Text model
@cf/meta/llama-3.3-70b-instruct-fp8-fast pricing
Cloudflare Workers AI charges $0.293 per million input tokens and $2.253 per million output tokens for @cf/meta/llama-3.3-70b-instruct-fp8-fast. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.293/ 1M
- Output
- $2.253/ 1M
- Context
- 24Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.293 | $2.253 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00134 | 100,000 | $134.07 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00288 | 100,000 | $288.45 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00532 | 250,000 | $1,329.60 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with @cf/meta/llama-3.3-70b-instruct-fp8-fast, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| cloudflare/@cf/openai/gpt-oss-120b | $0.000825 | 38% |
| cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it | $0.000749 | 44% |
| novita/baidu/ernie-4.5-vl-424b-a47b | $0.00113 | 16% |
| together/meta-models/Muse-Glimmer-30B | $0.00112 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Cloudflare Workers AI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.