impulse

Meta Llama 3.3 70B Instruct

Open weights
API id Meta-Llama-3_3-70B-Instruct
Input / 1M
$0.67
at OVHcloud AI Endpoints
Output / 1M
$0.67
at OVHcloud AI Endpoints
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

List prices at OVHcloud AI Endpoints, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.67$0.67

What it costs a month

At OVHcloud AI Endpoints list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$251
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$346
  • Coding agent1,000 requests a day, 40K in / 2K out$844
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,769
Use your own numbers

Where to run it

3 hosts serve Meta Llama 3.3 70B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Meta-Llama-3_3-70B-Instruct
$0.67 / $0.67
SambaNovaInference
Meta-Llama-3.3-70B-Instruct
$0.60 / $1.20
+12% vs headline
databricks-meta-llama-3-3-70b-instruct
$0.50 / $1.50
+12% vs headline

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
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 OVHcloud AI Endpoints.

Smaller Meta models

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    31% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    70% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    70% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    61% less

Open-weight picks

  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    5% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    22% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    28% less
  • GLM 4 6v
    Zhipu AI · on Novita AI
    $0.30 / $0.90
    Has every key capability
    33% less

Model line

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

  1. UndatedMeta Llama 3.3 70B InstructLatest$0.67 / $0.67
  2. UndatedMeta Llama 3.1 70B Instruct$0.12 / $0.30
  3. UndatedMeta Llama 3 70B Instruct$0.12 / $0.30

Call it

Using OVHcloud AI Endpoints's API.

Python
from litellm import completion

response = completion(
    model="ovhcloud/Meta-Llama-3_3-70B-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Meta Llama 3.3 70B Instruct cost?

On OVHcloud AI Endpoints, Meta Llama 3.3 70B Instruct costs $0.67 per million input tokens and $0.67 per million output tokens.

Which APIs offer Meta Llama 3.3 70B Instruct?

Meta Llama 3.3 70B Instruct runs on 3 APIs: OVHcloud AI Endpoints, SambaNova and Databricks.

What is Meta Llama 3.3 70B Instruct's context window?

131K tokens, with up to 131K tokens in one reply.

Is Meta Llama 3.3 70B Instruct being retired?

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

Is there a newer version of Meta Llama 3.3 70B Instruct?

No. Meta Llama 3.3 70B Instruct is the newest model in its line.

What are cheaper alternatives to Meta Llama 3.3 70B Instruct?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (81% less), GPT-5.4 Nano on OpenAI (31% less), Claude Haiku 5.5 on Anthropic (70% less) and Inkling Small on DeepInfra (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Meta Llama 3.3 70B Instruct's API model id?

Use Meta-Llama-3_3-70B-Instruct with OVHcloud AI Endpoints. Other hosts use their own ids: Meta-Llama-3.3-70B-Instruct on SambaNova, databricks-meta-llama-3-3-70b-instruct on Databricks.

Sources

Raw catalog entry for Meta-Llama-3_3-70B-Instruct on OVHcloud AI Endpoints
{
  "input_cost_per_token": 6.7e-7,
  "litellm_provider": "ovhcloud",
  "max_input_tokens": 131000,
  "max_output_tokens": 131000,
  "mode": "chat",
  "output_cost_per_token": 6.7e-7,
  "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
  "supports_function_calling": true,
  "supports_response_schema": true,
  "supports_tool_choice": true
}