Cloudflare Workers AI models

Models: 9; 7 scored
Cheapest call: $0.0033; Gemma 4 26B A4B (Workers AI)
Dearest call: $0.0473; GLM-5.3 (Workers AI)
Best bugs caught: 61%; GLM-5.3 (Workers AI)
Newest: 2026-08-26; GLM-5.3 Flash (Workers AI)

Pricing

Models CodePanel calls on Cloudflare Workers AI: list prices per 1M tokens, one review call and reading a pull request.

Gemma 4 26B A4B (Workers AI)Google@cf/google/gemma-4-26b-a4b-it	$0.10	$0.30	–	$0.0033	$0.0026
GLM-5.3 Flash (Workers AI)Z.ai@cf/zai-org/glm-5.3-flash	$0.15	$0.50	–	$0.0051	$0.0039
GPT-OSS 120B (Workers AI)OpenAI@cf/openai/gpt-oss-120b	$0.35	$0.75	–	$0.011	$0.0092
DeepSeek V4 Flash (Workers AI)DeepSeek@cf/deepseek-ai/deepseek-v4-flash-0731	$0.44	$1.32	–	$0.0147	$0.0115
Nemotron 3 Super (Workers AI)NVIDIA@cf/nvidia/nemotron-3-120b-a12b	$0.50	$1.50	–	$0.0167	$0.0131
Qwen3.8 27B (Workers AI)Qwen@cf/qwen/qwen3.8-27b	$0.45	$3.20	–	$0.0195	$0.0118
Kimi K2.7 Code (Workers AI)Moonshot@cf/moonshotai/kimi-k2.7-code	$0.95	$4.00	–	$0.0346	$0.0249
DeepSeek V4 Pro (Workers AI)DeepSeek@cf/deepseek-ai/deepseek-v4-pro-0813	$1.32	$3.96	–	$0.0442	$0.0346
GLM-5.3 (Workers AI)Z.ai@cf/zai-org/glm-5.3	$1.40	$4.40	–	$0.0473	$0.0367

Benchmark

Benchmark results
Compare
	2	GLM-5.3 Flash (Workers AI)Z.ai · Economy · open weights@cf/zai-org/glm-5.3-flash	61%	61%	100%	1.8	$0.0035	$0.0066	254s
	3	GLM-5.3 (Workers AI)Z.ai · Mid-range · open weights@cf/zai-org/glm-5.3	61%	61%	99%	1.9	$0.0311	$0.0559	65s
	4	DeepSeek V4 Pro (Workers AI)DeepSeek · Mid-range · open weights@cf/deepseek-ai/deepseek-v4-pro-0813	54%	54%	67%	2.9	$0.0643	$0.0872	390s
	5	DeepSeek V4 Flash (Workers AI)DeepSeek · Economy · open weights@cf/deepseek-ai/deepseek-v4-flash-0731	49%	49%	81%	1.3	$0.0178	$0.0309	137s
	8	GPT-OSS 120B (Workers AI)OpenAI · Economy · open weights@cf/openai/gpt-oss-120b	40%	40%	100%	2.5	$0.0075	$0.0189	55s
	11	Kimi K2.7 Code (Workers AI)Moonshot · Mid-range · open weights@cf/moonshotai/kimi-k2.7-code	38%	38%	39%	2.6	$0.0567	$0.0805	610s
	13	Gemma 4 26B A4B (Workers AI)Google · Economy · open weights@cf/google/gemma-4-26b-a4b-it	26%	27%	91%	0.4	$0.0048	$0.0209	308s

By language and bug kind

Share of known bugs each model caught, by language
Model	All	TypeScript6 bugs	Go4 bugs	Java4 bugs	Rust4 bugs	C#3 bugs	JavaScript3 bugs	Kotlin3 bugs	PHP3 bugs	Python3 bugs	Ruby3 bugs	Swift3 bugs	C++2 bugs	C1 bug
GLM-5.3 Flash (Workers AI)	61%	57%	31%	45%	88%	30%	67%	89%	33%	78%	67%	67%	100%	67%
GLM-5.3 (Workers AI)	61%	78%	19%	46%	73%	48%	33%	72%	44%	58%	67%	100%	100%	67%
DeepSeek V4 Pro (Workers AI)	54%	79%	25%	49%	54%	59%	17%	30%	69%	72%	67%	75%	38%	33%
DeepSeek V4 Flash (Workers AI)	49%	46%	25%	55%	46%	22%	56%	61%	78%	61%	44%	67%	50%	0%
GPT-OSS 120B (Workers AI)	40%	42%	13%	46%	71%	41%	11%	44%	33%	78%	33%	44%	33%	0%
Kimi K2.7 Code (Workers AI)	38%	75%	26%	31%	46%	19%	8%	14%	42%	62%	33%	46%	6%	40%
Gemma 4 26B A4B (Workers AI)	26%	33%	0%	30%	38%	7%	0%	56%	33%	44%	67%	0%	0%	0%

Quality against cost

Higher catches more · further left is cheaper

Z.aiDeepSeekOpenAIMoonshotGoogleFaded: models outside this list95% range: the line through each point

Every point as a table

Bugs caught and measured cost per review, by model
Model	Bugs caught	95% range	Cost / review
GLM-5.3 (Workers AI)	61%	50%–72%	$0.0311
GLM-5.3 Flash (Workers AI)	61%	50%–72%	$0.0035
DeepSeek V4 Pro (Workers AI)	54%	43%–65%	$0.0643
DeepSeek V4 Flash (Workers AI)	49%	37%–60%	$0.0178
GPT-OSS 120B (Workers AI)	40%	29%–52%	$0.0075
Kimi K2.7 Code (Workers AI)	38%	28%–47%	$0.0567
Gemma 4 26B A4B (Workers AI)	26%	15%–38%	$0.0048

Same models elsewhere

One review call on Cloudflare Workers AI and elsewhere
Model	On Cloudflare Workers AI	Maker's API	Difference	Other hosts
DeepSeek V4 Pro (Workers AI)	$0.0442	$0.0442	same	–
DeepSeek V4 Flash (Workers AI)	$0.0147	$0.0108	+37%	–
Kimi K2.7 Code (Workers AI)	$0.0346	$0.0346	same	–

Related lists

Updated Oct 16, 2026All prices pricing.json