- Models
- 11
- listed and live
- Location
- Non-EU
- where requests are served
- Trains on prompts
- Not declared
- nothing published yet
- Keeps prompts
- Not declared
- nothing published yet
Models
What Prime Intellect serves on llm.buzz, at its own prices.
| Model | Input | Output | Cache read | Context | Latency | Uptime (3d) |
|---|---|---|---|---|---|---|
 deepseek/deepseek-v4-flash-0731 | $0.44 | $1.32 | n/a | 1M | 0.69 s | 98.6% |
deepseek/deepseek-v4.1-flash | $0.30 | $1.20 | $0.006 | 1M | 0.48 s | 100% |
deepseek/deepseek-v4.1-flash-1017 | $0.30 | $1.20 | $0.006 | 1M | 0.48 s | 100% |
 moondream/moondream3-preview | $0.30 | $2.50 | n/a | 32K | 0.33 s | 98.6% |
moondream/moondream3.1-9b-a2b | $0.30 | $2.50 | n/a | 32K | 0.28 s | 100% |
 moonshotai/kimi-k3 | $3.45 | $17.25 | n/a | 1M | 0.83 s | 98.6% |
 Qwen: Qwen3.5-0.8BPaused qwen/qwen3.5-0.8b | $0.04 | $0.08 | $0.004 | 64K | n/a | 66% |
Qwen: Qwen3.5-2BPaused qwen/qwen3.5-2b | $0.06 | $0.18 | $0.006 | 64K | n/a | 67.9% |
Qwen: Qwen3.5-4BPaused qwen/qwen3.5-4b | $0.10 | $0.30 | $0.01 | 64K | n/a | 67.9% |
Qwen: Qwen3.5-9BPaused qwen/qwen3.5-9b | $0.18 | $0.54 | $0.018 | 64K | n/a | 67.3% |
qwen/qwen3.6-35b-a3b | $0.25 | $1.25 | n/a | 256K | 0.48 s | 94.5% |
qwen/qwen3.8-27b | $0.99 | $3.20 | n/a | 256K | 0.83 s | 97.2% |
qwen/qwen3.8-flash | $0.225 | $0.705 | n/a | 1M | 1.44 s | 100% |
 z-ai/glm-5.3 | $0.98 | $3.08 | $0.182 | 1M | 0.58 s | 100% |
z-ai/glm-5.3-flash | $0.15 | $0.50 | $0.03 | 1M | 0.69 s | 100% |
Prime Intellect's own prices, in USD per million tokens. Latency is the median time to first token over 24 hours.
n/a: not enough traffic to show yet.
Call Prime Intellect's models with one keyThe same key reaches every provider here; each request pays the price of the provider that answered it.