Model prices / Meta / Llama 3.1 70B Instruct
Llama 3.1 70B InstructOpen weights
Meta · released 2024-07-23
No price from the maker itself is on record for Llama 3.1 70B Instruct. The lowest of 7 providers is Kilo Gateway: $0.72 per 1M input tokens and $0.72 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
KKilo GatewayLowestmeta-llama/ | $0.72 | $0.72 | — | Lowest | Official docs |
 DevPass (LLM Gateway)Betallama-3.1-70b-instruct | $0.72 | $0.72 | — | Beta | Official docs |
 OpenRoutermeta-llama/ | $0.72 | $0.72 | — | Official docs | |
 Vercel AI Gatewaymeta/ | $0.72 | $0.72 | — | Official docs | |
MMerge Gatewaymeta/ | $0.99 | $0.99 | — | Official docs | |
 Amazon BedrockDeprecatedmeta. | $0.72 | $0.72 | — | Deprecated | Official docs |
| Amazon BedrockDeprecatedus. | $0.72 | $0.72 | — | Deprecated | Official docs |
LLLM GatewayDeprecatedaws-bedrock/ | $0.72 | $0.72 | — | Deprecated | 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.
About
Open Llama instruction model for multilingual chat, reasoning, and coding
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 2K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Knowledge cutoff
- 2023-12
- Open weights
- Yes
- Released
- 2024-07-23
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.