Meta: Llama-3.3-70B-Instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Source-linked llama Open weights Released 2024-12-06

API record Report

InputT

OutputT

Input price$0.10/M

Output price$0.32/M

Context128K

Max output4.1K

Providers32

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Llama-3.3-70B-Instruct
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Snowflake Cortex	`snowflake-llama3.3-70b`	128K	4.1K	—	—	—	Not listed	Docs ↗
GitHub Models	`meta/llama-3.3-70b-instruct`	128K	32.8K	—	—	—	ReasoningTools	Docs ↗
Nvidia	`meta/llama-3.3-70b-instruct`	128K	4.1K	—	—	—	ToolsJSON	Docs ↗
Llama	`llama-3.3-70b-instruct`	128K	4.1K	—	—	—	Tools	Docs ↗
Pendra	`llama3.3:70b`	128K	4.1K	—	—	—	Tools	Docs ↗
OpenRouter	`meta-llama/llama-3.3-70b-instruct`	131K	16.4K	$0.10	$0.32	—	ToolsJSON	Docs ↗
Kilo Gateway	`meta-llama/llama-3.3-70b-instruct`	131K	16.4K	$0.10	$0.32	—	ToolsJSON	Docs ↗
Eden AI	`deepinfra/meta-llama/Llama-3.3-70B-Instruct`	131K	4.1K	$0.10	$0.32	—	ToolsJSON	Docs ↗
Eden AI	`nebius/meta-llama/Llama-3.3-70B-Instruct`	131K	4.1K	$0.13	$0.40	$0.13	ToolsJSON	Docs ↗
DevPass (LLM Gateway)	`llama-3.3-70b-instruct`	131K	4.1K	$0.14	$0.40	—	Tools	Docs ↗
Novita AI	`meta-llama/llama-3.3-70b-instruct`	12.3K	12.3K	$0.14	$0.40	—	ToolsJSON	Docs ↗
Merge Gateway	`meta/llama-3.3-70b-instruct`	131K	32.8K	$0.22	$0.50	$0.11	Tools	Docs ↗
Crusoe	`meta-llama/Llama-3.3-70B-Instruct`	128K	4.1K	$0.25	$0.75	$0.13	Tools	Docs ↗
Neon	`meta-llama-3-3-70b-instruct`	128K	8.19K	$0.50	$1.50	—	ToolsJSON	Docs ↗
Hugging Face	`meta-llama/Llama-3.3-70B-Instruct`	131K	4.1K	$0.59	$0.79	—	ToolsJSON	Docs ↗
Abacus	`meta-llama/Meta-Llama-3.3-70B-Instruct`	131K	8.19K	$0.59	$0.79	—	Tools	Docs ↗
SambaNova	`Meta-Llama-3.3-70B-Instruct`	131K	3.07K	$0.60	$1.20	—	Tools	Docs ↗
Charm Hyper	`llama-3.3-70b-instruct`	128K	12.8K	$0.61	$1.04	$0.30	Tools	Docs ↗
Azure	`llama-3.3-70b-instruct`	128K	32.8K	$0.71	$0.71	—	Tools	Docs ↗
Azure Cognitive Services	`llama-3.3-70b-instruct`	128K	32.8K	$0.71	$0.71	—	Tools	Docs ↗
Vercel AI Gateway	`meta/llama-3.3-70b`	128K	8.19K	$0.72	$0.72	—	Tools	Docs ↗
OCI Generative AI	`meta.llama-3.3-70b-instruct`	128K	4.1K	$0.72	$0.72	—	Not listed	Docs ↗
Cortecs	`llama-3.3-70b-instruct`	131K	131K	$0.72	$0.72	—	ToolsJSON	Docs ↗
watsonx.ai	`meta-llama/llama-3-3-70b-instruct`	131K	4.1K	$0.75	$0.75	—	Tools	Docs ↗
Eden AI	`ionos/meta-llama/Llama-3.3-70B-Instruct`	128K	4.1K	$0.76	$0.76	—	Not listed	Docs ↗
Pioneer	`meta-llama/Llama-3.3-70B-Instruct`	16.4K	16.4K	$0.90	$0.90	$0.90	Tools	Docs ↗
Scaleway	`llama-3.3-70b-instruct`	1K	16.4K	$1.01	$1.01	—	Tools	Docs ↗
Prime Inference	`meta-llama/llama-3.3-70b-instruct`	131K	16.4K	$1.04	$2.25	—	Tools	Docs ↗
Eden AI	`scaleway/llama-3.3-70b-instruct`	128K	4.1K	$1.05	$1.05	—	Tools	Docs ↗
evroc	`nvidia/Llama-3.3-70B-Instruct-FP8`	128K	4.1K	$1.15	$1.15	—	Tools	Docs ↗
GreenPT	`llama-3.3-70b-instruct`	1K	16.4K	$1.25	$1.25	—	Tools	Docs ↗
Tinfoil	`llama3-3-70b`	131K	4.1K	$1.75	$2.75	—	Tools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.10/M

