Overview
Model specifications
- Context
- 128,000 tokens
- Maximum output
- 115,200 tokens
- Architecture
- text+image->text
- Tokenizer
- Qwen
- Knowledge cutoff
- 2024-06-30
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.8 per 1M tokens
- Output
- $1 per 1M tokens
- Cache read
- $0.4 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":"qwen/qwen2.5-vl-72b-instruct","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
textimage
Output
text
API
Supported API parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_pAvailable 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.
Parasail
fp8- Context
- 128K
- Maximum output
- 115K
- Input
- $0.8
- Output
- $1
- Cache read
- $0.4
- Cache write
- Not provided