Llama 3 70B Instruct
llama-3-70b-instructPricing
List prices at Novita AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.51 | $0.74 |
What it costs a month
At Novita AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$209
- RAG over documents2,000 requests a day, 8K in / 0.6K out$271
- Coding agent1,000 requests a day, 40K in / 2K out$656
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,402
Where to run it
3 hosts serve Llama 3 70B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Novita AIInference llama-3-70b-instruct | $0.51 / $0.74 | llama-3-70b-instruct | |
Fireworks AIInference llama-v3-70b-instruct | $0.90 / $0.90 +59% vs headline | llama-v3-70b-instruct | |
ReplicateInference llama-3-70b-instruct | $0.65 / $2.75 +107% vs headline | llama-3-70b-instruct |
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 Novita AI.
Smaller Meta models
- 78% less
- 65% less
Other frontier labs
- 19% less
- 65% less
- 65% less
- 54% less
Open-weight picks
- 7% less
- 15% less
- 16% less
- 21% less
Model line
Newer and older versions, at each lab's own price.
- Dec 2024Llama 3.3 70B InstructLatestNot listed
- Dec 2024Llama3.3 70B Instruct$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 InstructThis page$0.51 / $0.74
- UndatedLlama3 70B Instruct$2.65 / $3.50
Call it
Using Novita AI's API.
from litellm import completion
response = completion(
model="novita/llama-3-70b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 3 70B Instruct cost?
On Novita AI, Llama 3 70B Instruct costs $0.51 per million input tokens and $0.74 per million output tokens.
Which APIs offer Llama 3 70B Instruct?
Llama 3 70B Instruct runs on 3 APIs: Novita AI, Fireworks AI and Replicate.
What is Llama 3 70B Instruct's context window?
8K tokens, with up to 8K tokens in one reply.
Is Llama 3 70B Instruct being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama 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 Llama 3 70B Instruct?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (78% less), GPT-5.4 Nano on OpenAI (19% less), Claude Haiku 5.5 on Anthropic (65% less) and DeepSeek Flash on DeepSeek (7% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 3 70B Instruct's API model id?
Use llama-3-70b-instruct with Novita AI. Other hosts use their own ids: llama-v3-70b-instruct on Fireworks AI.
Sources
Raw catalog entry for llama-3-70b-instruct on Novita AI
{
"litellm_provider": "novita",
"mode": "chat",
"input_cost_per_token": 5.1e-7,
"output_cost_per_token": 7.4e-7,
"max_input_tokens": 8192,
"max_output_tokens": 8000,
"supports_tool_choice": true,
"supports_system_messages": true,
"supports_response_schema": true
}