Meta Llama 3.1 8B Instruct API Pricing

Meta Llama 3.1 8B Instruct API pricing: $0.02 per 1M tokens for input and $0.04 per 1M tokens for output, from OpenRouter. Published Last checked · Source (data) · Methodology

OpenRouter listing: changed −60% since 8 Nov 2026.

OpenRouter: Amount worked out from the source page: $0.02 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded.

Data as of9 Nov 2026Prices checked 9 Nov 2026 · test requests to 8 Nov 2026Data & API
Task receipt: OpenRouter: $0.0033 Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown.
Task receipt.Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown. Open image · Explore the chart · Measured Lab · CC BY 4.0

Prices USD per 1M tokens, as listed

  • $0.02–$0.22Input per 1M tokens, through OpenRouter, across 4 endpoints Published
  • $0.04–$0.287Output per 1M tokens, through OpenRouter, across 4 endpoints Published

OpenRouter listing $0.02 / $0.04 per 1M tokens: listing differs from 3 of 4 endpoints read on 9 Nov 2026.

All prices by channel
Price per 1M tokensProvider directThrough OpenRouterPrevious prices by channel
Input—$0.02–$0.22 Publishedacross 4 endpoints; listing $0.02: listing differs from 3 of 4 endpoints—
Output—$0.04–$0.287 Publishedacross 4 endpoints; listing $0.04: listing differs from 3 of 4 endpoints—
Cached input · read—$0.025 Published—

Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026

16 Oct 2026$0.05 → $0.02 → $0.05 → $0.029 Nov 2026

Context window131,072tokens Published
Max output16,384tokens Published

OpenRouter providers who serves this model through OpenRouter, at what price

OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.

Pinned min: $0.02 / $0.04 · DeepInfra (deepinfra/fp8)

Unpinned range: input $0.02–$0.22, output $0.04–$0.287 across 4 providers (listing shows $0.05 / $0.08).

Observed unpinned cost: 144 short requests sent without a pinned provider on 25 Oct 2026 – 9 Nov 2026 (16 dates), in each routing mode. Charged is the sum of the OpenRouter generation receipts for these requests; the listing price column is the price of the same input and output tokens at the listing price of that date.

Routing modeRequestsDatesServed byChargedListing price for the same tokensCharged / listingLowest-priced endpoint answered
Default (no provider field)4825 Oct 2026 – 9 Nov 2026 (16 dates)26 of 48 DeepInfra (deepinfra/fp8), 13 of 48 Novita (novita/fp8), 6 of 48 Cloudflare (cloudflare/fp8), 3 of 48 Groq (groq)$0.000073$0.0000860.85×26 of 48
:floor4825 Oct 2026 – 9 Nov 2026 (16 dates)46 of 48 DeepInfra (deepinfra/fp8), 2 of 48 Groq (groq)$0.000040$0.0000840.48×46 of 48
:nitro4825 Oct 2026 – 9 Nov 2026 (16 dates)48 of 48 Groq (groq)$0.00015$0.000151.00×0 of 48

Routing modes as documented by OpenRouter (OpenRouter provider routing, read 25 Oct 2026): the default request has no provider field; :floor and :nitro are suffixes of the model name. Served by names the endpoint that answered, by the provider name and endpoint tag of the receipt. Each request asks for one short line with an answer cap of 32 tokens. The counts are for these requests on these dates only.

Models with the widest provider price spread on OpenRouter

Request fragment that pins DeepInfra (deepinfra/fp8):

{"provider": {"order": ["deepinfra/fp8"], "allow_fallbacks": false}}

With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).

All endpoints (4), by input price
ProviderEndpoint tagPrecisionInputOutputContext, tokens
DeepInfradeepinfra/fp8fp8$0.02$0.04131,072
GroqgroqNot stated$0.05$0.08131,072
Cloudflarecloudflare/fp8fp8$0.152$0.28732,000
CoreWeavecoreweave/bf16bf16$0.22$0.22131,072

Sorted by input price, then output price. Precision is the quantization field of the endpoints list.

Quality signals public test results, each with its source and date

SignalResultSource
Function callingBFCL V4 overall, tools described in the prompt25.83 % Publishedlive 70.76 % · non-live 84.00 % · multi-turn 11.12 % · web search 3.00 % · memory 10.75 %Berkeley Function Calling Leaderboard, BFCL V4, last updated 12 Apr 2026read 17 Oct 2026 · leaderboard entry Llama-3.1-8B-Instruct (Prompt) · Apache 2.0
  • Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
  • Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.

What each signal covers and how our run is scored: methodology.

How we got this number

  • What we read: the published price on openrouter.ai/api/v1/models
  • Checked: ; tracked since 16 Oct 2026
  • Shown in: the United States
  • Checks so far: 25 checks since 16 Oct 2026
  • What changed: the listed price moved between checks since 16 Oct 2026; see the record history
  • Page updated:

Other measured facts

QuestionAnswerCheckedStatus
How much does Meta Llama 3.1 8B Instruct cost per 1M output tokens on OpenRouter?$0.04 per 1M tokensPublished
What is the context window of Meta Llama 3.1 8B Instruct on OpenRouter, in tokens?131,072 tokensPublished
What is the maximum output length of Meta Llama 3.1 8B Instruct on OpenRouter, in tokens?16,384 tokensPublished

History

The listed price moved between the 25 checks since 16 Oct 2026; every reading is in the record history below.

