@ai-sdk/gateway 2.0.80 → 2.0.82
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 +12 -0
- package/dist/index.d.mts +50 -2
- package/dist/index.d.ts +50 -2
- package/dist/index.js +175 -75
- package/dist/index.js.map +1 -1
- package/dist/index.mjs +229 -122
- package/dist/index.mjs.map +1 -1
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# @ai-sdk/gateway
|
|
2
2
|
|
|
3
|
+
## 2.0.82
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- eacfb5e: feat (provider/gateway): add get-generation support
|
|
8
|
+
|
|
9
|
+
## 2.0.81
|
|
10
|
+
|
|
11
|
+
### Patch Changes
|
|
12
|
+
|
|
13
|
+
- dc91bcc: Backport: chore(provider/gateway): update gateway model settings files
|
|
14
|
+
|
|
3
15
|
## 2.0.80
|
|
4
16
|
|
|
5
17
|
### Patch Changes
|
package/dist/index.d.mts
CHANGED
|
@@ -2,7 +2,7 @@ import { LanguageModelV2, ProviderV2, EmbeddingModelV2, ImageModelV2, TypeValida
|
|
|
2
2
|
import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
|
|
3
3
|
import { FetchFunction, InferValidator } 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/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-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-3.5-haiku' | 'anthropic/claude-3.7-sonnet' | 'anthropic/claude-haiku-4.5' | 'anthropic/claude-opus-4' | 'anthropic/claude-opus-4.1' | 'anthropic/claude-opus-4.5' | 'anthropic/claude-opus-4.
|
|
5
|
+
type GatewayModelId = 'alibaba/qwen-3-14b' | 'alibaba/qwen-3-235b' | 'alibaba/qwen-3-30b' | 'alibaba/qwen-3-32b' | '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-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-3.5-haiku' | 'anthropic/claude-3.7-sonnet' | '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-sonnet-4' | 'anthropic/claude-sonnet-4.5' | 'anthropic/claude-sonnet-4.6' | 'arcee-ai/trinity-large-preview' | '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' | 'google/gemini-2.0-flash' | 'google/gemini-2.0-flash-lite' | '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-preview' | 'google/gemini-3.1-flash-lite-preview' | 'google/gemini-3.1-pro-preview' | 'google/gemma-4-26b-a4b-it' | 'google/gemma-4-31b-it' | 'inception/mercury-2' | 'inception/mercury-coder-small' | 'kwaipilot/kat-coder-pro-v1' | 'kwaipilot/kat-coder-pro-v2' | 'meituan/longcat-flash-chat' | 'meituan/longcat-flash-thinking-2601' | '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' | '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' | 'mistral/codestral' | 'mistral/devstral-2' | 'mistral/devstral-small' | '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-nemo' | 'mistral/mistral-small' | 'mistral/mixtral-8x22b-instruct' | 'mistral/pixtral-12b' | 'mistral/pixtral-large' | 'moonshotai/kimi-k2' | 'moonshotai/kimi-k2-0905' | 'moonshotai/kimi-k2-thinking' | 'moonshotai/kimi-k2-thinking-turbo' | 'moonshotai/kimi-k2-turbo' | 'moonshotai/kimi-k2.5' | 'morph/morph-v3-fast' | 'morph/morph-v3-large' | 'nvidia/nemotron-3-nano-30b-a3b' | 'nvidia/nemotron-3-super-120b-a12b' | 'nvidia/nemotron-nano-12b-v2-vl' | 'nvidia/nemotron-nano-9b-v2' | 'openai/gpt-3.5-turbo' | 'openai/gpt-3.5-turbo-instruct' | '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-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' | 'prime-intellect/intellect-3' | 'xai/grok-3' | 'xai/grok-3-fast' | 'xai/grok-3-mini' | 'xai/grok-3-mini-fast' | 'xai/grok-4' | 'xai/grok-4-fast-non-reasoning' | 'xai/grok-4-fast-reasoning' | '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-code-fast-1' | 'xiaomi/mimo-v2-flash' | 'xiaomi/mimo-v2-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-5v-turbo' | (string & {});
|
|
6
6
|
|
|
7
7
|
declare const KNOWN_MODEL_TYPES: readonly ["embedding", "image", "language"];
|
|
8
8
|
type KnownModelType = (typeof KNOWN_MODEL_TYPES)[number];
