Hy4 preview
- Input / output
- $0.751 / $2.25
- Providers
- 6
- Spread
- 1.32×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 1M
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
TencentCheapest fp8 | $0.751 | $2.25 | $1.13 | −5.3% | |||
| fp4 | $0.834 | $2.501 | $1.25 | +5.3% | |||
| bf16 | $0.834 | $2.501 | $1.25 | +5.3% | |||
| fp8 | $0.834 | $2.501 | $1.25 | +5.3% | |||
| fp8 | $0.834 | $2.501 | $1.25 | +5.3% | |||
| fp4 | $1.04 | $3.13 | $1.56 | +32% |
- TencentCheapest$1.13$0.751 in · $2.25 out−5.3% vs ref1M ctx100% uptimefp8
- $1.25$0.834 in · $2.501 out+5.3% vs ref1M ctx99.9% uptimefp4
- $1.25$0.834 in · $2.501 out+5.3% vs ref256K ctx100% uptimebf16
- $1.25$0.834 in · $2.501 out+5.3% vs ref1M ctx100% uptimefp8
- $1.25$0.834 in · $2.501 out+5.3% vs ref1M ctx100% uptimefp8
- $1.56$1.04 in · $3.13 out+32% vs ref1M ctx100% uptimefp4
Blended = (3 × input + output) / 4. Ref $1.19 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Long-context pricing
| Offered by | Prompt size | Input | Output |
|---|---|---|---|
| Tencent | base | $0.751 | $2.25 |
| > 0 | $0.834 | $2.501 | |
| > 0 | $0.751 | $2.25 |
Other pricing
| Offered by | Cache read |
|---|---|
| Tencent | $0.0378 |
| DeepInfra, GMICloud +2 | $0.042 |
| Venice | $0.0525 |
Changes
- PriceCache read price,$0.042→$0.0378−10.0%
- PriceOutput price,$2.501→$2.25−10.0%
- PriceInput price,$0.834→$0.751−10.0%
- PriceCache read price,$0.0378→$0.042+11.1%
- PriceOutput price,$2.25→$2.501+11.1%
- PriceInput price,$0.751→$0.834+11.1%
- PriceCache read price,$0.042→$0.0378−10.0%
- PriceOutput price,$2.501→$2.25−10.0%
- PriceInput price,$0.834→$0.751−10.0%
- PriceCache read price,$0.0378→$0.042+11.1%
- PriceOutput price,$2.25→$2.501+11.1%
- PriceInput price,$0.751→$0.834+11.1%
- PriceCache read price,$0.042→$0.0378−10.0%
- PriceOutput price,$2.501→$2.25−10.0%
- PriceInput price,$0.834→$0.751−10.0%
About
The cheapest provider for Hy4 preview is Tencent at $1.13 per 1M tokens (blended), charging $0.751 per 1M input and $2.25 per 1M output tokens. 6 providers serve it; the most expensive charges 1.32× the typical price. Context window: 1M tokens. Prices tracked since Oct 3, 2026.
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
- Released
- Aug 28, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- tencent/hy4-preview-20260827
- Weights
- tencent/Hy4-preview