Llama 3.3 70B Instruct

Metameta/llama-3.3-70b-instruct
Modality

Chat

Family

Llama

Context window

—

Max output

—

Served On

Microsoft Azure (OpenAI + AI Foundry)

Llama 3.3 70B Instruct is a chat model made by Meta, served on nRouter.

Model pricing

Exact provider list price · 0% platform fee · x-nr-request-cost header

Rates are read live

Pricing for meta/llama-3.3-70b-instruct is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Start building with meta/llama-3.3-70b-instruct

One API key, three steps. Choose your tool to begin.

  1. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"
  2. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · meta/llama-3.3-70b-instruct
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with meta/llama-3.3-70b-instruct
claude --model meta/llama-3.3-70b-instruct

Specifications & capabilities

VisionFunction callingStreamingJSON modeSystem prompt
Compare context window against peer models (—)

Context window, ranked against other chat models

Proportional scale: 0 to 400K tokens. Not ranked, no published context window: meta/llama-4-maverick-17b-128e-instruct-fp8.

Benchmarks & performance rankings

Published LLM Arena category placements and Elo ratings for Llama 3.3 70B Instruct.

LLM Arena category ratings
Overall#286

1274Elo

Coding#294

1268Elo

Math#277

1267Elo

Creative Writing#276

1250Elo

Hard Prompts#288

1257Elo

Instruction Following#294

1242Elo

Multi-Turn#273

1280Elo

Longer Query#293

1255Elo

Non-English#297

1236Elo

Source: huggingface.co · CC-BY-4.0

Provider-Reported Capabilities

What the hosting provider reports for this model, shown as it was returned. nRouter adds nothing to this report and infers nothing that is missing from it.

Area area

US

Agents V2 agentsV2

true

Chat Completion chatCompletion

true

Global Fine Tune globalFineTune

true

Supports vision supports_vision
Datazone Fine Tune datazoneFineTune

true

Supports JSON mode supports_json_mode
Supports responses supports_responses
Supports streaming supports_streaming
Fine Tune Tokens Max Value FineTuneTokensMaxValue

3000000000

Supports function calling supports_function_calling

Availability

Collecting probe samples

Not enough health probe samples collected yet to publish an uptime or latency figure.

More from Meta

FAQs

What is Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct is a chat model made by Meta, served on nRouter.

How much does Llama 3.3 70B Instruct cost?

Llama 3.3 70B Instruct is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.

Does Llama 3.3 70B Instruct support tool calling and structured outputs?

No. Llama 3.3 70B Instruct does not support tool calling, so it cannot invoke external tools or functions. It does not support a structured JSON output mode.

What inputs and outputs does Llama 3.3 70B Instruct support?

Llama 3.3 70B Instruct takes text as input and returns text as output.

How do I use Llama 3.3 70B Instruct via nRouter?

Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "meta/llama-3.3-70b-instruct". The quick-start panel above has a copy-paste curl command for this model.

Where is the Llama 3.3 70B Instruct documentation?

Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.

What other text models does Meta have?

Other Meta text models on nRouter include Llama 4 Maverick 17B 128E Instruct FP8 (nrouter.ai/models/meta-llama-4-maverick-17b-128e-instruct-fp8), Llama 4 Scout 17B 16E Instruct (nrouter.ai/models/meta-llama-4-scout-17b-16e-instruct).