Opennan

Llama 3.3 70B

Live on the API
by MetaTextllama-3.3-70b

$0.13/1M input

output $0.416/1MPrices checked Oct 16, 2026
Input → output
Text promptText
Context
131K tokens

Llama 3.3 70B

Meta

from $0.13/1M tokens

Output

Ready
Example output
Explain in two short sentences why the sky is blue.

Llama 3.3 70B

The sky appears blue because when sunlight enters the Earth's atmosphere, it is scattered by tiny molecules of gases such as nitrogen and oxygen, with shorter (blue) wavelengths being scattered more than longer (red) wavelengths. This scattered blue light is then dispersed throughout the atmosphere, giving the sky its blue color to our eyes.

Or start with

Enter to send · Shift + Enter for a new line

max 1,024 tokens out

Llama 3.3 70B API prices

Every tier we sell, next to the model maker's official price.

All prices
Llama 3.3 70B prices by tier, in US dollars
TierOpennanOfficial
Input, per 1M tokens$0.13No official price
Output, per 1M tokens$0.416No official price

The maker doesn't sell this exact model on its own API (open weights, or retired there), so there is no official price to compare.

Call Llama 3.3 70B from your code

Everything for your first call is on this page: the endpoint, a key, the request and every parameter.

POSThttps://api.opennan.com/v1/chat/completions

  1. Get an API key

    Create a key in the console. It uses the same balance as the playground.

    Create a key

  2. Send your first request

    The same request the playground sends. Set OPENNAN_KEY to your key.

    curl -N https://api.opennan.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENNAN_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-3.3-70b","messages":[{"role":"user","content":"Write a haiku about a city at night."}],"max_tokens":1024,"temperature":1,"top_p":1,"stream":true,"stream_options":{"include_usage":true}}'

  3. Read the result

    The result comes back in the same response. The X-Usage-Cost-Usd header says what the call cost.

Parameters

Built from the live catalog: every value listed here is one the API accepts.

Parameters
NameTypeAllowed valuesDefaultEffect on price
modelrequiredWhich model runs the call.stringllama-3.3-70b——
messagesrequiredThe conversation so far, as role and content pairs.list of messages———
max_tokensoptionalThe longest answer, in tokens.integer1–32,7688192Billed per token written
temperatureoptionalHigher gives more varied answers.number———
streamoptionalSend the answer piece by piece as it is written.boolean—false—
toolsoptionalFunctions the model may call.list———

Errors and how to fix them

  • 401Missing or wrong key

    Send the header Authorization: Bearer with a key from the console.

  • 402Balance too low

    Add credit in Billing, then send the same call again.

  • 400A value is not accepted

    Read error.message: it names the field. Use a value from the parameter table.

  • 429Too many requests

    Wait a few seconds and try again, waiting longer after each 429.

Add Opennan to your AI app

One install gives your AI every Opennan tool: video, images, chat, voice, music, sound effects, 3D, captions and dubbing. Pick your app and follow the steps.

MCP serverhttps://api.opennan.com/v1/mcp

Works in the Codex CLI, the Codex app and the Codex IDE extension: they share ~/.codex/config.toml. If the app or IDE does not see OPENNAN_KEY, use the config.toml option with your key in it. Codex asks before each tool call: approve it to go on.

  1. Get an API key

    Create a key in the console. It starts with sk- and uses the same balance as the website.

    Create a key

  2. Save your key as OPENNAN_KEY

    # macOS / Linux (zsh shown; bash: ~/.bashrc)
echo 'export OPENNAN_KEY="sk-..."' >> ~/.zshrc
source ~/.zshrc

# Windows (PowerShell), then open a new terminal
setx OPENNAN_KEY "sk-..."

  3. Install the Opennan plugin: the server plus a skill that teaches your AI to pick models, confirm prices and wait for results

    codex plugin marketplace add Opennan/opennan-ai-plugin
codex plugin add opennan@opennan

  4. Or add only the server

    codex mcp add opennan --url https://api.opennan.com/v1/mcp --bearer-token-env-var OPENNAN_KEY

  5. Or add this to ~/.codex/config.toml

    [mcp_servers.opennan]
url = "https://api.opennan.com/v1/mcp"
http_headers = { Authorization = "Bearer sk-..." }

  6. Check that opennan is listed

    codex mcp list

  7. Restart Codex, then ask for anything

    “Make a 5 second video of rain on a neon street, a song to go with it and a poster image.”

Replace sk-... with your own key and keep it private: anyone who has it can spend your balance. Your app can list the tools before you add a key; making anything needs one.

This tool from your AI

Once Opennan is added, your AI calls this tool with arguments like these.

Tool
chat
Example arguments
{
  "model": "llama-3.3-70b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about a city at night."
    }
  ]
}

Llama 3.3 70B API questions

How much does the Llama 3.3 70B API cost?

Llama 3.3 70B API on Opennan: $0.13 in / $0.416 out per 1M tokens. Prices are in US dollars per call, shown before you run, and every tier is in the price table.

What inputs does Llama 3.3 70B take?

Text prompt.

Which options can a call set?

Context window: 131,072 tokens. Up to 32,768 output tokens per reply.

How is it billed?

Per token: input, cached input and output tokens are priced per 1M tokens and billed separately.

What happens if a generation fails?

A request that fails is not charged. You pay only for the tokens used.

How do I call Llama 3.3 70B from an AI agent?

Add the MCP server https://api.opennan.com/v1/mcp with your API key as a bearer token, then call the chat tool with model "llama-3.3-70b". Or send a POST to https://api.opennan.com/v1/chat/completions.

Similar models

Text models you can call with the same key.

All models

Same task

More from Meta

Cheapest in Text

We only use the cookies the site needs, such as your language and a referral code. No ads. We count page visits with cookie-free analytics. See our Cookie Policy for details.