Overview

Model specifications

Context: 131,072 tokens
Maximum output: 16,384 tokens
Architecture: text->text
Tokenizer: Llama3
Knowledge cutoff: 2023-12-31
Moderated: No

OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input: $0.85
Output: $0.85

API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sao10k/l3.1-euryale-70b","messages":[{"role":"user","content":"Hello!"}]}'

Capabilities

Input → Output

Input

text

Output

text

API

Supported API parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Available providers

2 providers

Checked: September 15, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp8

Context: 131K
Maximum output: 16K
Input: $0.85
Output: $0.85
Cache read: Not provided
Cache write: Not provided

Novita

fp8

Context: 8K
Maximum output: 7K
Input: $1.4504
Output: $1.4504
Cache read: Not provided
Cache write: Not provided

Sao10K: Llama 3.1 Euryale 70B v2.2

Model specifications

Complete pricing

Quick start

Input → Output

Supported API parameters

2 providers

DeepInfra

Novita

2 models

Sao10K: Llama 3.3 Euryale 70B

Sao10K: Llama 3 8B Lunaris