Model Catalogopenrouter

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

CHAT Light tier Chat

Meta: Llama 3.3 70B Instruct (meta-llama/llama-3.3-70b-instruct) is a chat model from openrouter with a 131.1K-token context window; capabilities tools; input text; output text.

131.1KContext
128KMax output
$0.13$ / 1M in
9.4Intelligence
79.187tok / s

Pricing

Input
$0.13 / 1M tokens
Output
$0.4 / 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: openrouter. Last verified 2026-07-24.

Benchmarks

Intelligence index
9.4
Coding
11.9
Math
7.7

Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-24.

Performance

Throughput
79.187 tokens/s
Latency (TTFT)
0.648 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-24.

Specifications

Context window
131,072 tokens (131.1K)
Max output
128,000 tokens
Input modalities
text
Output modalities
text
Knowledge cutoff
2023-12-31

Capabilities

tools

Provenance

artificial-analysiscommittedopenrouter-api
Last verified: 2026-07-24

Related models

MoonshotAI: Kimi K3
moonshotai/kimi-k3
openrouter · CHAT · 1.0M ctx
xAI: Grok 4.5
x-ai/grok-4.5
openrouter · CHAT · 500K ctx
Meta: Muse Spark 1.1
meta/muse-spark-1.1
openrouter · CHAT · 1.0M ctx
Qwen: Qwen3.7 Max
qwen/qwen3.7-max
openrouter · CHAT · 1M ctx
Xiaomi: MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro
openrouter · CHAT · 1.0M ctx
Tencent: Hy3
tencent/hy3
openrouter · CHAT · 262.1K ctx