- Models
- 10
- listed and live
- Location
- EU
- where requests are served
- Trains on prompts
- Not declared
- nothing published yet
- Keeps prompts
- Not declared
- nothing published yet
Models
What Scaleway serves on llm.buzz, at its own prices.
| Model | Input | Output | Cache read | Context | Latency | Uptime (3d) |
|---|---|---|---|---|---|---|
 deepseek/deepseek-v4-flash-0731 | $0.461 | $0.9219 | $0.0922 | 256K | 0.40 s | 100% |
deepseek/deepseek-v4.1-flash | $0.6915 | $2.0743 | $0.1383 | 256K | 0.40 s | 95.8% |
 google/gemma-4-26b-a4b-it | $0.2881 | $0.5762 | n/a | 256K | 0.23 s | 100% |
 mistralai/mistral-medium-3-5 | $1.7286 | $8.6428 | n/a | 180K | 0.58 s | 100% |
mistralai/mistral-small-3.2-24b-instruct | $0.1729 | $0.4034 | n/a | 128K | 0.19 s | 100% |
 openai/gpt-oss-120b | $0.1729 | $0.6915 | n/a | 128K | 0.23 s | 100% |
openai/whisper-large-v3 | $57.6182/M seconds | n/a | n/a | n/a | n/a | n/a |
 qwen/qwen3.6-35b-a3b | $0.2881 | $1.7286 | n/a | 256K | 0.28 s | 100% |
qwen/qwen3.8-27b | $0.6915 | $3.8029 | $0.1383 | 256K | 0.23 s | 100% |
 z-ai/glm-5.3 | $2.0743 | $6.3381 | n/a | 256K | 0.28 s | 100% |
Scaleway's own prices, in USD per million tokens unless a price names another unit. Latency is the median time to first token over 24 hours.
Call Scaleway's models with one keyThe same key reaches every provider here; each request pays the price of the provider that answered it.