Scaleway: Models Intelligence, Performance & Price
Analysis of Scaleway's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Scaleway for your use-case.
Most Intelligent
Updated
Intelligence index
Total 10 models
Fastest
Output speed
Total 10 models
Lowest Price
Blended price (per 1M tokens)
Total 10 models
Scaleway offers 10 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Scaleway are GLM-5.2 (max) (51), GLM-5.2 (34), Qwen3.6 35B A3B (32).
- For output speed, the fastest models are gpt-oss-120b (high) (170 t/s), Qwen3.6 35B A3B (168 t/s), Qwen3 Coder 30B A3B (152 t/s).
- For latency, Gemma 4 26B A4B (0.93s), Qwen3 Coder 30B A3B (1.00s), Qwen3.6 35B A3B (1.06s) offer the lowest time to first answer token.
- For pricing, gpt-oss-120b (high) ($0.22), Llama 3.1 8B ($0.23), Gemma 4 26B A4B ($0.28) offer the lowest blended prices per 1M tokens.
- For context window size, GLM-5.2 (max) (262k), GLM-5.2 (262k), Qwen3.6 35B A3B (262k) support the largest context windows on Scaleway.
- gpt-oss-120b (high) offers both the fastest output and best pricing, making it attractive for throughput-sensitive and cost-conscious applications. GLM-5.2 (max) leads in intelligence for tasks that require the highest quality.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, task all-pass rate
Agentic business operations
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence vs. Price
Context Window
Context Window
Pricing
Intelligence vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
GLM-5.2 (max) | 262k | Open | 51 | $2.52 | 81 | 1.64 | 32.41 | 24.62 | |||
GLM-5.2 | 262k | Open | 34 | $2.52 | 75 | 1.76 | 8.39 | -- | |||
Qwen3.6 35B A3B | 262k | Open | 32 | $0.44 | 168 | 1.01 | 36.20 | 32.20 | |||
Qwen3.6 35B A3B | 262k | Open | 24 | $0.44 | 138 | 1.03 | 4.64 | -- | |||
gpt-oss-120b (high) | 128k | Open | 24 | $0.22 | 170 | 1.22 | 15.93 | 11.77 | |||
Gemma 4 26B A4B | 262k | Open | 20* | $0.28 | 137 | 0.97 | 4.62 | -- | |||
Qwen3 235B 2507 | 250k | Open | 18* | $1.04 | 85 | 1.45 | 7.34 | -- | |||
Qwen3 Coder 30B A3B | 128k | Open | 14* | $0.30 | 152 | 1.00 | 4.28 | -- | |||
 DeepSeek R1 Distill Llama 70B | 32k | Open | 10* | $1.05 | -- | -- | -- | -- | |||
Llama 3.3 70B | 100k | Open | 9 | $1.05 | 86 | 1.38 | 7.17 | -- | |||
Llama 3.1 8B | 128k | Open | 8 | $0.23 | 147 | 1.10 | 4.51 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Scaleway
Scaleway offers 10 models that we track: GLM-5.2 (max), GLM-5.2, Qwen3.6 35B A3B, Qwen3.6 35B A3B, gpt-oss-120b (high), Gemma 4 26B A4B, Qwen3 235B 2507, Qwen3 Coder 30B A3B, Llama 3.3 70B, and Llama 3.1 8B.
The most intelligent model available on Scaleway is GLM-5.2 (max) with an Intelligence Index score of 51.
The fastest model on Scaleway by output speed is gpt-oss-120b (high) at 169.9 tokens per second.
The model with the lowest time to first answer token on Scaleway is Gemma 4 26B A4B at 0.93s. Lower latency means faster initial response time.
The most affordable model on Scaleway by blended price is gpt-oss-120b (high) at $0.22 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Scaleway vary up to 11x across models, from $0.22 per 1M tokens for gpt-oss-120b (high) to $2.52 per 1M tokens for GLM-5.2.
Yes, Scaleway offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 10 models on Scaleway support JSON mode for structured output.
Yes, all 10 models on Scaleway support function calling (tool use).
Yes, Scaleway offers 3 reasoning models: GLM-5.2 (max), Qwen3.6 35B A3B, and gpt-oss-120b (high). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 10 models on Scaleway are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Scaleway, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.