Cloudflare

Models served by Cloudflare

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek V4 Flash deepseek/deepseek-v4-flash:cloudflare	1.0M	$0.46/M	$1.39/M	$0.01/M	N/A	0.7s	71 tps
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:cloudflare	1.0M	$0.46/M	$1.39/M	$0.01/M	N/A	0.7s	71 tps
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:cloudflare	384k	$0.46/M	$1.39/M	$0.01/M	N/A	0.9s	80 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:cloudflare	384k	$0.46/M	$1.39/M	$0.01/M	N/A	0.9s	80 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:cloudflare	1.0M	$1.39/M	$4.16/M	$0.05/M	N/A	2.6s	47 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:cloudflare	1.0M	$1.39/M	$4.16/M	$0.05/M	N/A	2.6s	47 tps
Gemma 4 26B A4B google/gemma-4-26b-a4b-it:cloudflare	262k	$0.11/M	$0.31/M	N/A	4.2%	0.4s	64 tps
Gemma 4 26B A4B (Thinking) google/gemma-4-26b-a4b-it:thinking:cloudflare	262k	$0.11/M	$0.31/M	N/A	42.3%	0.4s	64 tps
GLM 4.7 Flash zai-org/glm-4.7-flash:cloudflare	200k	$0.06/M	$0.42/M	N/A	0%	0.3s	32 tps
GLM 4.7 Flash (Thinking) zai-org/glm-4.7-flash:thinking:cloudflare	200k	$0.06/M	$0.42/M	N/A	0%	0.3s	32 tps
GLM 4.7 Flash Original zai-org/glm-4.7-flash-original:cloudflare	200k	$0.06/M	$0.42/M	N/A	0%	0.3s	32 tps
GLM 4.7 Flash Original (Thinking) zai-org/glm-4.7-flash-original:thinking:cloudflare	200k	$0.06/M	$0.42/M	N/A	0%	0.3s	32 tps
GLM 5.2 zai-org/glm-5.2:cloudflare	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	2.1s	52 tps
GLM 5.2 (Thinking) zai-org/glm-5.2:thinking:cloudflare	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	2.1s	52 tps
GLM 5.3 zai-org/glm-5.3:cloudflare	1.3M	$1.47/M	$4.62/M	$0.27/M	N/A	2.1s	36 tps
GLM 5.3 (Thinking) zai-org/glm-5.3:thinking:cloudflare	1.3M	$1.47/M	$4.62/M	$0.27/M	N/A	2.1s	36 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:cloudflare	1.3M	$0.16/M	$0.53/M	$0.03/M	N/A	1.9s	48 tps
GPT OSS 120B openai/gpt-oss-120b:cloudflare	128k	$0.37/M	$0.79/M	N/A	0%	3.5s	51.3 tps
GPT OSS 20B openai/gpt-oss-20b:cloudflare	128k	$0.21/M	$0.31/M	N/A	0%	0.5s	57.6 tps
Kimi K2.6 moonshotai/kimi-k2.6:cloudflare	256k	$1.00/M	$4.20/M	Supported	16.3%	1s	49 tps
Kimi K2.6 Thinking moonshotai/kimi-k2.6:thinking:cloudflare	256k	$1.00/M	$4.20/M	Supported	20%	1s	49 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:cloudflare	262k	$1.00/M	$4.20/M	Supported	57.5%	1.3s	34 tps
Llama 3.3 70B Instruct FP8 meta-llama/llama-3.3-70b-instruct:cloudflare	131k	$0.31/M	$2.37/M	N/A	N/A	0.5s	27 tps
Qwen3.8 27B qwen3.8-27b:cloudflare	262k	$0.47/M	$3.36/M	$0.05/M	0%	0.3s	46 tps
Qwen3.8 27B Thinking qwen3.8-27b:thinking:cloudflare	262k	$0.47/M	$3.36/M	$0.05/M	0%	0.3s	46 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Cloudflare via the API

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 5% markup over that provider's base price; the prices in the table above already include it.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash:cloudflare",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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