Across 27 priced providers

Median input $0.71/M

Midpoint of listed rates

Highest input $1.75/M

17.5× the lowest listed rate

Output range $0.32 – $2.75

Per million output tokens

OpenRouter $0.10/M

Kilo Gateway $0.10/M

Eden AI $0.10/M

Eden AI $0.13/M

DevPass (LLM Gateway) $0.14/M

Novita AI $0.14/M

Merge Gateway $0.22/M

Crusoe $0.25/M

Neon $0.50/M

Hugging Face $0.59/M

Abacus $0.59/M

SambaNova $0.60/M

Charm Hyper $0.61/M

Azure $0.71/M

Azure Cognitive Services $0.71/M

Vercel AI Gateway $0.72/M

OCI Generative AI $0.72/M

Cortecs $0.72/M

watsonx.ai $0.75/M

Eden AI $0.76/M

Pioneer $0.90/M

Scaleway $1.01/M

Prime Inference $1.04/M

Eden AI $1.05/M

evroc $1.15/M

GreenPT $1.25/M

Tinfoil $1.75/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

3 providers list the identical $0.10 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 12.3K to 131K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No

✓ Tool calling Yes

✓ Structured output Yes

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: Meta
Model family: llama
Knowledge cutoff: 2023-12
License: Not documented
Release date: 2024-12-06
Model ID: meta/llama-3.3-70b-instruct

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Benchmark profile

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

SciCode percent correct · 2026-03-11 Source ↗

SciCode #22 of 27

26.0

Artificial Analysis Coding Index index · 2026-03-11 Source ↗

Artificial Analysis Coding Index #24 of 26

10.7

Terminal-Bench Hard success rate · 2026-03-11 Source ↗

Terminal-Bench Hard #22 of 22

3.0

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against SciCode, the benchmark with the widest published coverage that this model appears in.

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Aug 03, 2026Price Completion0.4 → 0.32

Aug 03, 2026Price Prompt0.13 → 0.1

Jul 16, 2026Price Completion0.32 → 0.4

Jul 16, 2026Price Prompt0.1 → 0.13

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Oct 24, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://modelbench.lol/api/v1/models/meta/llama-3.3-70b-instruct

curl

curl "https://modelbench.lol/api/v1/models/meta/llama-3.3-70b-instruct"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Llama-3.3-70B-Instruct?

Popular open Llama workhorse for multilingual chat, coding, and self-hosting. It is published by Meta and catalogued here from Models.dev.

How much does Llama-3.3-70B-Instruct cost?

Listed input pricing starts at $0.10 per million tokens from OpenRouter, rising to $1.75 across 27 listed providers.

What is the context length of Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct accepts up to 128K tokens of context and returns up to 4.1K output tokens.

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

Provider catalogs list support for tool calling, and structured output.

Which providers serve Llama-3.3-70B-Instruct?

29 providers list this model: Snowflake Cortex, GitHub Models, Nvidia, Llama, Pendra, OpenRouter and 23 more.

Are the weights for Llama-3.3-70B-Instruct open?

Yes. The weights are published and downloadable from Hugging Face.

When was Llama-3.3-70B-Instruct released?

The catalog records a release date of 2024-12-06, last verified Oct 24, 2026.

More models from Meta

View all →

Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

164K ctx $0.18/M in Meta: Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

128K ctx $0.19/M in Meta: Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

328K ctx $0.10/M in Meta: Llama 3.3 70B Instruct (free)

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

65.5K ctx