
- 15% less
Model line
Newer and older versions, at each lab's own price.
- Dec 2024Llama 3.3 70B InstructLatestNot listed
- Dec 2024Llama3.3 70B InstructThis page$0.12 / $0.30
- Jul 2024Llama 3.1 70B Instruct$0.72 / $0.72
- Jul 2024Llama3.1 70B Instruct$0.12 / $0.30
- UndatedLlama 3 70B Instruct$0.51 / $0.74
- UndatedLlama3 70B Instruct$2.65 / $3.50
Call it
Using Lambda AI's API.
from litellm import completion
response = completion(
model="lambda_ai/llama3.3-70b-instruct-fp8",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama3.3 70B Instruct cost?
On Lambda AI, Llama3.3 70B Instruct costs $0.12 per million input tokens and $0.30 per million output tokens.
Which APIs offer Llama3.3 70B Instruct?
Llama3.3 70B Instruct runs on 3 APIs: Lambda AI, GradientAI and Amazon Bedrock.
What is Llama3.3 70B Instruct's context window?
131K tokens, with up to 131K tokens in one reply.
Is Llama3.3 70B Instruct being retired?
Amazon Bedrock retires it on 30 Mar 2027. 2 hosts keep serving it.
Is there a newer version of Llama3.3 70B Instruct?
Yes. Llama 3.3 70B Instruct is the newest model in this line, released on 6 Dec 2024.
What are cheaper alternatives to Llama3.3 70B Instruct?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (24% less) and Gemma 4 31B IT on W&B Inference (3% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Llama3.3 70B Instruct released?
Meta released it on 6 Dec 2024.
What is Llama3.3 70B Instruct's API model id?
Use llama3.3-70b-instruct-fp8 with Lambda AI. Other hosts use their own ids: llama3.3-70b-instruct on GradientAI, meta.llama3-3-70b-instruct-v1:0 on Amazon Bedrock.
Sources
Raw catalog entry for llama3.3-70b-instruct-fp8 on Lambda AI
{
"input_cost_per_token": 1.2e-7,
"litellm_provider": "lambda_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3e-7,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
}