|
|
@@ -120,6 +120,49 @@ interface GatewaySpendReportResponse {
|
|
|
120
120
|
results: GatewaySpendReportRow[];
|
|
121
121
|
}
|
|
122
122
|
|
|
123
|
+
interface GatewayGenerationInfoParams {
|
|
124
|
+
/** The generation ID to look up (format: gen_<ulid>) */
|
|
125
|
+
id: string;
|
|
126
|
+
}
|
|
127
|
+
interface GatewayGenerationInfo {
|
|
128
|
+
/** The generation ID */
|
|
129
|
+
id: string;
|
|
130
|
+
/** Total cost in USD */
|
|
131
|
+
totalCost: number;
|
|
132
|
+
/** Upstream inference cost in USD (BYOK only) */
|
|
133
|
+
upstreamInferenceCost: number;
|
|
134
|
+
/** Usage cost in USD (same as totalCost) */
|
|
135
|
+
usage: number;
|
|
136
|
+
/** ISO 8601 timestamp when the generation was created */
|
|
137
|
+
createdAt: string;
|
|
138
|
+
/** Model identifier */
|
|
139
|
+
model: string;
|
|
140
|
+
/** Whether BYOK credentials were used */
|
|
141
|
+
isByok: boolean;
|
|
142
|
+
/** Provider that served this generation */
|
|
143
|
+
providerName: string;
|
|
144
|
+
/** Whether streaming was used */
|
|
145
|
+
streamed: boolean;
|
|
146
|
+
/** Finish reason (e.g. 'stop') */
|
|
147
|
+
finishReason: string;
|
|
148
|
+
/** Time to first token in milliseconds */
|
|
149
|
+
latency: number;
|
|
150
|
+
/** Total generation time in milliseconds */
|
|
151
|
+
generationTime: number;
|
|
152
|
+
/** Number of prompt tokens */
|
|
153
|
+
promptTokens: number;
|
|
154
|
+
/** Number of completion tokens */
|
|
155
|
+
completionTokens: number;
|
|
156
|
+
/** Reasoning tokens used */
|
|
157
|
+
reasoningTokens: number;
|
|
158
|
+
/** Cached tokens used */
|
|
159
|
+
cachedTokens: number;
|
|
160
|
+
/** Cache creation input tokens */
|
|
161
|
+
cacheCreationTokens: number;
|
|
162
|
+
/** Billable web search calls */
|
|
163
|
+
billableWebSearchCalls: number;
|
|
164
|
+
}
|
|
165
|
+
|
|
123
166
|
type GatewayEmbeddingModelId = 'alibaba/qwen3-embedding-0.6b' | 'alibaba/qwen3-embedding-4b' | 'alibaba/qwen3-embedding-8b' | 'amazon/titan-embed-text-v2' | 'cohere/embed-v4.0' | 'google/gemini-embedding-001' | 'google/gemini-embedding-2' | 'google/text-embedding-005' | 'google/text-multilingual-embedding-002' | 'mistral/codestral-embed' | 'mistral/mistral-embed' | 'openai/text-embedding-3-large' | 'openai/text-embedding-3-small' | 'openai/text-embedding-ada-002' | 'voyage/voyage-3-large' | 'voyage/voyage-3.5' | 'voyage/voyage-3.5-lite' | 'voyage/voyage-4' | 'voyage/voyage-4-large' | 'voyage/voyage-4-lite' | 'voyage/voyage-code-2' | 'voyage/voyage-code-3' | 'voyage/voyage-finance-2' | 'voyage/voyage-law-2' | (string & {});
|
|
124
167
|
|
|
125
168
|
type GatewayImageModelId = 'bfl/flux-2-flex' | 'bfl/flux-2-klein-4b' | 'bfl/flux-2-klein-9b' | 'bfl/flux-2-max' | 'bfl/flux-2-pro' | 'bfl/flux-kontext-max' | 'bfl/flux-kontext-pro' | 'bfl/flux-pro-1.0-fill' | 'bfl/flux-pro-1.1' | 'bfl/flux-pro-1.1-ultra' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.5' | 'bytedance/seedream-5.0-lite' | 'google/imagen-4.0-fast-generate-001' | 'google/imagen-4.0-generate-001' | 'google/imagen-4.0-ultra-generate-001' | 'openai/gpt-image-1' | 'openai/gpt-image-1-mini' | 'openai/gpt-image-1.5' | 'prodia/flux-fast-schnell' | 'recraft/recraft-v2' | 'recraft/recraft-v3' | 'recraft/recraft-v4' | 'recraft/recraft-v4-pro' | 'xai/grok-imagine-image' | 'xai/grok-imagine-image-pro' | (string & {});
|
|
@@ -428,6 +471,11 @@ interface GatewayProvider extends ProviderV2 {
|
|
|
428
471
|
*/
|
|
429
472
|
getSpendReport(params: GatewaySpendReportParams): Promise<GatewaySpendReportResponse>;
|
|
430
473
|
/**
|
|
474
|
+
* Returns detailed information about a specific generation by its ID,
|
|
475
|
+
* including cost, token usage, latency, and provider details.
