@ai-sdk/gateway 4.0.23 → 4.0.25

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,20 @@
1
1
  # @ai-sdk/gateway
2
2
 
3
+ ## 4.0.25
4
+
5
+ ### Patch Changes
6
+
7
+ - Updated dependencies [02ffdcb]
8
+ - Updated dependencies [76cb673]
9
+ - @ai-sdk/provider-utils@5.0.12
10
+
11
+ ## 4.0.24
12
+
13
+ ### Patch Changes
14
+
15
+ - cefa3b1: chore(provider/gateway): remove `hipaaCompliant` provider option
16
+ - 8fbb89c: chore(provider/gateway): update gateway model settings files
17
+
3
18
  ## 4.0.23
4
19
 
5
20
  ### Patch Changes
package/dist/index.d.ts CHANGED
@@ -2,7 +2,7 @@ import { LanguageModelV4, ProviderV4, EmbeddingModelV4, ImageModelV4, Experiment
2
2
  import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
3
3
  import { FetchFunction, WebSocketConstructor, InferSchema } from '@ai-sdk/provider-utils';
4
4
 
5
- type GatewayModelId = 'alibaba/qwen-3-14b' | 'alibaba/qwen-3-235b' | 'alibaba/qwen-3-30b' | 'alibaba/qwen-3-32b' | 'alibaba/qwen-3.6-max-preview' | 'alibaba/qwen3-235b-a22b-thinking' | 'alibaba/qwen3-coder' | 'alibaba/qwen3-coder-30b-a3b' | 'alibaba/qwen3-coder-next' | 'alibaba/qwen3-coder-plus' | 'alibaba/qwen3-max' | 'alibaba/qwen3-max-preview' | 'alibaba/qwen3-max-thinking' | 'alibaba/qwen3-next-80b-a3b-instruct' | 'alibaba/qwen3-next-80b-a3b-thinking' | 'alibaba/qwen3-vl-235b-a22b-instruct' | 'alibaba/qwen3-vl-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-27b' | 'alibaba/qwen3.6-plus' | 'alibaba/qwen3.7-max' | 'alibaba/qwen3.7-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-fable-5' | 'anthropic/claude-haiku-4.5' | 'anthropic/claude-opus-4' | 'anthropic/claude-opus-4.1' | 'anthropic/claude-opus-4.5' | 'anthropic/claude-opus-4.6' | 'anthropic/claude-opus-4.7' | 'anthropic/claude-opus-4.7-fast' | 'anthropic/claude-opus-4.8' | 'anthropic/claude-opus-4.8-fast' | 'anthropic/claude-sonnet-4' | 'anthropic/claude-sonnet-4.5' | 'anthropic/claude-sonnet-4.6' | 'anthropic/claude-sonnet-5' | 'arcee-ai/trinity-large-thinking' | 'arcee-ai/trinity-mini' | 'bytedance/seed-1.6' | 'bytedance/seed-1.8' | 'cohere/command-a' | 'deepseek/deepseek-r1' | 'deepseek/deepseek-v3' | 'deepseek/deepseek-v3.1' | 'deepseek/deepseek-v3.1-terminus' | 'deepseek/deepseek-v3.2' | 'deepseek/deepseek-v3.2-thinking' | 'deepseek/deepseek-v4-flash' | 'deepseek/deepseek-v4-pro' | 'google/gemini-2.5-flash' | 'google/gemini-2.5-flash-image' | 'google/gemini-2.5-flash-lite' | 'google/gemini-2.5-pro' | 'google/gemini-3-flash' | 'google/gemini-3-pro-image' | 'google/gemini-3-pro-preview' | 'google/gemini-3.1-flash-image' | 'google/gemini-3.1-flash-image-preview' | 'google/gemini-3.1-flash-lite' | 