Modal: Models Intelligence, Performance & Price

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Modal

This analysis is intended to support you in choosing the best model provided by Modal for your use-case.

Most Intelligent

GLM-5.3 (max)

Kimi K3 (max)

GLM-5.3-Flash

Qwen3.8 2.4T A95B

DeepSeek V4.1 Flash (max)

Intelligence Index

Total 7 models

Fastest

DeepSeek V4.1 Flash (max)

210 t/s

Qwen3.8 2.4T A95B

206 t/s

Inkling (xhigh) (NVFP4)

195 t/s

DeepSeek V4.1 Flash (non-reasoning)

186 t/s

GLM-5.3-Flash

169 t/s

Output speed

Total 7 models

Lowest Price

DeepSeek V4.1 Flash (max)

$0.20

DeepSeek V4.1 Flash (non-reasoning)

$0.20

GLM-5.3-Flash

$0.30

GLM-5.3 (max)

$0.90

Inkling (xhigh) (NVFP4)

$0.93

Blended price (per 1M tokens)

Total 7 models

Modal 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 Modal are GLM-5.3 (max) (45), Kimi K3 (max) (44), and GLM-5.3-Flash (42).
For output speed, the fastest models are DeepSeek V4.1 Flash (max) (210 t/s), Qwen3.8 2.4T A95B (206 t/s), and Inkling (xhigh) (NVFP4) (195 t/s).
For latency, DeepSeek V4.1 Flash (non-reasoning) (0.69s), DeepSeek V4.1 Flash (max) (10.20s), and Qwen3.8 2.4T A95B (10.52s) offer the lowest time to first answer token.
For pricing, DeepSeek V4.1 Flash (max) ($0.20), DeepSeek V4.1 Flash (non-reasoning) ($0.20), and GLM-5.3-Flash ($0.30) offer the lowest blended prices per 1M tokens. Prices vary up to 4.6x across models.
For context window size, Kimi K3 (max) (1M), Inkling (xhigh) (NVFP4) (1M), and GLM-5.3 (max) (1M) support the largest context windows on Modal.
DeepSeek V4.1 Flash (max) 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

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1Updated

Agentic real-world work tasks, (Elo-500)/2000

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

AA-LCR v1.1

Long context reasoning

SciCodeUnder review

Coding

CritPtUnder review

Physics reasoning

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 1.1New

Agentic software engineering in open-source repositories

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

EnterpriseOps-Gym-AA

Agentic business operations

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AA

Medical long context reasoning

MMMU-Pro

Visual reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Pricing

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Cache Behaviour

Cache Hit Rate

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Sep 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Sep 26, 2026

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

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

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)

Most attractive quadrant

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).


									Further Analysis
GLM-5.3 (max)	1M	Open	45	$1.97	108	0.84	23.97	18.50	Model Provider
Kimi K3 (max)	1.05M	Open	44	$3.48	85	1.15	30.71	23.65	Model Provider
GLM-5.3-Flash	1M	Open	42	$0.88	167	0.94	15.92	11.99	Model Provider
Qwen3.8 2.4T A95B	1M	Open	40	$1.96	204	0.81	13.06	9.80	Model Provider
DeepSeek V4.1 Flash (max)	1M	Open	39	$0.52	204	0.66	12.92	9.81	Model Provider
Inkling (xhigh) (NVFP4)	1.05M	Open	25	$0.86	195	1.16	14.00	10.27	Model Provider
DeepSeek V4.1 Flash (non-reasoning)	1M	Open	25	$0.33	186	0.69	3.38	--	Model Provider

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Frequently Asked Questions

Common questions about Modal

Modal offers 7 models that we track: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, DeepSeek V4.1 Flash (max), Inkling (xhigh) (NVFP4), and DeepSeek V4.1 Flash (non-reasoning).

The most intelligent model available on Modal is GLM-5.3 (max) with an Intelligence Index score of 45.

The fastest model on Modal by output speed is DeepSeek V4.1 Flash (max) at 209.6 tokens per second.

The model with the lowest time to first answer token on Modal is DeepSeek V4.1 Flash (non-reasoning) at 0.69s. Lower latency means faster initial response time.

The most affordable model on Modal by blended price is DeepSeek V4.1 Flash (max) at $0.20 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on Modal vary up to 11x across models, from $0.20 per 1M tokens for DeepSeek V4.1 Flash (max) to $2.31 per 1M tokens for Kimi K3 (max).

Yes, Modal offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.

Yes, all 7 models on Modal support JSON mode for structured output.

Yes, all 7 models on Modal support function calling (tool use).

Yes, Modal offers 6 reasoning models: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, DeepSeek V4.1 Flash (max), and Inkling (xhigh) (NVFP4). Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, all 7 models on Modal 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 Modal, 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.

Modal: Models Intelligence, Performance & Price

Most Intelligent

Fastest

Lowest Price

Intelligence

Speed

Price

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence Index vs. Price

Price-Quality Variance

Context Window

Context Window

Context Window for RAG

Context Window

Pricing

Intelligence Index vs. Price

Price-Quality Variance

Performance Summary

Output Speed vs. Price

Output Speed

Price

Speed

Output Speed

Output Speed

Model Performance Representation

Latency

Latency: Time To First Answer Token

Time to First Answer Token

Cache Behaviour

Cache Hit Rate

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time vs. Price

Price

Key definitions

Context Window

Frequently Asked Questions

What models does Modal offer?

What is the most intelligent model on Modal?

What is the fastest model on Modal?

Which model has the lowest latency on Modal?

What is the cheapest model on Modal?

How much do prices vary across models on Modal?

Is Modal OpenAI compatible?

Does Modal support JSON mode?

Does Modal support function calling?

Does Modal offer reasoning models?

Does Modal offer open weight models?

Does Modal's performance change over time?

How do I choose a model on Modal?