ZappushZappush
SkillsUse CasesBenchmarkCommunity
← Meta Models

Meta

Llama 3.1 8b Instruct

meta-llama/llama-3.1-8b-instruct

16.4K context·16.4K max output·text->text

Input

$0.0200

per 1M tokens

Output

$0.0500

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

GoodValue: -66.7

Coding

Code generation, completion, debugging

46.6

Math

Competition math, calculus, olympiad

46.6

Reasoning

Logic, spatial, puzzle solving

46.6

Language

Summarization, paraphrase, writing

46.6

Overall

46.6

Source: LiveBench (livebench.ai) / Scores 0-100

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

Gemma 3n E4b It

Google

$0.0200 in$0.0400 out32.8K

Llama 3.2 1b Instruct

Meta

$0.0270 in$0.2000 out60K

GPT Oss 20b

OpenAI

$0.0300 in$0.1100 out131.1K

More from Meta

Llama Guard 3 8b

$0.0200 / $0.0600

Llama 3.2 1b Instruct

$0.0270 / $0.2000

Llama 3 8b Instruct

$0.0300 / $0.0400

Llama 3.2 11b Vision Instruct

$0.0490 / $0.0490

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.

Deploy Your Agent
Zappush© 2026 Zappush
HomeSkillsUse CasesBenchmarkGuarantee