Overview

Model specifications

Context: 8,192 tokens
Maximum output: 3,686 tokens
Architecture: text->text
Tokenizer: Llama2
Knowledge cutoff: 2023-06-30
Moderated: No

OPENROUTER

Complete pricing

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

Input: $0.08
Output: $0.11

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":"gryphe/mythomax-l2-13b","messages":[{"role":"user","content":"Hello!"}]}'

Capabilities

Input → Output

Input

text

Output

text

API

Supported API parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_atop_ktop_logprobstop_p

Available providers

3 providers

Checked: September 17, 2026

Live providers on OpenRouter

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

OpenRouter

Parasail

fp16

Context: 4K
Maximum output: 4K
Input: $0.08
Output: $0.11
Cache read: Not provided
Cache write: Not provided

Mancer 2

fp8

Context: 8K
Maximum output: 7K
Input: $0.35
Output: $0.6
Cache read: Not provided
Cache write: Not provided

DeepInfra