Metallama familyActive

Llama 3.1 8B Instruct

Open Llama instruction model for multilingual chat, reasoning, and coding

JSON Embed chart Compare

Context

131,072

Max output

131,072

Input / 1M

$0.02

Output / 1M

$0.03

Providers

01 Profile 02 Capabilities 03 Pricing 04 History 05 Usage 06 Related

01Profile

Profile

Released

2024-07-23

Last updated

2025-01-01

Knowledge cutoff

—

Weights

Open

02Capabilities

Capabilities

Input

text

Output

text

Reasoning

Tool calling

Yes

Structured output

Attachments

Cache read

—

Cache write

—

03Pricing

Pricing across 13 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

Provider	Provider model id	Input	Output	Cache read	Context
abacus	meta-llama/Meta-Llama-3.1-8B-Instructorg:meta	$0.02	$0.05	Not listed	128,000
helicone	llama-3.1-8b-instruct	$0.02	$0.05	Not listed	16,384
kilo	meta-llama/llama-3.1-8b-instruct	$0.02	$0.04	Not listed	131,072
novita-ai	meta-llama/llama-3.1-8b-instruct	$0.02	$0.05	Not listed	16,384
inference	meta/llama-3.1-8b-instruct	$0.03	$0.03	Not listed	16,000
openrouter	meta-llama/llama-3.1-8b-instruct	$0.05	$0.08	$0.03	131,072
nano-gpt	meta-llama/llama-3.1-8b-instruct	$0.05	$0.09	$0.03	131,072
huggingface	meta-llama/Llama-3.1-8B-Instruct	$0.06	$0.06	Not listed	131,072
neon	meta-llama-3-1-8b-instructorg:meta	$0.15	$0.45	Not listed	131,072
cortecs	llama-3.1-8b-instruct	$0.17	$0.17	Not listed	128,000
pioneer	meta-llama/Llama-3.1-8B-Instruct	$0.20	$0.20	$0.20	128,000
merge-gateway	meta/llama-3.1-8b-instruct	$0.22	$0.22	Not listed	128,000

Show all 14 providers ↓

Provider	Provider model id	Input	Output	Cache read	Context
wandb	meta-llama/Llama-3.1-8B-Instruct	$0.22	$0.22	$0.22	131,072
nvidia	meta/llama-3.1-8b-instruct	Not listed	Not listed	Not listed	16,000

04History

Change history

12+ recent events since 2024-07-23

2026-08-26ContextwandbContext window—→ 131,072

2026-08-26ContextwandbMax output128,000→ 131,072

2026-08-25ContextkiloMax output131,072→ 117,964

2026-08-25ContextopenrouterMax output131,072→ 117,964

2026-08-19ContextpioneerContext window131,072→ 128,000

2026-08-19ContextpioneerMax output16,384→ 8,192

2026-08-14Removedcloudflare-ai-gatewayofferingremoved→ new

2026-08-14ContextcortecsContext window128,000→ new

2026-08-14Addedhuggingfaceoffering→ new

2026-08-14Addedmerge-gatewayoffering→ new

2026-08-14ContextwandbContext window128,000→ new

2026-08-08ContextneonMax output16,384→ 8,192

05Usage

Monthly token share

Rank #87 · 2026-07

0.0%