'google/gemini-3.1-flash-lite-image' | 'google/gemini-3.1-flash-lite-preview' | 'google/gemini-3.1-pro-preview' | 'google/gemini-3.5-flash' | 'google/gemini-omni-flash-preview' | 'google/gemma-4-26b-a4b-it' | 'google/gemma-4-31b-it' | 'inception/mercury-2' | 'inception/mercury-coder-small' | 'interfaze/interfaze-beta' | 'kwaipilot/kat-coder-air-v2.5' | 'kwaipilot/kat-coder-pro-v1' | 'kwaipilot/kat-coder-pro-v2' | 'kwaipilot/kat-coder-pro-v2.5' | 'meta/llama-3.1-70b' | 'meta/llama-3.1-8b' | 'meta/llama-3.2-11b' | 'meta/llama-3.2-1b' | 'meta/llama-3.2-3b' | 'meta/llama-3.2-90b' | 'meta/llama-3.3-70b' | 'meta/llama-4-maverick' | 'meta/llama-4-scout' | 'meta/muse-spark-1.1' | 'minimax/minimax-m2' | 'minimax/minimax-m2.1' | 'minimax/minimax-m2.1-lightning' | 'minimax/minimax-m2.5' | 'minimax/minimax-m2.5-highspeed' | 'minimax/minimax-m2.7' | 'minimax/minimax-m2.7-highspeed' | 'minimax/minimax-m3' | 'mistral/codestral' | 'mistral/devstral-2' | 'mistral/devstral-small-2' | 'mistral/magistral-medium' | 'mistral/magistral-small' | 'mistral/ministral-14b' | 'mistral/ministral-3b' | 'mistral/ministral-8b' | 'mistral/mistral-large-3' | 'mistral/mistral-medium' | 'mistral/mistral-medium-3.5' | 'mistral/mistral-nemo' | 'mistral/mistral-small' | 'mistral/pixtral-12b' | 'moonshotai/kimi-k2' | 'moonshotai/kimi-k2-thinking' | 'moonshotai/kimi-k2.5' | 'moonshotai/kimi-k2.6' | 'moonshotai/kimi-k2.7-code' | 'moonshotai/kimi-k2.7-code-highspeed' | 'moonshotai/kimi-k3' | 'morph/morph-v3-fast' | 'morph/morph-v3-large' | 'nvidia/nemotron-3-nano-30b-a3b' | 'nvidia/nemotron-3-super-120b-a12b' | 'nvidia/nemotron-3-ultra-550b-a55b' | 'nvidia/nemotron-nano-12b-v2-vl' | 'nvidia/nemotron-nano-9b-v2' | 'openai/gpt-3.5-turbo' | 'openai/gpt-4-turbo' | 'openai/gpt-4.1' | 'openai/gpt-4.1-mini' | 'openai/gpt-4.1-nano' | 'openai/gpt-4o' | 'openai/gpt-4o-mini' | 'openai/gpt-4o-mini-search-preview' | 'openai/gpt-5' | 'openai/gpt-5-chat' | 'openai/gpt-5-codex' | 'openai/gpt-5-mini' | 'openai/gpt-5-nano' | 'openai/gpt-5-pro' | 'openai/gpt-5.1-codex' | 'openai/gpt-5.1-codex-max' | 'openai/gpt-5.1-codex-mini' | 'openai/gpt-5.1-instant' | 'openai/gpt-5.1-thinking' | 'openai/gpt-5.2' | 'openai/gpt-5.2-chat' | 'openai/gpt-5.2-codex' | 'openai/gpt-5.2-pro' | 'openai/gpt-5.3-chat' | 'openai/gpt-5.3-codex' | 'openai/gpt-5.4' | 'openai/gpt-5.4-mini' | 'openai/gpt-5.4-nano' | 'openai/gpt-5.4-pro' | 'openai/gpt-5.5' | 'openai/gpt-5.5-pro' | 'openai/gpt-5.6-luna' | 'openai/gpt-5.6-sol' | 'openai/gpt-5.6-terra' | 'openai/gpt-oss-120b' | 'openai/gpt-oss-20b' | 'openai/gpt-oss-safeguard-20b' | 'openai/o1' | 'openai/o3' | 'openai/o3-deep-research' | 'openai/o3-mini' | 