Model specifications
- Context
- 1,048,576 tokens
- Maximum output
- 65,536 tokens
- Architecture
- text+image->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.035 per 1M tokens
- Output
- $0.1405 per 1M tokens
- Cache read
- $0.0015 per 1M tokens
Model configuration
Reasoning
- Reasoning required
- No
- Default parameters
- Yes
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":"tencent/hy4-flash","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Yes
Supported API parameters
include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetools1 Provider
Checked: November 19, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Tencent
fp8- Context
- 1.0M
- Maximum output
- 66K
- Input
- $0.035
- Output
- $0.1405
- Cache read
- $0.0015
- Cache write
- Not provided