Llama 3.3 70B Instruct
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
Model by Meta
Chalk Labs
Need help deploying Llama 3.3 70B Instruct?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Pick your client. Read the repository before you give any tool access to your data.
{
"model": "meta-llama/llama-3.3-70b-instruct",
"baseURL": "https://openrouter.ai/api/v1"
}OpenAI-compatible API: point any OpenAI SDK at the base URL and use this model id.
Settings it needs
OPENROUTER_API_KEYrequiredsecret
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: model-inference
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Price and limits
| Variant | Input $/M tokens | Output $/M tokens | Cached input $/M |
|---|---|---|---|
| Standard | $0.1 | $0.32 | — |
Price as of Oct 26, 2026 from OpenRouter. Prices change often; check before you rely on one.
- Provider
- Meta
- Model id
meta-llama/llama-3.3-70b-instruct- Context window
- 131,072 tokens (131K)
- Max output
- 16,384 tokens
- Input
- text
- Output
- text
- Tool calling
- Yes
- Structured outputs
- Yes
- Reasoning
- No
- Weights
- Open: meta-llama/Llama-3.3-70B-Instruct
- Released
- Dec 6, 2024
- Knowledge cutoff
- 2023-12-31
Details
- Auth
- API key
- License
- License unknown
- Website
- www.llama.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 26, 2026
- Source
- OpenRouter
More from Meta
- 0.851score
Faiss
Meta
Library for efficient similarity search and clustering of dense vectors, with optional GPU support.
InfrastructureAFreshness: A★ 41.2Kvector db - 0.756score
Llama Guard
Meta
Meta's open safeguard models that moderate LLM prompts and responses, including Llama Guard 4.
Observability toolAFreshness: A★ 4.4Kguardrails - 0.681score
Llama 3.2 3B Instruct
Meta
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation…
ModelAFreshness: A$0.05 / $0.33131K ctxOpen weights - 0.681score
Llama 3.2 1B Instruct
Meta
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and…
ModelAFreshness: A$0.027 / $0.20160K ctxOpen weights - 0.592score
Muse Spark 1.2
Meta
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.
ModelAFreshness: A$1.25 / $4.251M ctx - 0.592score
Muse Spark 1.1
Meta
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.
ModelAFreshness: A$1.25 / $4.251M ctx
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Llama 3.3 70B Instruct running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Llama 3.3 70B Instruct: price, context window, tool use. Agent Mart. https://agentmart.dev/models/meta-llama-llama-3-3-70b-instruct (last updated 2026-10-26)