feat(ai): add Cloudflare Workers AI as a provider (#3851)
* feat(ai): add Cloudflare Workers AI as a provider
Cloudflare Workers AI hosts open-weight LLMs (Kimi K2.6, GPT-OSS,
GLM-4.7, Llama 4, Gemma 4, Nemotron 3) on Cloudflare's GPU network with
an OpenAI-compatible endpoint. Reuses the openai-completions API
protocol; the per-account URL contains a {CLOUDFLARE_ACCOUNT_ID}
placeholder resolved at request time by a small helper.
Pi automatically sets x-session-affinity for prefix caching:
https://developers.cloudflare.com/workers-ai/features/prompt-caching/
Auth: CLOUDFLARE_API_KEY (matches pi's *_API_KEY convention) +
CLOUDFLARE_ACCOUNT_ID. The User-Agent identifies traffic as
'pi-coding-agent' in Cloudflare analytics.
Verified end-to-end against a real Cloudflare account: 17 e2e tests
pass across stream/empty/tokens/unicode/tool-call-without-result/
total-tokens against @cf/moonshotai/kimi-k2.6.
Cloudflare AI Gateway is a separate, larger change (it requires routing
through provider-specific subpaths with the matching API protocol per
upstream) and will land in a follow-up PR.
* refactor(ai): move Cloudflare User-Agent and session-affinity flag to per-model metadata
Instead of conditionally setting them in openai-completions.ts based on
provider detection, declare them as model-level fields in the catalog
(headers + compat). This is consistent with how the github-copilot and
kimi-coding entries already declare their static headers.
packages/ai/scripts/generate-models.ts: emit headers and compat fields
on each cloudflare-workers-ai entry (CLOUDFLARE_STATIC_HEADERS).
packages/ai/src/providers/openai-completions.ts: drop the
isCloudflareProvider conditional that injected User-Agent and the
isCloudflareWorkersAI override of sendSessionAffinityHeaders.
packages/ai/src/models.generated.ts: re-spliced 8 cloudflare-workers-ai
entries with headers + compat.
Behavior is unchanged - verified via fetch interceptor that User-Agent
and x-session-affinity / session_id / x-client-request-id are still sent
on outbound requests. 5/5 e2e tests pass.
This commit is contained in:
MC
@@ -15374,4 +15374,158 @@ export const MODELS = {
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"cloudflare-workers-ai": {
|
||||
"@cf/google/gemma-4-26b-a4b-it": {
|
||||
id: "@cf/google/gemma-4-26b-a4b-it",
|
||||
name: "Gemma 4 26B A4B IT",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/meta/llama-4-scout-17b-16e-instruct": {
|
||||
id: "@cf/meta/llama-4-scout-17b-16e-instruct",
|
||||
name: "Llama 4 Scout 17B 16E Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.27,
|
||||
output: 0.85,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/moonshotai/kimi-k2.5": {
|
||||
id: "@cf/moonshotai/kimi-k2.5",
|
||||
name: "Kimi K2.5",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/moonshotai/kimi-k2.6": {
|
||||
id: "@cf/moonshotai/kimi-k2.6",
|
||||
name: "Kimi K2.6",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.95,
|
||||
output: 4,
|
||||
cacheRead: 0.16,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/nvidia/nemotron-3-120b-a12b": {
|
||||
id: "@cf/nvidia/nemotron-3-120b-a12b",
|
||||
name: "Nemotron 3 Super 120B",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/openai/gpt-oss-120b": {
|
||||
id: "@cf/openai/gpt-oss-120b",
|
||||
name: "GPT OSS 120B",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.35,
|
||||
output: 0.75,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/openai/gpt-oss-20b": {
|
||||
id: "@cf/openai/gpt-oss-20b",
|
||||
name: "GPT OSS 20B",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.2,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"@cf/zai-org/glm-4.7-flash": {
|
||||
id: "@cf/zai-org/glm-4.7-flash",
|
||||
name: "GLM-4.7-Flash",
|
||||
api: "openai-completions",
|
||||
provider: "cloudflare-workers-ai",
|
||||
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
||||
headers: {"User-Agent":"pi-coding-agent"},
|
||||
compat: {"sendSessionAffinityHeaders":true},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.06,
|
||||
output: 0.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
} as const;
|
||||
|
||||
Reference in New Issue
Block a user