Hy4 Flash via the Tokenator API
What the model is for
Hy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent pipelines, document and chart comprehension, and high-volume routine automation, with the same context and output limits as Hy4.
Specification
| Full name | Hy4 Flash |
| API ID | hy4-flash |
| Model vendor | Tencent |
| Type | Text model (chat / completions) |
| Context window | 1.05M tokens |
| Max output | 65.5K tokens |
| Image input | yes |
| Tokenator usage multiplier | 0.3× |
| Output token multiplier | 0.6× |
| Badge | NEW |
| Input modalities | text, image |
| Aliases | cursor-hy4-flash |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-22 |
Benchmarks
| Vals Finance Index (Vals AI) | 52.7% |
| Vals Index (Vals AI) | 50.8% |
| Vals Legal Index (Vals AI) | 68.3% |
| Terminal-Bench 4.0 (Vals AI) | 15.2% |
| Vibe Code Bench v1.1 (Vals AI) | 74.8% |
| EMB v1.1 (Vals AI) | 63% |
| Finance Agent v2.1 (Vals AI) | 60.8% |
| Tax Agent Bench (Vals AI) | 23.3% |
| HLAB-Vals-1.1 (Vals AI) | 5.4% |
| Legal Research Bench (Vals AI) | 38.5% |
Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier | Output token multiplier |
|---|---|---|
| AiPartners Ltd | 0.3× | 0.6× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "hy4-flash", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.
See also
FAQ about Hy4 Flash
What is the API ID of Hy4 Flash?
hy4-flash — put this into the model field of your request.
What context window does Hy4 Flash have?
1.05M tokens; max output is 65.5K tokens.
How many tokens will a request cost?
(input × 0.3×) + (output × 0.6×). See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.