Overview
Model specifications
- Context
- 400,000 tokens
- Maximum output
- 128,000 tokens
- Architecture
- text+image+file->text
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-05-31
- Moderated
- Yes
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.05 per 1M tokens
- Output
- $0.4 per 1M tokens
- Cache read
- $0.005 per 1M tokens
API
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- medium
- Capabilities
- high, medium, low, minimal
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-5-nano","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
textimagefile
Output
text
Reasoning
No · high · medium · low · minimal
API
Supported API parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsAvailable providers
4 providers
Checked: September 7, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
OpenAI
Not provided- Context
- 400K
- Maximum output
- 128K
- Input
- $0.025
- Output
- $0.2
- Cache read
- $0.0025
- Cache write
- Not provided
Azure
Not provided- Context
- 400K
- Maximum output
- 360K
- Input
- $0.05
- Output
- $0.4
- Cache read
- $0.01
- Cache write
- Not provided
OpenAI
Not provided- Context
- 400K
- Maximum output
- 128K
- Input
- $0.05
- Output
- $0.4
- Cache read
- $0.005
- Cache write
- Not provided
Azure
Not provided- Context
- 400K
- Maximum output
- 360K
- Input
- $0.055
- Output
- $0.44
- Cache read
- $0.011
- Cache write
- Not provided