Overview
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
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $5 per 1M tokens
- ≤272K$5
- >272K$10
- Output
- $25 per 1M tokens
- ≤272K$25
- >272K$37.5
- Cache read
- $0.5 per 1M tokens
- ≤272K$0.5
- >272K$1
- Cache write
- $6.25 per 1M tokens
- ≤272K$6.25
- >272K$12.5
- Web search
- $10 per 1,000 calls
API
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- medium
- Capabilities
- max, xhigh, high, medium, low
API
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
This submits an asynchronous batch using the base model ID. A job ID confirms submission, not completion.
curl --fail-with-body https://openrouter.ai/api/beta/batches \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"endpoint":"/v1/chat/completions","model":"openai/gpt-6-astra-pro","requests":[{"custom_id":"request-1","body":{"messages":[{"role":"user","content":"Hello!"}]}}]}'
# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/beta/batches/JOB_ID" \
-H "Authorization: Bearer $OPENROUTER_API_KEY"Capabilities
Input → Output
Input
fileimagetext
Output
text
Reasoning
Yes · max · xhigh · high · medium · low
API
Supported API parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsAvailable providers
1 Provider
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
- 1.1M
- Maximum output
- 128K
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25