Model Catalog › openrouter

Llama 3 70B Instruct (via OpenRouter)

meta-llama/llama-3-70b-instruct

CHAT Mid tier Chat

Llama 3 70B Instruct (via OpenRouter) (meta-llama/llama-3-70b-instruct) is a chat model from openrouter with a 8.2K-token context window; input text.

8.2KContext

8KMax output

$0.59$ / 1M in

3.5Intelligence

44.571tok / s

Pricing

Input: $0.59 / 1M tokens
Output: $0.79 / 1M tokens
Currency: USD
Note: Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.

Benchmarks

Intelligence index: 3.5

Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.

Performance

Throughput: 44.571 tokens/s
Latency (TTFT): 0.614 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.

Specifications

Context window: 8,192 tokens (8.2K)
Max output: 8,000 tokens
Input modalities: text

Provenance

artificial-analysiscommittedoverrides

Last verified: 2026-07-22

Related models

Claude 3 Haiku (via OpenRouter)

anthropic/claude-3-haiku

openrouter · CHAT · 200K ctx

Gemini 2.0 Flash (via OpenRouter)

google/gemini-2.0-flash-001

openrouter · CHAT · 1.0M ctx

Claude Sonnet 4.5 (via OpenRouter)

anthropic/claude-sonnet-4.5

openrouter · CHAT · 1M ctx

GPT-4o (via OpenRouter)

openai/gpt-4o

openrouter · CHAT · 128K ctx

DeepSeek Chat (via OpenRouter)

deepseek/deepseek-chat

openrouter · CHAT · 65.5K ctx

Markdown · Vendor JSON · Full catalog · All openrouter models