← All models

gemini-3.6-flash-thinking:payg

Chat Vision Tool calling Streaming Codex

Variant

metered metered:full-context payg

Cost415 in / 2,073.5 out per 1M

Minimum planBasic

Context window1,048,576

Max output65,536

Uptime (7d)89.6%

Latency5323 ms

Throughput19.2 tps

Latency your local time

Use this model

Base URL https://api.literouter.com/v1

Model gemini-3.6-flash-thinking:payg

API key your LiteRouter API key

Using SillyTavern, Janitor AI, or Chub? See the setup guides.

bash

curl https://api.literouter.com/v1/chat/completions \
  -H "Authorization: Bearer $LITEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.6-flash-thinking:payg",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Add the provider to ~/.codex/config.toml, export your key, then run codex. Full steps: Codex CLI.

toml

# ~/.codex/config.toml
model = "gemini-3.6-flash-thinking:payg"
model_provider = "literouter"

[model_providers.literouter]
base_url = "https://api.literouter.com/v1"
env_key = "LITEROUTER_API_KEY"
wire_api = "responses"

bash

export LITEROUTER_API_KEY="your_literouter_api_key"