Cloudflare

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by Cloudflare

Model name

27 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Clef cloudflare/clef:cloudflare	66k	$0.25/M	Free	N/A	N/A	N/A
Clef Flash cloudflare/clef-flash:cloudflare	66k	$0.09/M	Free	N/A	N/A	N/A
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:cloudflare	1.0M	$0.46/M	$1.39/M	$0.01/M	1s	60 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:cloudflare	1.0M	$0.46/M	$1.39/M	$0.01/M	1s	60 tps
DeepSeek V4 Pro deepseek/deepseek-v4-pro:cloudflare	1.0M	$1.21/M	$2.68/M	$0.21/M	2.1s	48 tps
DeepSeek V4 Pro (Thinking) deepseek/deepseek-v4-pro:thinking:cloudflare	1.0M	$1.21/M	$2.68/M	$0.21/M	2.1s	48 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:cloudflare	1.0M	$1.39/M	$4.16/M	$0.05/M	1.2s	45 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:cloudflare	1.0M	$1.39/M	$4.16/M	$0.05/M	1.2s	45 tps
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017:cloudflare	1.0M	$0.10/M	$0.63/M	$0.0032/M	6.9s	36 tps
DeepSeek V4.1 Flash 1017 (Thinking) deepseek/deepseek-v4.1-flash-1017:thinking:cloudflare	1.0M	$0.10/M	$0.63/M	$0.0032/M	6.9s	36 tps
Gemma 4 26B A4B google/gemma-4-26b-a4b-it:cloudflare	262k	$0.11/M	$0.31/M	Supported	0.3s	50 tps
Gemma 4 26B A4B (Thinking) google/gemma-4-26b-a4b-it:thinking:cloudflare	262k	$0.11/M	$0.31/M	Supported	0.3s	50 tps
GLM 4.7 Flash z-ai/glm-4.7-flash:cloudflare	200k	$0.06/M	$0.42/M	N/A	0.4s	41 tps
GLM 4.7 Flash (Thinking) z-ai/glm-4.7-flash:thinking:cloudflare	200k	$0.06/M	$0.42/M	N/A	0.4s	41 tps
GLM 5.2 z-ai/glm-5.2:cloudflare	262k	$0.20/M	$8.40/M	$0.20/M	0.8s	83 tps
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:cloudflare	262k	$0.20/M	$8.40/M	$0.20/M	0.8s	83 tps
GLM 5.3 z-ai/glm-5.3:cloudflare	1.0M	$1.47/M	$4.62/M	$0.27/M	2.2s	32 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:cloudflare	1.0M	$1.47/M	$4.62/M	$0.27/M	2.2s	32 tps
GPT OSS 120B openai/gpt-oss-120b:cloudflare	128k	$0.37/M	$0.79/M	N/A	N/A	N/A
GPT OSS 20B openai/gpt-oss-20b:cloudflare	128k	$0.21/M	$0.31/M	N/A	N/A	N/A
Kimi K2.6 moonshotai/kimi-k2.6:cloudflare	256k	$1.00/M	$4.20/M	Supported	1.4s	35.5 tps
Kimi K2.6 Thinking moonshotai/kimi-k2.6:thinking:cloudflare	256k	$1.00/M	$4.20/M	Supported	1.4s	35.5 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:cloudflare	262k	$1.00/M	$4.20/M	Supported	1s	35 tps
Llama 3.1 8B FP8 meta-llama/llama-3.1-8b-instruct:cloudflare	32k	$0.16/M	$0.30/M	N/A	0.4s	19 tps
Llama 3.3 70B Instruct FP8 meta-llama/llama-3.3-70b-instruct:cloudflare	24k	$0.31/M	$2.37/M	N/A	0.4s	46 tps
Qwen3.8 27B qwen3.8-27b:cloudflare	262k	$0.47/M	$3.36/M	$0.05/M	10s	17 tps
Qwen3.8 27B Thinking qwen3.8-27b:thinking:cloudflare	262k	$0.47/M	$3.36/M	$0.05/M	10s	17 tps

