Llama 3.3 70B Instruct API

Model details

Context window

131K tokens

Max output

120K tokens

Input

Text

Output

Text

Capabilities

Tool calling, Streaming

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Llama 3.3 70B Instruct for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Llama 3.3 70B Instruct

Llama 3.3 70B Instruct answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "llama-3.3-70b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "llama-3.3-70b-instruct",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "llama-3.3-70b-instruct",
  "input": "Hello"
}'

Use Llama 3.3 70B Instruct in your tools

Every coding agent below has a setup guide. Set the model to llama-3.3-70b-instruct.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from Meta

Alternatives to Llama 3.3 70B Instruct

• Claude Haiku 5.5Anthropic's fastest model, priced for volume.Anthropic
• GPT-6 LunaThe lowest-priced GPT-6 for high-volume tasks.OpenAI
• Ministral 14BMinistral 14B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral

Questions about this model

How much does the Llama 3.3 70B Instruct API cost?

Llama 3.3 70B Instruct costs $0.13 per 1M input tokens and $0.4 per 1M output tokens on Inferray. That is the list price, with no gateway fee on top.

Is there a free tier for Llama 3.3 70B Instruct?

No. You add credit and pay Llama 3.3 70B Instruct's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Llama 3.3 70B Instruct included in Token Plans?

No. Llama 3.3 70B Instruct is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Llama 3.3 70B Instruct in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to llama-3.3-70b-instruct. The same key works in Codex, opencode, Cline, and other agents.

Does Llama 3.3 70B Instruct support tool calling and vision?

Llama 3.3 70B Instruct supports tool calling and streaming on Inferray. It does not take image input.

Is it the real Llama 3.3 70B Instruct?

Yes. A request for llama-3.3-70b-instruct is answered by Llama 3.3 70B Instruct from Meta, billed at its published list price. Inferray never substitutes a different or smaller model.