Model specifications
- Context
- 1,050,000 tokens
- Maximum output
- 128,000 tokens
- Architecture
- text+image+file->text
- Tokenizer
- GPT
- Knowledge cutoff
- Not provided
- Moderated
- Yes
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $8 per 1M tokens
- ≤272K$8
- >272K$16
- Output
- $40 per 1M tokens
- ≤272K$40
- >272K$60
- Cache read
- $0.4 per 1M tokens
- ≤272K$0.4
- >272K$0.8
- Cache write
- $10 per 1M tokens
- ≤272K$10
- >272K$20
- Web search
- $10 per 1,000 calls
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- medium
- Capabilities
- max, xhigh, high, medium, low
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-6.2-astra-pro","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Yes · max · xhigh · high · medium · low
Supported API parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity6 providers
Checked: November 18, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
OpenAI
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $8
- Output
- $40
- Cache read
- $0.4
- Cache write
- $10
Azure
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $8
- Output
- $40
- Cache read
- $0.4
- Cache write
- $10
Azure
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $8.8
- Output
- $44
- Cache read
- $0.44
- Cache write
- $11
Azure
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $9.6
- Output
- $48
- Cache read
- $0.48
- Cache write
- $12
OpenAI
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $16
- Output
- $80
- Cache read
- $0.8
- Cache write
- $20
OpenAI
Not provided- Context
- 1.1M
- Maximum output
- 128K
- Input
- $24
- Output
- $120
- Cache read
- $1.2
- Cache write
- $30