|
|
476
|
+
*/
|
|
477
|
+
getGenerationInfo(params: GatewayGenerationInfoParams): Promise<GatewayGenerationInfo>;
|
|
478
|
+
/**
|
|
431
479
|
Creates a model for generating text embeddings.
|
|
432
480
|
*/
|
|
433
481
|
textEmbeddingModel(modelId: GatewayEmbeddingModelId): EmbeddingModelV2<string>;
|
|
@@ -630,4 +678,4 @@ declare class GatewayResponseError extends GatewayError {
|
|
|
630
678
|
static isInstance(error: unknown): error is GatewayResponseError;
|
|
631
679
|
}
|
|
632
680
|
|
|
633
|
-
export { GatewayAuthenticationError, type GatewayCreditsResponse, GatewayError, type GatewayErrorResponse, GatewayInternalServerError, GatewayInvalidRequestError, type GatewayLanguageModelEntry, type GatewayLanguageModelSpecification, type GatewayLanguageModelEntry as GatewayModelEntry, type GatewayModelId, GatewayModelNotFoundError, type GatewayProvider, type GatewayProviderOptions, type GatewayProviderSettings, GatewayRateLimitError, GatewayResponseError, type GatewaySpendReportParams, type GatewaySpendReportResponse, type GatewaySpendReportRow, createGatewayProvider as createGateway, createGatewayProvider, gateway };
|
|
681
|
+
export { GatewayAuthenticationError, type GatewayCreditsResponse, GatewayError, type GatewayErrorResponse, type GatewayGenerationInfo, type GatewayGenerationInfoParams, GatewayInternalServerError, GatewayInvalidRequestError, type GatewayLanguageModelEntry, type GatewayLanguageModelSpecification, type GatewayLanguageModelEntry as GatewayModelEntry, type GatewayModelId, GatewayModelNotFoundError, type GatewayProvider, type GatewayProviderOptions, type GatewayProviderSettings, GatewayRateLimitError, GatewayResponseError, type GatewaySpendReportParams, type GatewaySpendReportResponse, type GatewaySpendReportRow, createGatewayProvider as createGateway, createGatewayProvider, gateway };
|
package/dist/index.d.ts
CHANGED
|
@@ -2,7 +2,7 @@ import { LanguageModelV2, ProviderV2, EmbeddingModelV2, ImageModelV2, TypeValida
|
|
|
2
2
|
import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
|
|
3
3
|
import { FetchFunction, InferValidator } 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/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-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-3.5-haiku' | 'anthropic/claude-3.7-sonnet' | 'anthropic/claude-haiku-4.5' | 'anthropic/claude-opus-4' | 'anthropic/claude-opus-4.1' | 'anthropic/claude-opus-4.5' | 'anthropic/claude-opus-4.
|
|
5
|
+
type GatewayModelId = 'alibaba/qwen-3-14b' | 'alibaba/qwen-3-235b' | 'alibaba/qwen-3-30b' | 'alibaba/qwen-3-32b' | '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-instruct' | 'alibaba/qwen3-vl-thinking' | 'alibaba/qwen3.5-flash' | 'alibaba/qwen3.5-plus' | 'alibaba/qwen3.6-plus' | 'amazon/nova-2-lite' | 'amazon/nova-lite' | 'amazon/nova-micro' | 'amazon/nova-pro' | 'anthropic/claude-3-haiku' | 'anthropic/claude-3.5-haiku' | 'anthropic/claude-3.7-sonnet' | '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-sonnet-4' | 'anthropic/claude-sonnet-4.5' | 'anthropic/claude-sonnet-4.6' | 'arcee-ai/trinity-large-preview' | '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' | 'google/gemini-2.0-flash' | 'google/gemini-2.0-flash-lite' | '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-preview' | 'google/gemini-3.1-flash-lite-preview' | 'google/gemini-3.1-pro-preview' | 'google/gemma-4-26b-a4b-it' | 'google/gemma-4-31b-it' | 'inception/mercury-2' | 'inception/mercury-coder-small' | 'kwaipilot/kat-coder-pro-v1' | 'kwaipilot/kat-coder-pro-v2' | 