Hy4 preview
llmgateway/hy4-preview · family Hy · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.25
Blended $/1M (3:1)
$0.834
Input $/1M
$2.5
Output $/1M
$3.33
1M in + 1M out
$0.042 −95%
Cache read $/1M
#4438 of 7,708
Cheapest rank
- Provider
- DevPass (LLM Gateway) (
llmgateway) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 64,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Hy4 preview” is offered by 10 providers — cheapest-effective first. Vancine is the cheapest at $1.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vancine | $0.67 | $2 | $1.00 | 1M |
| DevPass (LLM Gateway) (this) | $0.834 | $2.5 | $1.25 | 1M |
| Kilo Gateway | $0.834 | $2.5 | $1.25 | 1M |
| OpenRouter | $0.834 | $2.5 | $1.25 | 1M |
| Hugging Face | $0.834 | $2.5 | $1.25 | 1M |
| Tencent TokenHub | $0.834 | $2.5 | $1.25 | 1M |
| OpenCode Go | $0.834 | $2.5 | $1.25 | 1M |
| Tencent Token Plan | $0.834 | $2.5 | $1.25 | 1M |
| AIHubMix | $0.845 | $2.54 | $1.27 | 1M |
| CrossModel | $0.96 | $2.88 | $1.44 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at DevPass (LLM Gateway) and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"hy4-preview","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):