Llama 3.3 70B

by MetaChat

Open Llama instruction model for multilingual chat, reasoning, and coding

Context
131K tokens
Max output
16,384 tokens
Parameters
70B (total or active not stated)
Released
2024-12-06
Weights
Open

Feed

meta/llama-3-3-70b · also seen as TEE/llama3-3-70b, llama3.3-70b

Specifications

Full facts as recorded, incl. what is unknown.

Released
2024-12-06
Weights
Open
Input
Text
Output
Text
Context window
131,072 max across endpoints
Max output
16,384
Providers
4 + 2 gateways, not counted as providers
Epoch Capabilities Index
127.3 ± 3.9 against price
Direct price range
$0.20–$0.85 in · $0.50–$2.80 out per 1M tokens · across all 4 providers
More details
Last updated
2026-06-11
Knowledge cutoff
2023-12
Parameters
70B (total or active not stated)
Developer country
United States of America
Training compute
6.9×10²⁴ FLOP

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured output
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messages
  • Assistant prefillunknown
  • Temperature
  • Streaming
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

Atom feed

No change since 19 Oct 2026. The cheapest direct price has been $0.20 in / $0.50 out per 1M tokens at inferenceapis on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

Similarly priced models

Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).

ModelBlended/1MIn/1MOut/1MContextvs Llama 3.3 70B
Qwen3.6 Max PreviewAlibaba (Qwen)$1.91$1.04$6.24262K−1% cheaper
Gemini 2.0 Pro 1206Google$1.88$1.26$5.002.1M−2% cheaper
Nano Banana ProGoogle$1.83$1.00$6.0065.5K−4% cheaper
QVQ MaxAlibaba (Qwen)$1.80$1.20$4.80131K−6% cheaper
Cogito v1 Preview Qwen 32BDeep Cogito$1.80$1.80$1.80131K−6% cheaper
Qwen3.8 Max PreviewAlibaba (Qwen)$2.06$1.54$4.631M+7%
DeepSeek V4 Pro 0423DeepSeek$1.76$1.32$3.961M−8% cheaper
Muse Spark 1.1Meta$1.75$1.25$4.251.05M−9% cheaper

More from Meta

Newest Meta models in the catalogue. All Meta models

ModelReleasedContextListed price
Muse Spark Open2026-10-151.05Mfrom $1.25
Muse Wonder2026-10-121.05Mfrom $4.00
Muse Wonder2026-10-121.05Mfrom $4.00
Muse Voice Transcribe 1.02026-09-11—unpriced
Muse Spark 1.32026-09-021.05Mfrom $1.25
Muse Spark 1.3 Contributor2026-09-021.05Mfrom $0.10
Muse Image 1.02026-08-26—unpriced
Muse Image2026-08-2665.5Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model