zerogpu llama-3.1-8b-instruct-fast (llama-3.1-8b-instruct-fast)
zerogpu llama-3.1-8b-instruct-fast costs USD 0.15 per 1M input tokens and USD 0.28 per 1M output tokens (community cross-check, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json), verified 2026-10-29 06:01 UTC.
Last verified 2026-10-29T06:01:15+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 0.15 / 1M tokens
- Output
- USD 0.28 / 1M tokens
- Cached input
- USD 0.025 / 1M
- This price since
- 2026-10-28T23:57:27+00:00
- FX used
- 1 EUR = 1.1133 USD (ECB)
- Billing
- per_token
Specification
- Context window (tokens)
- 131,072
- Max output
- 8,192
- Mode
- chat
- Region
- global
- Listing
- listing not verifiable
aggregator / community mirror: no first-party public page to check against - First seen
- 2026-10-28T23:57:27+00:00
- SKU id
llm/zerogpu/llama-3.1-8b-instruct-fast
Price history (90 days)
| Observed (UTC) | Price | USD | EUR | Output / 1M | Snapshot |
|---|---|---|---|---|---|
| 2026-10-28T23:57:27+00:00 | USD 0.15 | 0.15 | 0.1347 | 0.28 | #1523 |
Each row is a change point: the price held from that moment until the next row. History via the API: JSON · CSV.
Changes
| Seen | Kind | Change |
|---|---|---|
| 2026-10-28T23:57:27+00:00 between 2026-10-28 and 2026-10-28 |
New SKU | 0.15 USD |
API: /v1/skus/llm/zerogpu/llama-3.1-8b-instruct-fast
Cite this
Free to reuse under CC BY 4.0 with this credit. The numbers are list prices, not transacted prices.
InfraRabbit (2026). zerogpu llama-3.1-8b-instruct-fast [data as of 2026-10-29]. https://infrarabbit.com/prices/llm/zerogpu/llama-3.1-8b-instruct-fast (accessed 2026-10-29). List prices, not transacted prices. CC BY 4.0.
BibTeX
@misc{infrarabbit_llm_zerogpu_llama_3_1_8b_instruct_fast_2026,
author = {InfraRabbit},
title = {zerogpu llama-3.1-8b-instruct-fast},
year = {2026},
howpublished = {\url{https://infrarabbit.com/prices/llm/zerogpu/llama-3.1-8b-instruct-fast}},
note = {Data as of 2026-10-29; accessed 2026-10-29; list prices, not transacted prices; CC BY 4.0}
}