Meta Llama 3 70B
meta-llama-3-70bPricing
List prices at Replicate, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.65 | $2.75 |
What it costs a month
At Replicate list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$401
- RAG over documents2,000 requests a day, 8K in / 0.6K out$411
- Coding agent1,000 requests a day, 40K in / 2K out$945
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,220
Where to run it
1 host serve Meta Llama 3 70B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ReplicateInference meta-llama-3-70b | $0.65 / $2.75 | meta-llama-3-70b |
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
- Open weights
- License: Llama Community LicenseRuntimes: 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 Replicate.
Smaller Meta models
- 89% less
- 83% less
Other frontier labs
- 28% less
- 61% less
- 83% less
- 83% less
Open-weight picks
- 26% less
- 27% less
- 31% less
- 33% less
Call it
Using Replicate's API.
from litellm import completion
response = completion(
model="replicate/meta-llama-3-70b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Meta Llama 3 70B cost?
On Replicate, Meta Llama 3 70B costs $0.65 per million input tokens and $2.75 per million output tokens.
Which APIs offer Meta Llama 3 70B?
Meta Llama 3 70B runs on 1 API: Replicate.
Is Meta Llama 3 70B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Meta Llama 3 70B?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (89% less), Gemini 3.5 Flash Lite on Google AI Studio (28% less), GPT-5.4 Nano on OpenAI (61% less) and Motif 3 on ai& (26% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Meta Llama 3 70B's API model id?
Use meta-llama-3-70b with Replicate.
Sources
Raw catalog entry for meta-llama-3-70b on Replicate
{
"input_cost_per_token": 6.5e-7,
"litellm_provider": "replicate",
"mode": "chat",
"output_cost_per_token": 0.00000275,
"source": "https://replicate.com/meta/meta-llama-3-70b"
}