FriendliAI: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by FriendliAI for your use-case.
Most Intelligent
GLM-5.3 (max)GLM-5.3-FlashIntelligence Index
Total 8 models
Fastest
GLM-5.3-FlashGLM-5.2 (max)GLM-5.1GLM-5.3 (max)GLM-5.1 (non-reasoning)Output speed
Total 8 models
Lowest Price
GLM-5.3-Flash
Gemma 4 31BGemma 4 31B (non-reasoning)
DeepSeek V3.2 (non-reasoning)GLM-5.3 (max)Blended price (per 1M tokens)
Total 8 models
FriendliAI offers 8 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 FriendliAI are GLM-5.3 (max) (32) and GLM-5.3-Flash (28).
- For output speed, the fastest models are GLM-5.3-Flash (236 t/s), GLM-5.2 (max) (188 t/s), and GLM-5.1 (145 t/s). Speed varies significantly across models, with a 74% difference between the fastest and slowest.
- For latency, GLM-5.1 (non-reasoning) (0.82s), DeepSeek V3.2 (non-reasoning) (1.06s), and Gemma 4 31B (non-reasoning) (1.20s) offer the lowest time to first answer token.
- For pricing, GLM-5.3-Flash ($0.10), Gemma 4 31B ($0.17), and Gemma 4 31B (non-reasoning) ($0.17) offer the lowest blended prices per 1M tokens. Prices vary up to 8.0x across models.
- For context window size, GLM-5.3 (max) (1M), GLM-5.3-Flash (1M), and GLM-5.2 (max) (1M) support the largest context windows on FriendliAI.
- GLM-5.3-Flash offers both the fastest output and best pricing, making it attractive for throughput-sensitive and cost-conscious applications. GLM-5.3 (max) leads in intelligence for tasks that require the highest quality.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
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
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
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-5.3 (max) | 1M | Open | 32 | $4.53 | 139 | 0.94 | 18.91 | 14.37 | |||
GLM-5.3-Flash | 1M | Open | -- | -- | 303 | 0.62 | 8.88 | 6.61 | |||
 MiniMax-M2.1 | 197k | Open | -- | -- | -- | -- | -- | -- | |||
GLM-5.1 | 203k | Open | -- | -- | 129 | 0.86 | 34.03 | 29.30 | |||
DeepSeek V3.2 (non-reasoning) | 164k | Open | -- | -- | 79 | 1.09 | 7.46 | -- | |||
GLM-5.1 (non-reasoning) | 203k | Open | -- | -- | 125 | 0.85 | 4.85 | -- | |||
Gemma 4 31B | 256k | Open | -- | -- | 116 | 1.31 | 20.64 | 15.00 | |||
Gemma 4 31B (non-reasoning) | 262k | Open | -- | -- | 101 | 0.92 | 5.89 | -- | |||
GLM-5.2 (max) | 1M | Open | -- | -- | 191 | 0.95 | 14.06 | 10.49 | |||
Key definitions
Frequently Asked Questions
Common questions about FriendliAI
FriendliAI offers 8 models that we track: GLM-5.3 (max), GLM-5.3-Flash, GLM-5.1, DeepSeek V3.2 (non-reasoning), GLM-5.1 (non-reasoning), Gemma 4 31B, Gemma 4 31B (non-reasoning), and GLM-5.2 (max).
The most intelligent model available on FriendliAI is GLM-5.3 (max) with an Intelligence Index score of 32.
The fastest model on FriendliAI by output speed is GLM-5.3-Flash at 236.2 tokens per second.
The model with the lowest time to first answer token on FriendliAI is GLM-5.1 (non-reasoning) at 0.82s. Lower latency means faster initial response time.
The most affordable model on FriendliAI by blended price is GLM-5.3-Flash at $0.10 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on FriendliAI vary up to 9x across models, from $0.10 per 1M tokens for GLM-5.3-Flash to $0.90 per 1M tokens for GLM-5.2 (max).
Yes, FriendliAI offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 8 models on FriendliAI support JSON mode for structured output.
Yes, all 8 models on FriendliAI support function calling (tool use).
Yes, FriendliAI offers 5 reasoning models: GLM-5.3 (max), GLM-5.3-Flash, GLM-5.1, Gemma 4 31B, and GLM-5.2 (max). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 8 models on FriendliAI 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 FriendliAI, 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.