Wafer: Models Intelligence, Performance & Price
Analysis of Wafer'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 Wafer for your use-case.
Most Intelligent
Intelligence index
Total 7 models
Fastest
Output speed
Total 7 models
Lowest Price
Blended price (per 1M tokens)
Total 7 models
Wafer offers 7 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 Wafer are Kimi K3 (max) (FAST) (57), GLM-5.2 (max) (51), and GLM-5.1 (40).
- For output speed, the fastest models are Kimi K3 (max) (FAST) (194 t/s), GLM-5.2 (184 t/s), and GLM-5.2 (max) (161 t/s). Speed varies significantly across models, with a 122% difference between the fastest and slowest.
- For latency, GLM-5.1 (1.24s), Qwen3.5 397B A17B (2.39s), and GLM-5.2 (5.78s) offer the lowest time to first answer token.
- For pricing, Qwen3.5 397B A17B ($0.37), Qwen3.5 397B A17B ($0.37), and GLM-5.1 ($0.59) offer the lowest blended prices per 1M tokens. Prices vary up to 2.1x across models.
- For context window size, Kimi K3 (max) (FAST) (1M), Qwen3.5 397B A17B (262k), and Qwen3.5 397B A17B (262k) support the largest context windows on Wafer.
- Kimi K3 (max) (FAST) offers the best combination of intelligence and speed. For cost optimization, Qwen3.5 397B A17B provides the most competitive pricing.
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, criterion pass rate
Agentic business operations
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index 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 | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Kimi K3 (max) (FAST) | 1M | Open | 57 | $1.30 | 194 | 0.87 | 13.74 | 10.30 | |||
GLM-5.2 (max) | 205k | Open | 51 | $0.36 | 161 | 5.84 | 21.37 | 12.42 | |||
GLM-5.1 | 203k | Open | 40 | $0.15 | 88 | 1.27 | 50.24 | 43.27 | |||
GLM-5.1 | 203k | Open | 35* | -- | 89 | 1.24 | 6.84 | -- | |||
GLM-5.2 | 205k | Open | 34 | -- | 184 | 5.78 | 8.50 | -- | |||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.13 | 66 | 2.28 | 58.48 | 48.58 | |||
Qwen3.5 397B A17B | 262k | Open | 32* | -- | 63 | 2.39 | 10.30 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Wafer
Wafer offers 7 models that we track: Kimi K3 (max) (FAST), GLM-5.2 (max), GLM-5.1, GLM-5.1, GLM-5.2, Qwen3.5 397B A17B, and Qwen3.5 397B A17B.
The most intelligent model available on Wafer is Kimi K3 (max) (FAST) with an Intelligence Index score of 57.
The fastest model on Wafer by output speed is Kimi K3 (max) (FAST) at 194.1 tokens per second.
The model with the lowest time to first answer token on Wafer is GLM-5.1 at 1.24s. Lower latency means faster initial response time.
The most affordable model on Wafer by blended price is Qwen3.5 397B A17B at $0.37 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Wafer vary up to 9x across models, from $0.37 per 1M tokens for Qwen3.5 397B A17B to $3.46 per 1M tokens for Kimi K3 (max) (FAST).
Yes, Wafer offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 7 models on Wafer support JSON mode for structured output.
Yes, all 7 models on Wafer support function calling (tool use).
Yes, Wafer offers 4 reasoning models: Kimi K3 (max) (FAST), GLM-5.2 (max), GLM-5.1, and Qwen3.5 397B A17B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 7 models on Wafer 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 Wafer, 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.