InfraRabbit Nederlands

lambda_ai llama3.1-70b-instruct-fp8 (llama3.1-70b-instruct-fp8)

lambda_ai llama3.1-70b-instruct-fp8 costs USD 0.12 per 1M input tokens and USD 0.30 per 1M output tokens (community cross-check, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json), verified 2026-10-23 22:53 UTC.

Last verified 2026-10-23T22:53:51+00:00 · Source: https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json (community cross-check, waak source litellm)
No first-party source is read for this model yet; this value is a community cross-check and can lag the provider.

Price

Input
USD 0.12 / 1M tokens
Output
USD 0.30 / 1M tokens
This price since
2025-07-27T16:46:25+00:00
FX used
1 EUR = 1.1724 USD (ECB)
Billing
per_token

Specification

Context window (tokens)
131,072
Max output
131,072
Mode
chat
Region
global
Listing
listing not verifiable
aggregator / community mirror: no first-party public page to check against
First seen
2025-07-27T16:46:25+00:00
SKU id
llm/lambda_ai/llama3.1-70b-instruct-fp8

Price history (90 days)

1 line, 2025-07-27 to 2025-07-27; values between 0.12 and 0.12 USD; latest 0.12 USD.0.1080.1140.120.1260.132Jul 26Aug 17Sep 9Oct 1Oct 242025-07-27 UTC: 0.12 USD
Observed (UTC)PriceUSDEUROutput / 1MSnapshot
2025-07-27T16:46:25+00:00USD 0.120.120.10240.30#162

Each row is a change point: the price held from that moment until the next row. Full history: JSON · CSV.

Changes

SeenKindChange
2025-07-27T16:46:25+00:00
between 2025-07-19 and 2025-07-27
New SKU 0.12 USD

API: /v1/skus/llm/lambda_ai/llama3.1-70b-instruct-fp8

Cite this

Free to reuse under CC BY 4.0 with this credit. The numbers are list prices, not transacted prices.

InfraRabbit (2026). lambda_ai llama3.1-70b-instruct-fp8 [data as of 2026-10-23]. https://infrarabbit.com/llm/lambda_ai/llama3.1-70b-instruct-fp8 (accessed 2026-10-24). List prices, not transacted prices. CC BY 4.0.
BibTeX
@misc{infrarabbit_llm_lambda_ai_llama3_1_70b_instruct_fp8_2026,
  author       = {{InfraRabbit}},
  title        = {lambda_ai llama3.1-70b-instruct-fp8},
  year         = {2026},
  howpublished = {\url{https://infrarabbit.com/llm/lambda_ai/llama3.1-70b-instruct-fp8}},
  note         = {Data as of 2026-10-23; accessed 2026-10-24; list prices, not transacted prices; CC BY 4.0}
}