impulse

Llama 3.1 70B Instruct

Open weights

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.

API id meta.llama-3.1-70b-instructReleased 23 Jul 2024 (Jul 2024)
Input / 1M
$0.72
at Oracle OCI
Output / 1M
$0.72
at Oracle OCI
Context window
128K
tokens
Max output
4K
tokens per reply
Hosts
5
5 listings
Released
Jul 2024
23 Jul 2024

Pricing

List prices at Oracle OCI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.72$0.72

What it costs a month

At Oracle OCI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$270
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$372
  • Coding agent1,000 requests a day, 40K in / 2K out$907
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,901
Use your own numbers

Where to run it

5 hosts serve Llama 3.1 70B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
meta.llama-3.1-70b-instruct
$0.72 / $0.72
W&B InferenceInference
Llama-3.1-70B-Instruct
$0.80 / $0.80
+11% vs headline
Fireworks AIInference
llama-v3p1-70b-instruct
$0.90 / $0.90
+25% vs headline
PerplexityGateway
llama-3.1-70b-instruct
$1.00 / $1.00
+39% vs headline
llama-3.1-70b-instruct-maas
-

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 License
Runs in about 169.3 GB of GPU memory
Runtimes: 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 Oracle OCI.

Smaller Meta models

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    36% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    64% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    5% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    11% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    27% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    33% less

Model line

Newer and older versions, at each lab's own price.

  1. Dec 2024Llama 3.3 70B InstructLatestNot listed
  2. Dec 2024Llama3.3 70B Instruct$0.12 / $0.30
  3. Jul 2024Llama 3.1 70B InstructThis page$0.72 / $0.72
  4. Jul 2024Llama3.1 70B Instruct$0.12 / $0.30
  5. UndatedLlama 3 70B Instruct$0.51 / $0.74
  6. UndatedLlama3 70B Instruct$2.65 / $3.50

Call it

Using Oracle OCI's API.

Python
from litellm import completion

response = completion(
    model="oci/meta.llama-3.1-70b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama 3.1 70B Instruct cost?

On Oracle OCI, Llama 3.1 70B Instruct costs $0.72 per million input tokens and $0.72 per million output tokens.

Which APIs offer Llama 3.1 70B Instruct?

Llama 3.1 70B Instruct runs on 5 APIs: Oracle OCI, W&B Inference, Fireworks AI, Perplexity and Vertex AI.

What is Llama 3.1 70B Instruct's context window?

128K tokens, with up to 4K tokens in one reply.

Is Llama 3.1 70B Instruct being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Llama 3.1 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 3.1 70B Instruct?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (83% less), GPT-5.4 Nano on OpenAI (36% less), Claude Haiku 5.5 on Anthropic (72% less) and Kimi K2.7 Code on CLF AI Gateway (5% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Llama 3.1 70B Instruct released?

Meta released it on 23 Jul 2024.

What is Llama 3.1 70B Instruct's API model id?

Use meta.llama-3.1-70b-instruct with Oracle OCI. Other hosts use their own ids: Llama-3.1-70B-Instruct on W&B Inference, llama-v3p1-70b-instruct on Fireworks AI, llama-3.1-70b-instruct on Perplexity, llama-3.1-70b-instruct-maas on Vertex AI.

Sources

Raw catalog entry for meta.llama-3.1-70b-instruct on Oracle OCI
{
  "input_cost_per_token": 7.2e-7,
  "litellm_provider": "oci",
  "max_input_tokens": 128000,
  "max_output_tokens": 4000,
  "mode": "chat",
  "output_cost_per_token": 7.2e-7,
  "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
  "supports_function_calling": true,
  "supports_response_schema": false,
  "supports_native_streaming": true
}