'openai/o3-pro' | 'openai/o4-mini' | 'perplexity/sonar' | 'perplexity/sonar-pro' | 'perplexity/sonar-reasoning-pro' | 'sakana/fugu-ultra' | 'stepfun/step-3.5-flash' | 'stepfun/step-3.7-flash' | 'thinkingmachines/inkling' | 'xai/grok-4.1-fast-non-reasoning' | 'xai/grok-4.1-fast-reasoning' | 'xai/grok-4.20-multi-agent' | 'xai/grok-4.20-multi-agent-beta' | 'xai/grok-4.20-non-reasoning' | 'xai/grok-4.20-non-reasoning-beta' | 'xai/grok-4.20-reasoning' | 'xai/grok-4.20-reasoning-beta' | 'xai/grok-4.3' | 'xai/grok-4.5' | 'xai/grok-build-0.1' | 'xiaomi/mimo-v2.5' | 'xiaomi/mimo-v2.5-pro' | 'zai/glm-4.5' | 'zai/glm-4.5-air' | 'zai/glm-4.5v' | 'zai/glm-4.6' | 'zai/glm-4.6v' | 'zai/glm-4.6v-flash' | 'zai/glm-4.7' | 'zai/glm-4.7-flash' | 'zai/glm-4.7-flashx' | 'zai/glm-5' | 'zai/glm-5-turbo' | 'zai/glm-5.1' | 'zai/glm-5.2' | 'zai/glm-5.2-fast' | 'zai/glm-5v-turbo' | (string & {});
5
+ type GatewayModelId = 'alibaba/qwen-3-14b' | 'alibaba/qwen-3-235b' | 'alibaba/qwen-3-30b' | 'alibaba/qwen-3-32b' | 'alibaba/qwen-3.6-max-preview' | 'alibaba/qwen3-235b-a22b-thinking' | 'alibaba/qwen3-coder' | 'alibaba/qwen3-coder-30b-a3b' | 'alibaba/qwen3-coder-next' | 'alibaba/qwen3-coder-plus' | 'alibaba/qwen3-max' | 'alibaba/qwen3-max-preview' | 'alibaba/qwen3-max-thinking' | 'alibaba/qwen3-next-80b-a3b-instruct' | 'alibaba/qwen3-next-80b-a3b-thinking' | 'alibaba/qwen3-vl-235b-a22b-instruct' | 'alibaba/qwen3-vl-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-27b' | 'alibaba/qwen3.6-plus' | 'alibaba/qwen3.7-max' | 'alibaba/qwen3.7-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-fable-5' | 'anthropic/claude-haiku-4.5' | 'anthropic/claude-opus-4' | 'anthropic/claude-opus-4.1' | 'anthropic/claude-opus-4.5' | 'anthropic/claude-opus-4.6' | 'anthropic/claude-opus-4.7' | 'anthropic/claude-opus-4.7-fast' | 'anthropic/claude-opus-4.8' | 'anthropic/claude-opus-4.8-fast' | 'anthropic/claude-sonnet-4' | 'anthropic/claude-sonnet-4.5' | 'anthropic/claude-sonnet-4.6' | 'anthropic/claude-sonnet-5' | 'arcee-ai/trinity-large-thinking' | 'arcee-ai/trinity-mini' | 'bytedance/seed-1.6' | 'bytedance/seed-1.8' | 'cohere/command-a' | 'deepseek/deepseek-r1' | 'deepseek/deepseek-v3' | 'deepseek/deepseek-v3.1' | 'deepseek/deepseek-v3.1-terminus' | 'deepseek/deepseek-v3.2' | 'deepseek/deepseek-v3.2-thinking' | 'deepseek/deepseek-v4-flash' | 'deepseek/deepseek-v4-pro' | 'google/gemini-2.5-flash' | 'google/gemini-2.5-flash-image' | 'google/gemini-2.5-flash-lite' | 'google/gemini-2.5-pro' | 'google/gemini-3-flash' | 'google/gemini-3-pro-image' | 'google/gemini-3-pro-preview' | 'google/gemini-3.1-flash-image' | 'google/gemini-3.1-flash-image-preview' | 