Overview
Model specifications
- Context
- 128,000 tokens
- Maximum output
- 2,048 tokens
- Architecture
- text+image->text
- Tokenizer
- Other
- Knowledge cutoff
- 2025-01-31
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.1 /M tokens
- Output
- $0.2 /M tokens
- Cache read
- $0.1 /M tokens
API
Quick start
Call this exact model ID through OpenRouter’s OpenAI-compatible API.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"bytedance/ui-tars-1.5-7b","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
imagetext
Output
text
API
Supported API parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyseedstopstructured_outputstemperaturetop_ktop_logprobstop_pAvailable providers
1 Provider
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Parasail
bf16- Context
- 128K
- Maximum output
- 2K
- Input
- $0.100
- Output
- $0.200
- Cache read
- $0.100
- Cache write
- Not provided