Model prices / Meta / Llama-3.3-70B-Instruct
Llama-3.3-70B-InstructOpen weights
Meta · released 2024-12-06
No price from the maker itself is on record for Llama-3.3-70B-Instruct. The lowest of 40 providers is NanoGPT: $0.05 per 1M input tokens and $0.23 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 4.1K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestmeta-llama/ | $0.05 | $0.23 | $0.025 | Lowest | Official docs |
MMeganovameta-llama/ | $0.1 | $0.3 | — | Official docs | |
| $0.1 | $0.32 | — | Official docs | ||
EEden AIdeepinfra/ | $0.1 | $0.32 | — | Official docs | |
KKilo Gatewaymeta-llama/ | $0.1 | $0.32 | — | Official docs | |
HHeliconellama-3.3-70b-instruct | $0.13 | $0.39 | — | Official docs | |
| $0.135 | $0.4 | — | Official docs | ||
LLLM Gatewaynovita/ | $0.135 | $0.4 | — | Official docs | |
| $0.135 | $0.4 | — | Official docs | ||
MMerge Gatewaymeta/ | $0.22 | $0.5 | $0.11 | Official docs | |
SSTACKITcortecs/ | $0.53 | $0.76 | — | Official docs | |
HHeliconellama-3.3-70b-versatile | $0.59 | $0.79 | — | Official docs |
35 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| $0.59 | $0.79 | — | Official docs | ||
| $0.71 | $0.71 | $0.71 | Official docs | ||
| $0.71 | $0.71 | $0.71 | Official docs | ||
| $0.72 | $0.72 | — | Official docs | ||
EEden AIionos/ | $0.723255 | $0.723255 | — | Official docs | |
CCortecsllama-3.3-70b-instruct | $0.724 | $0.724 | — | Official docs | |
OOVHcloud AI Endpointsmeta-llama-3_ | $0.74 | $0.74 | — | Official docs | |
Wwatsonx.aimeta-llama/ | $0.7526 | $0.7526 | — | Official docs | |
| $0.5466 | $1.0226 | $0.2733 | Official docs | ||
| $0.6 | $1.2 | — | Official docs | ||
NNeonmeta-llama-3-3-70b-instruct | $0.5 | $1.5 | — | Official docs | |
EEden AIscaleway/ | $1.00143 | $1.00143 | — | Official docs | |
SScalewayllama-3.3-70b-instruct | $1.00935 | $1.00935 | — | Official docs | |
Eevrocnvidia/ | $1.15 | $1.15 | — | Official docs | |
EEden AIgreenpt/ | $1.22397 | $1.22397 | — | Official docs | |
| $1.254 | $1.254 | — | Official docs | ||
| $0.293 | $2.253 | — | Official docs | ||
| $0.76176 | $2.383674 | — | Official docs | ||
PPrime Inferencemeta-llama/ | $1.04 | $2.253 | — | Official docs | |
| $0.7 | $2.8 | — | Official docs | ||
NNanoGPTTEE/ | $1.75 | $2.75 | $1.75 | Official docs | |
TTinfoilllama3-3-70b | $1.75 | $2.75 | — | Official docs | |
CCloudFerro Sherlockmeta-llama/ | $2.92 | $2.92 | — | Official docs | |
| $0.25 | $0.75 | $0.13 | Deprecated | Official docs | |
AAbacusDeprecatedllama-3.3-70b-versatile | $0.59 | $0.79 | — | Deprecated | Official docs |
AAbacusDeprecatedmeta-llama/ | $0.59 | $0.79 | — | Deprecated | Official docs |
| $0.59 | $0.79 | — | Deprecated | Official docs | |
| $0.72 | $0.72 | — | Deprecated | Official docs | |
| $0.72 | $0.72 | — | Deprecated | Official docs | |
OOCI Generative AIDeprecatedmeta. | $0.72 | $0.72 | — | Deprecated | Official docs |
| $1.04 | $1.04 | — | Deprecated | Official docs | |
RRegolo AIDeprecatedllama-3.3-70b-instruct | $0.6 | $2.7 | — | Deprecated | Official docs |
PPendrallama3.3: | $0 | $0 | — | Official docs | |
| — | — | — | Deprecated | Official docs | |
SSnowflake Cortexsnowflake-llama3.3-70b | — | — | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
Price changes
| Date | Provider | Change |
|---|---|---|
| 2026-11-12 | Eden AI | Input $1.233541 → $1.22397 |
| 2026-11-12 | Eden AI | Output $1.233541 → $1.22397 |
| 2026-11-12 | Eden AI | Input $0.72891 → $0.723255 |
| 2026-11-12 | Eden AI | Output $0.72891 → $0.723255 |
| 2026-11-12 | Eden AI | Input $1.009261 → $1.00143 |
| 2026-11-12 | Eden AI | Output $1.009261 → $1.00143 |
About
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 4.1K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2023-12
- Open weights
- Yes
- Released
- 2024-12-06
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.