'google/gemini-3.1-flash-lite' | 'google/gemini-3.1-flash-lite-image' | 'google/gemini-3.1-flash-lite-preview' | 'google/gemini-3.1-pro-preview' | 'google/gemini-3.5-flash' | 'google/gemini-omni-flash-preview' | 'google/gemma-4-26b-a4b-it' | 'google/gemma-4-31b-it' | 'inception/mercury-2' | 'inception/mercury-coder-small' | 'interfaze/interfaze-beta' | 'kwaipilot/kat-coder-air-v2.5' | 'kwaipilot/kat-coder-pro-v1' | 'kwaipilot/kat-coder-pro-v2' | 'kwaipilot/kat-coder-pro-v2.5' | 'meta/llama-3.1-70b' | 'meta/llama-3.1-8b' | 'meta/llama-3.3-70b' | 'meta/llama-4-maverick' | 'meta/llama-4-scout' | 'meta/muse-spark-1.1' | 'minimax/minimax-m2' | 'minimax/minimax-m2.1' | 'minimax/minimax-m2.1-lightning' | 'minimax/minimax-m2.5' | 'minimax/minimax-m2.5-highspeed' | 'minimax/minimax-m2.7' | 'minimax/minimax-m2.7-highspeed' | 'minimax/minimax-m3' | 'mistral/codestral' | 'mistral/devstral-2' | 'mistral/devstral-small-2' | 'mistral/magistral-medium' | 'mistral/magistral-small' | 'mistral/ministral-14b' | 'mistral/ministral-3b' | 'mistral/ministral-8b' | 'mistral/mistral-large-3' | 'mistral/mistral-medium' | 'mistral/mistral-medium-3.5' | 'mistral/mistral-nemo' | 'mistral/mistral-small' | 'mistral/pixtral-12b' | 'moonshotai/kimi-k2' | 'moonshotai/kimi-k2-thinking' | 'moonshotai/kimi-k2.5' | 'moonshotai/kimi-k2.6' | 'moonshotai/kimi-k2.7-code' | 'moonshotai/kimi-k2.7-code-highspeed' | 'moonshotai/kimi-k3' | 'morph/morph-v3-fast' | 'morph/morph-v3-large' | 'nvidia/nemotron-3-nano-30b-a3b' | 'nvidia/nemotron-3-super-120b-a12b' | 'nvidia/nemotron-3-ultra-550b-a55b' | 'nvidia/nemotron-nano-12b-v2-vl' | 'nvidia/nemotron-nano-9b-v2' | 'openai/gpt-3.5-turbo' | 'openai/gpt-4-turbo' | 'openai/gpt-4.1' | 'openai/gpt-4.1-mini' | 'openai/gpt-4.1-nano' | 'openai/gpt-4o' | 'openai/gpt-4o-mini' | 'openai/gpt-4o-mini-search-preview' | 'openai/gpt-5' | 'openai/gpt-5-chat' | 'openai/gpt-5-codex' | 'openai/gpt-5-mini' | 'openai/gpt-5-nano' | 'openai/gpt-5-pro' | 'openai/gpt-5.1-codex' | 'openai/gpt-5.1-codex-max' | 'openai/gpt-5.1-codex-mini' | 'openai/gpt-5.1-instant' | 'openai/gpt-5.1-thinking' | 'openai/gpt-5.2' | 'openai/gpt-5.2-chat' | 'openai/gpt-5.2-codex' | 'openai/gpt-5.2-pro' | 'openai/gpt-5.3-chat' | 'openai/gpt-5.3-codex' | 'openai/gpt-5.4' | 'openai/gpt-5.4-mini' | 'openai/gpt-5.4-nano' | 'openai/gpt-5.4-pro' | 'openai/gpt-5.5' | 'openai/gpt-5.5-pro' | 'openai/gpt-5.6-luna' | 'openai/gpt-5.6-sol' | 'openai/gpt-5.6-terra' | 'openai/gpt-oss-120b' | 'openai/gpt-oss-20b' | 'openai/gpt-oss-safeguard-20b' | 'openai/o1' | 'openai/o3' | 'openai/o3-deep-research' | 'openai/o3-mini' | 'openai/o3-pro' | 'openai/o4-mini' | 