Overview
Model specifications
- Context
- 16,385 tokens
- Maximum output
- 4,096 tokens
- Architecture
- text->text
- Tokenizer
- GPT
- Knowledge cutoff
- 2021-09-30
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $3 per 1M tokens
- Output
- $4 per 1M tokens
API
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-3.5-turbo-16k","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
API
Supported API parameters
frequency_penaltylogit_biaslogprobsmax_completion_tokensmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_pAvailable providers
2 providers
Checked: October 19, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Azure
Not provided- Context
- 16K
- Maximum output
- 4K
- Input
- $3
- Output
- $4
- Cache read
- Not provided
- Cache write
- Not provided
OpenAI
Not provided- Context
- 16K
- Maximum output
- 4K
- Input
- $3
- Output
- $4
- Cache read
- Not provided
- Cache write
- Not provided