Near AI
- Cheapest on
- 2
- 25% of its models
- Median premium
- +30%
- vs reference price
- Models
- 8
- served today
- Live offers
- 8
- priced endpoints
Offers
| Model | Input | Output | Blended | Premium | Context | Since |
|---|---|---|---|---|---|---|
| gpt-oss-120b (batch) near-ai/fp4 | $0.03 | $0.15 | $0.06 | — | Oct 16 | |
| gpt-oss-120b near-ai/fp4 | $0.03 | $0.15 | $0.06 | — | Oct 16 | |
| GLM 5.3 Flash (batch) near-ai/fp8 | $0.08 | $0.50 | $0.185 | — | Oct 13 | |
| GLM 5.3 Flash near-ai/fp8 | $0.08 | $0.50 | $0.185 | — | Oct 13 | |
| Qwen3.8 27B (batch) near-ai/fp8 | $0.04 | $1.35 | $0.368 | — | Nov 7 | |
| Qwen3.8 27B near-ai/fp8 | $0.04 | $1.35 | $0.368 | — | Oct 9 | |
| DeepSeek V4.1 Flash 1017 (batch) near-ai | $0.30 | $1.20 | $0.525 | — | Nov 8 | |
| DeepSeek V4.1 Flash 1017 near-ai | $0.30 | $1.20 | $0.525 | — | Oct 31 |
- gpt-oss-120b (batch)$0.03 in · $0.15 out · fp4$0.06—
- gpt-oss-120b$0.03 in · $0.15 out · fp4$0.06—
- GLM 5.3 Flash (batch)$0.08 in · $0.50 out · fp8$0.185—
- GLM 5.3 Flash$0.08 in · $0.50 out · fp8$0.185—
- Qwen3.8 27B (batch)$0.04 in · $1.35 out · fp8$0.368—
- Qwen3.8 27B$0.04 in · $1.35 out · fp8$0.368—
- DeepSeek V4.1 Flash 1017 (batch)$0.30 in · $1.20 out$0.525—
- DeepSeek V4.1 Flash 1017$0.30 in · $1.20 out$0.525—
Recent changes
- ListedNow served,Listed
- ListedNow served,Listed
- ListedNow served,Listed
- PriceDiscount price,30%→——
- PriceCache read price,$0.0245→$0.012−51.0%
- PriceOutput price,$0.35→$0.50+42.9%
- PriceInput price,$0.105→$0.08−23.8%
- PriceDiscount price,30%→——
- PriceCache read price,$0.0245→$0.012−51.0%
- PriceOutput price,$0.35→$0.50+42.9%
- PriceInput price,$0.105→$0.08−23.8%
- ListedNow served,Listed