'perplexity/sonar' | 'perplexity/sonar-pro' | 'perplexity/sonar-reasoning-pro' | 'sakana/fugu-ultra' | 'stepfun/step-3.5-flash' | 'stepfun/step-3.7-flash' | 'thinkingmachines/inkling' | 'xai/grok-4.1-fast-non-reasoning' | 'xai/grok-4.1-fast-reasoning' | 'xai/grok-4.20-multi-agent' | 'xai/grok-4.20-multi-agent-beta' | 'xai/grok-4.20-non-reasoning' | 'xai/grok-4.20-non-reasoning-beta' | 'xai/grok-4.20-reasoning' | 'xai/grok-4.20-reasoning-beta' | 'xai/grok-4.3' | 'xai/grok-4.5' | 'xai/grok-build-0.1' | 'xiaomi/mimo-v2.5' | 'xiaomi/mimo-v2.5-pro' | 'zai/glm-4.5' | 'zai/glm-4.5-air' | 'zai/glm-4.5v' | 'zai/glm-4.6' | 'zai/glm-4.6v' | 'zai/glm-4.6v-flash' | 'zai/glm-4.7' | 'zai/glm-4.7-flash' | 'zai/glm-4.7-flashx' | 'zai/glm-5' | 'zai/glm-5-turbo' | 'zai/glm-5.1' | 'zai/glm-5.2' | 'zai/glm-5.2-fast' | 'zai/glm-5v-turbo' | (string & {});
6
6
 
7
7
  /**
8
8
  * Shared WebSocket subprotocol contract for AI Gateway realtime and streaming
@@ -843,8 +843,6 @@ type GatewayProviderOptions = {
843
843
  * Currently supports `'implicit-caching'`.
844
844
  */
845
845
  has?: Array<'implicit-caching'>;
846
- /** Filter to providers that are HIPAA compliant with Vercel AI Gateway. */
847
- hipaaCompliant?: boolean;
848
846
  /** Array of model slugs specifying fallback models to use in order. */
849
847
  models?: string[];
850
848
  /** Array of provider slugs that are the only ones allowed to be used. */
package/dist/index.js CHANGED
@@ -2631,7 +2631,7 @@ async function getVercelRequestId() {
2631
2631
  }
2632
2632
 
2633
2633
  // src/version.ts
2634
- var VERSION = true ? "4.0.23" : "0.0.0-test";
2634
+ var VERSION = true ? "4.0.25" : "0.0.0-test";
2635
2635
 
2636
2636
  // src/gateway-provider.ts
2637
2637
  var AI_GATEWAY_PROTOCOL_VERSION = "0.0.1";
@@ -511,7 +511,7 @@ const { text } = await generateText({
511
511
  tools: {
512
512
  getWeather: tool({
513
513
  description: 'Get the current weather for a location',
514
- parameters: z.object({
514
+ inputSchema: z.object({
515
515
  location: z.string().describe('The location to get weather for'),
516
516
  }),
517
517
  execute: async ({ location }) => {
@@ -1037,10 +1037,6 @@ The following gateway provider options are available:
1037
1037
 
1038
1038
  Restricts routing to providers that have agreements with Vercel for AI Gateway to not use prompts for model training. When using BYOK credentials, this filter is not applied. If BYOK credentials fail and the request falls back to system credentials, only providers that do not train on prompt data will be used. If there are no providers available for the model that disallow prompt training, the request will fail.