  1. — First check: $0.05 per 1M tokens
  2. Short-lived or unconfirmed moves are not shown as changes.

The source record lists $0.00000002 per token ($0.02 per 1M tokens), fetched on 9 Nov 2026.

The source record, as published
"prompt":"0.00000002"
What the source says · openrouter.ai

Latest briefings each price change recalculated as a task cost

  1. DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
  2. DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
  3. MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)

All briefings

Record history — 111 records for 5 questions
Last record
Shown in
the United States
How much does Meta Llama 3.1 8B Instruct cost per 1M input tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.02 per 1M tokensPublished
8 Nov 2026$0.05 per 1M tokensPublished
7 Nov 2026$0.05 per 1M tokensPublished
6 Nov 2026$0.05 per 1M tokensPublished
5 Nov 2026$0.05 per 1M tokensPublished
4 Nov 2026$0.05 per 1M tokensPublished
3 Nov 2026$0.05 per 1M tokensPublished
2 Nov 2026$0.05 per 1M tokensPublished
1 Nov 2026$0.05 per 1M tokensPublished
31 Oct 2026$0.05 per 1M tokensPublished
30 Oct 2026$0.05 per 1M tokensPublished
29 Oct 2026$0.05 per 1M tokensPublished
How much does Meta Llama 3.1 8B Instruct cost per 1M output tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.04 per 1M tokensPublished
8 Nov 2026$0.08 per 1M tokensPublished
7 Nov 2026$0.08 per 1M tokensPublished
6 Nov 2026$0.08 per 1M tokensPublished
5 Nov 2026$0.08 per 1M tokensPublished
4 Nov 2026$0.08 per 1M tokensPublished
3 Nov 2026$0.08 per 1M tokensPublished
2 Nov 2026$0.08 per 1M tokensPublished
1 Nov 2026$0.08 per 1M tokensPublished
31 Oct 2026$0.08 per 1M tokensPublished
30 Oct 2026$0.08 per 1M tokensPublished
29 Oct 2026$0.08 per 1M tokensPublished
What is the context window of Meta Llama 3.1 8B Instruct on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026131,072 tokensPublished
8 Nov 2026131,072 tokensPublished
7 Nov 2026131,072 tokensPublished
6 Nov 2026131,072 tokensPublished
5 Nov 2026131,072 tokensPublished
4 Nov 2026131,072 tokensPublished
3 Nov 2026131,072 tokensPublished
2 Nov 2026131,072 tokensPublished
1 Nov 2026131,072 tokensPublished
31 Oct 2026131,072 tokensPublished
30 Oct 2026131,072 tokensPublished
29 Oct 2026131,072 tokensPublished
28 Oct 2026131,072 tokensPublished
What is the maximum output length of Meta Llama 3.1 8B Instruct on OpenRouter, in tokens?
TimeValueStatus
9 Nov 202616,384 tokensPublished
8 Nov 2026117,964 tokensPublished
7 Nov 2026117,964 tokensPublished
6 Nov 2026117,964 tokensPublished
5 Nov 2026117,964 tokensPublished
4 Nov 2026117,964 tokensPublished
3 Nov 2026117,964 tokensPublished
2 Nov 2026117,964 tokensPublished
1 Nov 2026117,964 tokensPublished
31 Oct 2026117,964 tokensPublished
30 Oct 2026117,964 tokensPublished
29 Oct 2026117,964 tokensPublished
How much does Meta Llama 3.1 8B Instruct cost per 1M cache-read tokens (cache hits) on OpenRouter?
TimeValueStatus
8 Nov 2026$0.03 per 1M tokensPublished
7 Nov 2026$0.03 per 1M tokensPublished
6 Nov 2026$0.03 per 1M tokensPublished
5 Nov 2026$0.03 per 1M tokensPublished
4 Nov 2026$0.03 per 1M tokensPublished
3 Nov 2026$0.03 per 1M tokensPublished
2 Nov 2026$0.03 per 1M tokensPublished
1 Nov 2026$0.03 per 1M tokensPublished
31 Oct 2026$0.03 per 1M tokensPublished
30 Oct 2026$0.03 per 1M tokensPublished
29 Oct 2026$0.03 per 1M tokensPublished

Showing the latest 60 of 111 records; the full history is in data.json and data.csv.

Explore the numbers

Llama 3.1 8B Instruct

OpenRouter$0.0033$0.00$0.001$0.002$0.003$0.004OpenRouter$0.0033$0.00$0.001$0.002$0.003$0.004
OpenRouter$48.18$0$20$40$60OpenRouter$48.18$0$20$40$60

Calculated · Document analysis

Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries.

Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown.

Fresh input · Visible output · Cache read · Cache write

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.