Enterprise AI pricing snapshot
Cloudflare Workers AI models
Cloudflare-hosted models and Workers AI routes for teams building inference close to edge or app workloads.
This page reflects the Apostic pricing snapshot published on April 22, 2026. Apostic handles billing and vendor consolidation for Voxvey Cortex and related Enterprise AI engagements.
Snapshot details
5 catalog rows
Every row on this page comes from the provider snapshot imported into Apostic’s Enterprise AI pricing catalog.
0 public rows
Public availability reflects the source export supplied for this pricing snapshot and does not replace provider-side availability checks.
Voxvey Cortex ready
Use this snapshot to narrow model fit, then let Apostic handle commercial coordination, billing, and private deployment planning.
Catalog summary
Wildcard and provider-wide availability rows.
These entries appear exactly as supplied in the source export and help show higher-level access coverage in addition to model-specific rows.
| Public Model Name | Mode | Tokens | Input Cost / 1M | Output Cost / 1M | Features | Public |
|---|---|---|---|---|---|---|
cloudflare/* |
chat | - / - | — | — | — | No |
Full catalog
Cloudflare model rows in the current snapshot.
Model families, token windows, features, and public flags are shown from the imported export. Apostic can translate this list into a practical shortlist based on search quality, reasoning needs, coding support, realtime requirements, private deployment rules, and budget targets.
| Public Model Name | Mode | Tokens | Input Cost / 1M | Output Cost / 1M | Features | Public |
|---|---|---|---|---|---|---|
cloudflare/@cf/meta/llama-2-7b-chat-fp16 |
chat | 3.1K / 3.1K | $1.92 | $1.92 | — | No |
cloudflare/@hf/thebloke/codellama-7b-instruct-awq |
chat | 4.1K / 4.1K | $1.92 | $1.92 | — | No |
cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 |
chat | 8.2K / 8.2K | $1.92 | $1.92 | — | No |
cloudflare/@cf/meta/llama-2-7b-chat-int8 |
chat | 2.0K / 2.0K | $1.92 | $1.92 | — | No |
Enterprise AI advisory
Use this pricing snapshot to shortlist models, then let Apostic handle the rollout conversation.
We can help map providers and model families to Voxvey Cortex, private enterprise search, internal chat, and centralized billing across providers.