LLMRates.ai
Cloudflare Workers AI logo

Cloudflare Workers AI API pricing

Model Aggregator

Cloudflare Workers AI runs open models (Llama, Qwen, Mistral, Gemma, GPT-OSS, plus embeddings and speech) on Cloudflare's global edge network, billed per token in USD (also denominated in Neurons).

Compare the published API prices listed for Cloudflare Workers AI. Open a model for its available pricing tiers, source and conditions, or use the cost planner to estimate your own workload.

Models
49
Prompt Caching
—
Batch Discount
—
Tool Calling
—
Visit Website →View Official Pricing →
Model49
@cf/ai4bharat/indictrans2-en-indic-1B$0.342$0.342
@cf/aisingapore/gemma-sea-lion-v4-27b-itGemma$0.351$0.555
@cf/baai/bge-base-en-v1.5BGE$0.0666—
@cf/baai/bge-large-en-v1.5BGE$0.204—
@cf/baai/bge-m3BGE$0.0118—
@cf/baai/bge-reranker-baseBGE$0.00311—
@cf/baai/bge-small-en-v1.5BGE$0.0202—
@cf/cloudflare/clairic$0.1—
@cf/cloudflare/clef$0.24—
@cf/cloudflare/clef-flash$0.038—
@cf/cloudflare/clef-omni$0.15—
@cf/deepgram/flux$0.0077/min—
@cf/deepgram/nova-3$0.0052/min—
@cf/deepseek-ai/deepseek-r1-distill-qwen-32bQwen$0.497$4.88
@cf/deepseek-ai/deepseek-v4-flash-0731DeepSeek$0.014$1.32
@cf/deepseek-ai/deepseek-v4-pro-0813DeepSeek$0.044$3.96
@cf/deepseek-ai/deepseek-v4.1-flash-1017DeepSeek$0.3$1.2
@cf/google/gemma-4-26b-a4b-itGemma$0.1$0.3
@cf/huggingface/distilbert-sst-2-int8$0.0263—
@cf/ibm-granite/granite-4.0-h-micro$0.017$0.112
@cf/meta/llama-3.1-8b-instruct-fp8Llama$0.152$0.287
@cf/meta/llama-3.2-11b-vision-instructLlama$0.0485$0.676
@cf/meta/llama-3.2-1b-instructLlama$0.027$0.201
@cf/meta/llama-3.2-3b-instructLlama$0.0509$0.335
@cf/meta/llama-3.3-70b-instruct-fp8-fastLlama$0.293$2.25
@cf/meta/llama-4-scout-17b-16e-instructLlama$0.27$0.85
@cf/meta/llama-guard-3-8bLlama$0.484$0.03
@cf/meta/m2m100-1.2b$0.342$0.342
@cf/mistralai/mistral-small-3.1-24b-instructMistral$0.351$0.555
@cf/moondream/moondream3.1-9B-A2B$0.3$1
@cf/moonshotai/kimi-k2.6$0.16$4
@cf/moonshotai/kimi-k2.7-code$0.19$4
@cf/myshell-ai/melotts$0.000205/min—
@cf/nvidia/nemotron-3-120b-a12b$0.5$1.5
@cf/openai/gpt-oss-120bGPT-OSS$0.35$0.75
@cf/openai/gpt-oss-20bGPT-OSS$0.2$0.3
@cf/openai/whisper$0.000453/min—
@cf/openai/whisper-large-v3-turbo$0.000513/min—
@cf/pfnet/plamo-embedding-1b$0.0186—
@cf/pipecat-ai/smart-turn-v2$0.000338/min—
@cf/qwen/qwen2.5-coder-32b-instructQwen$0.66$1
@cf/qwen/qwen3-30b-a3b-fp8Qwen$0.0509$0.335
@cf/qwen/qwen3-embedding-0.6bQwen$0.0118—
@cf/qwen/qwen3.8-27bQwen$0.05$3.2
@cf/qwen/qwq-32bQwen$0.66$1
@cf/zai-org/glm-4.7-flash$0.0605$0.4
@cf/zai-org/glm-5.2$0.26$4.4
@cf/zai-org/glm-5.3$0.26$4.4
@cf/zai-org/glm-5.3-flash$0.03$0.5

Cloudflare Workers AI API cost examples

1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.

Standard text token prices and estimated workload cost in USD
ModelInput / 1M tokensOutput / 1M tokensEstimated costPricing conditions
@cf/ibm-granite/granite-4.0-h-microCloudflare Workers AI$0.017$0.112$0.0394Region not specifiedView official pricing
@cf/meta/llama-3.2-1b-instructCloudflare Workers AI$0.027$0.201$0.0672Region not specifiedView official pricing
@cf/meta/llama-3.2-3b-instructCloudflare Workers AI$0.0509$0.335$0.1179Region not specifiedView official pricing
@cf/qwen/qwen3-30b-a3b-fp8Cloudflare Workers AI$0.0509$0.335$0.1179Region not specifiedView official pricing
@cf/zai-org/glm-5.3-flashCloudflare Workers AI$0.03$0.5$0.13Region not specifiedView official pricing
@cf/zai-org/glm-4.7-flashCloudflare Workers AI$0.0605$0.4$0.1405Region not specifiedView official pricing

Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.

Calculate costs for your workload →