1039
1039
 
1040
- - **hipaaCompliant** _boolean_
1041
-
1042
- Restricts routing to models and tools from providers that have signed a BAA with Vercel for the use of AI Gateway (requires Vercel HIPAA BAA add on). BYOK credentials are skipped when `hipaaCompliant` is set to `true` to ensure that requests are only routed to providers that support HIPAA compliance.
1043
-
1044
1040
  - **quotaEntityId** _string_
1045
1041
 
1046
1042
  The unique identifier for the entity against which quota is tracked. Used for quota management and enforcement purposes.
@@ -1166,25 +1162,6 @@ const { text } = await generateText({
1166
1162
  });
1167
1163
  ```
1168
1164
 
1169
- #### HIPAA Compliance Example
1170
-
1171
- Set `hipaaCompliant` to true to route requests only to models or tools by providers that have signed a BAA with Vercel for the use of AI Gateway. If the model or tool does not have a HIPAA-compliant provider, the request will fail. When `hipaaCompliant` is `false` or not specified, there is no enforcement of restricting routing. BYOK credentials are skipped when `hipaaCompliant` is set to `true` to ensure that requests are only routed to providers that support HIPAA compliance.
1172
-
1173
- ```ts
1174
- import type { GatewayProviderOptions } from '@ai-sdk/gateway';
1175
- import { generateText } from 'ai';
1176
-
1177
- const { text } = await generateText({
1178
- model: 'anthropic/claude-sonnet-4.6',
1179
- prompt: 'Analyze this patient data...',
1180
- providerOptions: {
1181
- gateway: {
1182
- hipaaCompliant: true,
1183
- } satisfies GatewayProviderOptions,
1184
- },
1185
- });
1186
- ```
1187
-
1188
1165
  #### Quota Entity ID Example
1189
1166
 
1190
1167
  Set `quotaEntityId` to track and enforce quota against a specific entity. This is useful for multi-tenant applications where you need to manage quota at the entity level (e.g., per organization or team).
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@ai-sdk/gateway",
3
3
  "private": false,
4
- "version": "4.0.23",
4
+ "version": "4.0.25",
5
5
  "type": "module",
6
6
  "license": "Apache-2.0",
7
7
  "sideEffects": false,
@@ -32,7 +32,7 @@
32
32
  "dependencies": {
33
33
  "@vercel/oidc": "3.2.0",
34
34
  "@ai-sdk/provider": "4.0.3",
35
- "@ai-sdk/provider-utils": "5.0.11"
35
+ "@ai-sdk/provider-utils": "5.0.12"
36
36
  },
37
37
  "devDependencies": {
38
38
  "@types/node": "22.19.19",
@@ -81,10 +81,6 @@ export type GatewayModelId =
81
81
  | 'kwaipilot/kat-coder-pro-v2.5'
82
82
  | 'meta/llama-3.1-70b'
83
83
  | 'meta/llama-3.1-8b'
84
- | 'meta/llama-3.2-11b'
85
- | 'meta/llama-3.2-1b'
86
- | 'meta/llama-3.2-3b'
87
- | 'meta/llama-3.2-90b'
88
84
  | 'meta/llama-3.3-70b'
89
85
  | 'meta/llama-4-maverick'
90
86
  | 'meta/llama-4-scout'
@@ -21,9 +21,6 @@ export type GatewayProviderOptions = {
21
21
  */
22
22
  has?: Array<'implicit-caching'>;
23
23
 
24
- /** Filter to providers that are HIPAA compliant with Vercel AI Gateway. */
25
- hipaaCompliant?: boolean;
26
-
27
24
  /** Array of model slugs specifying fallback models to use in order. */
28
25
  models?: string[];
29
26