'meituan/longcat-flash-chat' | 'meituan/longcat-flash-thinking-2601' | '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' | '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' | 'mistral/codestral' | 'mistral/devstral-2' | 'mistral/devstral-small' | '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-nemo' | 'mistral/mistral-small' | 'mistral/mixtral-8x22b-instruct' | 'mistral/pixtral-12b' | 'mistral/pixtral-large' | 'moonshotai/kimi-k2' | 'moonshotai/kimi-k2-0905' | 'moonshotai/kimi-k2-thinking' | 'moonshotai/kimi-k2-thinking-turbo' | 'moonshotai/kimi-k2-turbo' | 'moonshotai/kimi-k2.5' | 'morph/morph-v3-fast' | 'morph/morph-v3-large' | 'nvidia/nemotron-3-nano-30b-a3b' | 'nvidia/nemotron-3-super-120b-a12b' | 'nvidia/nemotron-nano-12b-v2-vl' | 'nvidia/nemotron-nano-9b-v2' | 'openai/gpt-3.5-turbo' | 'openai/gpt-3.5-turbo-instruct' | '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-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' | 'prime-intellect/intellect-3' | 'xai/grok-3' | 'xai/grok-3-fast' | 'xai/grok-3-mini' | 'xai/grok-3-mini-fast' | 'xai/grok-4' | 'xai/grok-4-fast-non-reasoning' | 'xai/grok-4-fast-reasoning' | '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-code-fast-1' | 'xiaomi/mimo-v2-flash' | 'xiaomi/mimo-v2-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-5v-turbo' | (string & {});
|
|
6
6
|
|
|
7
7
|
declare const KNOWN_MODEL_TYPES: readonly ["embedding", "image", "language"];
|
|
8
8
|
type KnownModelType = (typeof KNOWN_MODEL_TYPES)[number];
|
|
@@ -120,6 +120,49 @@ interface GatewaySpendReportResponse {
|
|
|
120
120
|
results: GatewaySpendReportRow[];
|
|
121
121
|
}
|
|
122
122
|
|
|
123
|
+
interface GatewayGenerationInfoParams {
|
|
124
|
+
/** The generation ID to look up (format: gen_<ulid>) */
|
|
125
|
+
id: string;
|
|
126
|
+
}
|
|
127
|
+
interface GatewayGenerationInfo {
|
|
128
|
+
/** The generation ID */
|
|
129
|
+
id: string;
|
|
130
|
+
/** Total cost in USD */
|
|
131
|
+
totalCost: number;
|
|
132
|
+
/** Upstream inference cost in USD (BYOK only) */
|
|
133
|
+
upstreamInferenceCost: number;
|
|
134
|
+
/** Usage cost in USD (same as totalCost) */
|
|
135
|
+
usage: number;
|
|
136
|
+
/** ISO 8601 timestamp when the generation was created */
|
|
137
|
+
createdAt: string;
|
|
138
|
+
/** Model identifier */
|
|
139
|
+
model: string;
|
|
140
|
+
/** Whether BYOK credentials were used */
|
|
141
|
+
isByok: boolean;
|
|
142
|
+
/** Provider that served this generation */
|
|
143
|
+
providerName: string;
|
|
144
|
+
/** Whether streaming was used */
|
|
145
|
+
streamed: boolean;
|
|
146
|
+
/** Finish reason (e.g. 'stop') */
|
|
147
|
+
finishReason: string;
|
|
148
|
+
/** Time to first token in milliseconds */
|
|
149
|
+
latency: number;
|
|
150
|
+
/** Total generation time in milliseconds */
|
|
151
|
+
generationTime: number;
|
|
152
|
+
/** Number of prompt tokens */
|
|
153
|
+
promptTokens: number;
|
|
154
|
+
/** Number of completion tokens */
|
|
155
|
+
completionTokens: number;
|
|
156
|
+
/** Reasoning tokens used */
|
|
157
|
+
reasoningTokens: number;
|
|
158
|
+
/** Cached tokens used */
|
|
159
|
+
cachedTokens: number;
|
|
160
|
+
/** Cache creation input tokens */
|
|
161
|
+
cacheCreationTokens: number;
|
|
162
|
+
/** Billable web search calls */
|
|
163
|
+
billableWebSearchCalls: number;
|
|
164
|
+
}
|
|
165
|
+
|
|
123
166
|
