Cloudflare: Models Intelligence, Performance & Price

Cloudflare
Cloudflare

Analysis of Cloudflare'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 Cloudflare for your use-case.

Most Intelligent

Updated
#1
Kimi K2.6
Kimi K2.6
44
#2
Gemma 4 26B A4B
Gemma 4 26B A4B
26
#3
gpt-oss-120b (high)
gpt-oss-120b (high)
24
#4
gpt-oss-120b (low)
gpt-oss-120b (low)
15
#5
gpt-oss-20b (high)
gpt-oss-20b (high)
15

Intelligence index

Total 11 models

Fastest

#1
Llama 3.1 8B
Llama 3.1 8B
193 t/s
#2
gpt-oss-20b (high)
gpt-oss-20b (high)
166 t/s
#3
gpt-oss-20b (low)
gpt-oss-20b (low)
161 t/s
#4
gpt-oss-120b (low)
gpt-oss-120b (low)
119 t/s
#5
gpt-oss-120b (high)
gpt-oss-120b (high)
113 t/s

Output speed

Total 11 models

Lowest Price

#1
Gemma 4 26B A4B
Gemma 4 26B A4B
$0.12
#2
gpt-oss-20b (high)
gpt-oss-20b (high)
$0.21
#3
gpt-oss-20b (low)
gpt-oss-20b (low)
$0.21
#4
Llama 4 Scout
Llama 4 Scout
$0.33
#5
Mistral Small 3.1
Mistral Small 3.1
$0.37

Blended price (per 1M tokens)

Total 11 models

Indicates a reasoning model

Cloudflare offers 11 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 Cloudflare are Kimi K2.6 (44), Gemma 4 26B A4B (26), gpt-oss-120b (high) (24).
  • For output speed, the fastest models are Llama 3.1 8B (193 t/s), gpt-oss-20b (high) (166 t/s), gpt-oss-20b (low) (161 t/s). Speed varies significantly across models, with a 70% difference between the fastest and slowest.
  • For latency, Llama 3.1 8B (0.71s), Llama 4 Scout (0.91s), Mistral Small 3.1 (3.41s) offer the lowest time to first answer token.
  • For pricing, Gemma 4 26B A4B ($0.12), gpt-oss-20b (high) ($0.21), gpt-oss-20b (low) ($0.21) offer the lowest blended prices per 1M tokens. Prices vary up to 3.1x across models.
  • For context window size, Kimi K2.6 (262k), Gemma 4 26B A4B (256k), Llama 4 Scout (131k) support the largest context windows on Cloudflare.

Highlights

Updated

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 v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

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

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-BriefcaseNew

Agentic knowledge work, Elo

AutomationBench-AANew

Agentic SaaS workflows

Harvey LAB-AANew

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon.

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

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

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

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

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).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

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 vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

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

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

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).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

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
Reasoning models are indicated by a lightbulb icon

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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

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
Reasoning models are indicated by a lightbulb icon

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.

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
Reasoning models are indicated by a lightbulb icon.

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).

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Further Analysis
Kimi logo
Kimi K2.6
262k
Open
44
$0.28
51
1.16
98.21
87.25
Model
Provider
Google logo
Gemma 4 26B A4B
256k
Open
26
--
83
1.15
31.40
24.20
Model
Provider
OpenAI logo
gpt-oss-120b (high)
116k
Open
24
--
113
0.91
22.94
17.63
Model
Provider
OpenAI logo
gpt-oss-120b (low)
128k
Open
15
--
119
0.93
21.93
16.80
Model
Provider
OpenAI logo
gpt-oss-20b (high)
128k
Open
15
--
166
0.74
15.85
12.08
Model
Provider
Mistral logo
Mistral Small 3.1
128k
Open
15
$0.14
35
3.41
17.80
--
Model
Provider
OpenAI logo
gpt-oss-20b (low)
128k
Open
14*
--
161
0.79
16.31
12.42
Model
Provider
Alibaba logo
QwQ-32B
24k
Open
13*
--
31
2.11
97.28
79.27
Model
Provider
Meta logo
Llama 4 Scout
131k
Open
10
$0.01
43
0.91
12.59
--
Model
Provider
Meta logo
Llama 3.3 70B
24k
Open
9
$0.04
49
3.93
14.13
--
Model
Provider
Meta logo
Llama 3.1 8B
30k
Open
8
--
193
0.71
3.30
--
Model
Provider
Google logo
Gemma 3 12B
80k
Open
6
$0.51
--
--
--
--
Model
Provider

Key definitions

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

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).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Price per token to write prompt tokens into the cache so that later requests can hit them, represented as USD per million tokens. Some providers charge a premium over the standard input price to create a cache entry (e.g. Anthropic), while others cache automatically with no separate write fee.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

Frequently Asked Questions

Common questions about Cloudflare

The most intelligent model available on Cloudflare is Kimi K2.6 with an Intelligence Index score of 44.

The fastest model on Cloudflare by output speed is Llama 3.1 8B at 193.2 tokens per second.

The model with the lowest time to first answer token on Cloudflare is Llama 3.1 8B at 0.71s. Lower latency means faster initial response time.

The most affordable model on Cloudflare by blended price is Gemma 4 26B A4B at $0.12 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on Cloudflare vary up to 6x across models, from $0.12 per 1M tokens for Gemma 4 26B A4B to $0.70 per 1M tokens for Kimi K2.6.

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

10 of 11 models on Cloudflare support JSON mode for structured output.

Yes, all 11 models on Cloudflare support function calling (tool use).

Yes, Cloudflare offers 7 reasoning models: Kimi K2.6, Gemma 4 26B A4B, gpt-oss-120b (high), gpt-oss-120b (low), gpt-oss-20b (high), gpt-oss-20b (low), and QwQ-32B. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, all 11 models on Cloudflare 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 Cloudflare, 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.