Clef

cloudflare/clef:cloudflare

Context

66k

Input /M

$0.25/M

Output /M

Free

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

Clef Flash

cloudflare/clef-flash:cloudflare

Context

66k

Input /M

$0.09/M

Output /M

Free

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:cloudflare

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.01/M

TTFT

1s

Throughput

60 tps

DeepSeek V4 Flash 0731 (Thinking)

deepseek/deepseek-v4-flash-0731:thinking:cloudflare

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.01/M

TTFT

1s

Throughput

60 tps

DeepSeek V4 Pro

deepseek/deepseek-v4-pro:cloudflare

Context

1.0M

Input /M

$1.21/M

Output /M

$2.68/M

Cache read /M

$0.21/M

TTFT

2.1s

Throughput

48 tps

DeepSeek V4 Pro (Thinking)

deepseek/deepseek-v4-pro:thinking:cloudflare

Context

1.0M

Input /M

$1.21/M

Output /M

$2.68/M

Cache read /M

$0.21/M

TTFT

2.1s

Throughput

48 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:cloudflare

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.05/M

TTFT

1.2s

Throughput

45 tps

DeepSeek V4 Pro 0813 (Thinking)

deepseek/deepseek-v4-pro-0813:thinking:cloudflare

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.05/M

TTFT

1.2s

Throughput

45 tps

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017:cloudflare

Context

1.0M

Input /M

$0.10/M

Output /M

$0.63/M

Cache read /M

$0.0032/M

TTFT

6.9s

Throughput

36 tps

DeepSeek V4.1 Flash 1017 (Thinking)

deepseek/deepseek-v4.1-flash-1017:thinking:cloudflare

Context

1.0M

Input /M

$0.10/M

Output /M

$0.63/M

Cache read /M

$0.0032/M

TTFT

6.9s

Throughput

36 tps

Gemma 4 26B A4B

google/gemma-4-26b-a4b-it:cloudflare

Context

262k

Input /M

$0.11/M

Output /M

$0.31/M

Cache read /M

Supported

TTFT

0.3s

Throughput

50 tps

Gemma 4 26B A4B (Thinking)

google/gemma-4-26b-a4b-it:thinking:cloudflare

Context

262k

Input /M

$0.11/M

Output /M

$0.31/M

Cache read /M

Supported

TTFT

0.3s

Throughput

50 tps

GLM 4.7 Flash

z-ai/glm-4.7-flash:cloudflare

Context

200k

Input /M

$0.06/M

Output /M

$0.42/M

Cache read /M

N/A

TTFT

0.4s

Throughput

41 tps

GLM 4.7 Flash (Thinking)

z-ai/glm-4.7-flash:thinking:cloudflare

Context

200k

Input /M

$0.06/M

Output /M

$0.42/M

Cache read /M

N/A

TTFT

0.4s

Throughput

41 tps

GLM 5.2

z-ai/glm-5.2:cloudflare

Context

262k

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.20/M

TTFT

0.8s

Throughput

83 tps

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:cloudflare

Context

262k

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.20/M

TTFT

0.8s

Throughput

83 tps

GLM 5.3

z-ai/glm-5.3:cloudflare

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

2.2s

Throughput

32 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:cloudflare

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

2.2s

Throughput

32 tps

GPT OSS 120B

openai/gpt-oss-120b:cloudflare

Context

128k

Input /M

$0.37/M

Output /M

$0.79/M

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

GPT OSS 20B

openai/gpt-oss-20b:cloudflare

Context

128k

Input /M

$0.21/M

Output /M

$0.31/M

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.6

moonshotai/kimi-k2.6:cloudflare

Context

256k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

Supported

TTFT

1.4s

Throughput

35.5 tps

Kimi K2.6 Thinking

moonshotai/kimi-k2.6:thinking:cloudflare

Context

256k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

Supported

TTFT

1.4s

Throughput

35.5 tps

Kimi K2.7 Code

moonshotai/kimi-k2.7-code:cloudflare

Context

262k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

Supported

TTFT

1s

Throughput

35 tps

Llama 3.1 8B

FP8

meta-llama/llama-3.1-8b-instruct:cloudflare

Context

32k

Input /M

$0.16/M

Output /M

$0.30/M

Cache read /M

N/A

TTFT

0.4s

Throughput

19 tps

Llama 3.3 70B Instruct

FP8

meta-llama/llama-3.3-70b-instruct:cloudflare

Context

24k

Input /M

$0.31/M

Output /M

$2.37/M

Cache read /M

N/A

TTFT

0.4s

Throughput

46 tps

Qwen3.8 27B

qwen3.8-27b:cloudflare

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

$0.05/M

TTFT

10s

Throughput

17 tps

Qwen3.8 27B Thinking

qwen3.8-27b:thinking:cloudflare

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

$0.05/M

TTFT

10s

Throughput

17 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Cloudflare via the API

Call a model served by Cloudflare using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cloudflare/clef:cloudflare",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :cloudflare to the model ID, set "provider": "cloudflare" in the request body, or send an X-Provider: cloudflare header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.