type GatewayEmbeddingModelId = 'alibaba/qwen3-embedding-0.6b' | 'alibaba/qwen3-embedding-4b' | 'alibaba/qwen3-embedding-8b' | 'amazon/titan-embed-text-v2' | 'cohere/embed-v4.0' | 'google/gemini-embedding-001' | 'google/gemini-embedding-2' | 'google/text-embedding-005' | 'google/text-multilingual-embedding-002' | 'mistral/codestral-embed' | 'mistral/mistral-embed' | 'openai/text-embedding-3-large' | 'openai/text-embedding-3-small' | 'openai/text-embedding-ada-002' | 'voyage/voyage-3-large' | 'voyage/voyage-3.5' | 'voyage/voyage-3.5-lite' | 'voyage/voyage-4' | 'voyage/voyage-4-large' | 'voyage/voyage-4-lite' | 'voyage/voyage-code-2' | 'voyage/voyage-code-3' | 'voyage/voyage-finance-2' | 'voyage/voyage-law-2' | (string & {});
|
|
124
167
|
|
|
125
168
|
type GatewayImageModelId = 'bfl/flux-2-flex' | 'bfl/flux-2-klein-4b' | 'bfl/flux-2-klein-9b' | 'bfl/flux-2-max' | 'bfl/flux-2-pro' | 'bfl/flux-kontext-max' | 'bfl/flux-kontext-pro' | 'bfl/flux-pro-1.0-fill' | 'bfl/flux-pro-1.1' | 'bfl/flux-pro-1.1-ultra' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.5' | 'bytedance/seedream-5.0-lite' | 'google/imagen-4.0-fast-generate-001' | 'google/imagen-4.0-generate-001' | 'google/imagen-4.0-ultra-generate-001' | 'openai/gpt-image-1' | 'openai/gpt-image-1-mini' | 'openai/gpt-image-1.5' | 'prodia/flux-fast-schnell' | 'recraft/recraft-v2' | 'recraft/recraft-v3' | 'recraft/recraft-v4' | 'recraft/recraft-v4-pro' | 'xai/grok-imagine-image' | 'xai/grok-imagine-image-pro' | (string & {});
|
|
@@ -428,6 +471,11 @@ interface GatewayProvider extends ProviderV2 {
|
|
|
428
471
|
*/
|
|
429
472
|
getSpendReport(params: GatewaySpendReportParams): Promise<GatewaySpendReportResponse>;
|
|
430
473
|
/**
|
|
474
|
+
* Returns detailed information about a specific generation by its ID,
|
|
475
|
+
* including cost, token usage, latency, and provider details.
|
|
476
|
+
*/
|
|
477
|
+
getGenerationInfo(params: GatewayGenerationInfoParams): Promise<GatewayGenerationInfo>;
|
|
478
|
+
/**
|
|
431
479
|
Creates a model for generating text embeddings.
|
|
432
480
|
*/
|
|
433
481
|
textEmbeddingModel(modelId: GatewayEmbeddingModelId): EmbeddingModelV2<string>;
|
|
@@ -630,4 +678,4 @@ declare class GatewayResponseError extends GatewayError {
|
|
|
630
678
|
static isInstance(error: unknown): error is GatewayResponseError;
|
|
631
679
|
}
|
|
632
680
|
|
|
633
|
-
export { GatewayAuthenticationError, type GatewayCreditsResponse, GatewayError, type GatewayErrorResponse, GatewayInternalServerError, GatewayInvalidRequestError, type GatewayLanguageModelEntry, type GatewayLanguageModelSpecification, type GatewayLanguageModelEntry as GatewayModelEntry, type GatewayModelId, GatewayModelNotFoundError, type GatewayProvider, type GatewayProviderOptions, type GatewayProviderSettings, GatewayRateLimitError, GatewayResponseError, type GatewaySpendReportParams, type GatewaySpendReportResponse, type GatewaySpendReportRow, createGatewayProvider as createGateway, createGatewayProvider, gateway };
|
|
681
|
+
export { GatewayAuthenticationError, type GatewayCreditsResponse, GatewayError, type GatewayErrorResponse, type GatewayGenerationInfo, type GatewayGenerationInfoParams, GatewayInternalServerError, GatewayInvalidRequestError, type GatewayLanguageModelEntry, type GatewayLanguageModelSpecification, type GatewayLanguageModelEntry as GatewayModelEntry, type GatewayModelId, GatewayModelNotFoundError, type GatewayProvider, type GatewayProviderOptions, type GatewayProviderSettings, GatewayRateLimitError, GatewayResponseError, type GatewaySpendReportParams, type GatewaySpendReportResponse, type GatewaySpendReportRow, createGatewayProvider as createGateway, createGatewayProvider, gateway };
|