@mastra/mcp-docs-server 1.2.13-alpha.11 → 1.2.13-alpha.12
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/.docs/docs/capabilities/channels/imessage.md +181 -0
- package/.docs/docs/capabilities/channels/overview.md +1 -0
- package/.docs/docs/datasets/running-experiments.md +33 -0
- package/.docs/models/environment-variables.md +5 -1
- package/.docs/models/gateways/netlify.md +1 -2
- package/.docs/models/gateways/openrouter.md +3 -1
- package/.docs/models/gateways/vercel.md +6 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/alibaba-cn.md +3 -1
- package/.docs/models/providers/alibaba-token-plan-cn.md +27 -25
- package/.docs/models/providers/alibaba-token-plan.md +27 -25
- package/.docs/models/providers/alibaba.md +2 -1
- package/.docs/models/providers/ambient.md +13 -12
- package/.docs/models/providers/baseten.md +3 -1
- package/.docs/models/providers/chutes.md +6 -8
- package/.docs/models/providers/crof.md +2 -1
- package/.docs/models/providers/crossmodel.md +4 -1
- package/.docs/models/providers/deepinfra.md +9 -2
- package/.docs/models/providers/digitalocean.md +34 -27
- package/.docs/models/providers/empiriolabs.md +4 -1
- package/.docs/models/providers/fireworks-ai.md +20 -19
- package/.docs/models/providers/greenpt.md +17 -8
- package/.docs/models/providers/groq.md +20 -20
- package/.docs/models/providers/huggingface.md +3 -1
- package/.docs/models/providers/hyper.md +9 -7
- package/.docs/models/providers/impossibl.md +148 -0
- package/.docs/models/providers/infomaniak.md +83 -0
- package/.docs/models/providers/kilo.md +349 -350
- package/.docs/models/providers/llmgateway.md +3 -1
- package/.docs/models/providers/mistral.md +5 -2
- package/.docs/models/providers/modal.md +5 -4
- package/.docs/models/providers/modelis.md +81 -0
- package/.docs/models/providers/nano-gpt.md +146 -148
- package/.docs/models/providers/neuralwatt.md +2 -1
- package/.docs/models/providers/ofox.md +2 -2
- package/.docs/models/providers/ollama-cloud.md +23 -22
- package/.docs/models/providers/opencode-go.md +3 -2
- package/.docs/models/providers/requesty.md +54 -45
- package/.docs/models/providers/scx.md +74 -0
- package/.docs/models/providers/tensorx.md +97 -0
- package/.docs/models/providers/togetherai.md +2 -1
- package/.docs/models/providers/umans-ai-coding-plan.md +11 -9
- package/.docs/models/providers/umans-ai.md +11 -9
- package/.docs/models/providers/wandb.md +2 -2
- package/.docs/models/providers/zai-coding-plan.md +7 -7
- package/.docs/models/providers/zhipuai-coding-plan.md +9 -9
- package/.docs/models/providers.md +5 -1
- package/CHANGELOG.md +7 -0
- package/package.json +5 -5
|
@@ -0,0 +1,181 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# iMessage
|
|
4
|
+
|
|
5
|
+
iMessage channels let a Mastra agent receive direct messages and group messages from iMessage. Mastra handles the agent wiring, the webhook route, and the gateway listener; the Photon iMessage adapter docs cover number provisioning, credentials, and webhook registration.
|
|
6
|
+
|
|
7
|
+
## Install the adapter
|
|
8
|
+
|
|
9
|
+
Install the Photon iMessage adapter:
|
|
10
|
+
|
|
11
|
+
**npm**:
|
|
12
|
+
|
|
13
|
+
```bash
|
|
14
|
+
npm install @photon-ai/chat-adapter-imessage
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
**pnpm**:
|
|
18
|
+
|
|
19
|
+
```bash
|
|
20
|
+
pnpm add @photon-ai/chat-adapter-imessage
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
**Yarn**:
|
|
24
|
+
|
|
25
|
+
```bash
|
|
26
|
+
yarn add @photon-ai/chat-adapter-imessage
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
**Bun**:
|
|
30
|
+
|
|
31
|
+
```bash
|
|
32
|
+
bun add @photon-ai/chat-adapter-imessage
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
## Agent configuration
|
|
36
|
+
|
|
37
|
+
Add `createiMessageAdapter()` to the agent's `channels.adapters` object:
|
|
38
|
+
|
|
39
|
+
```typescript
|
|
40
|
+
import { Agent } from '@mastra/core/agent'
|
|
41
|
+
import { createiMessageAdapter } from '@photon-ai/chat-adapter-imessage'
|
|
42
|
+
|
|
43
|
+
export const imessageAgent = new Agent({
|
|
44
|
+
id: 'imessage-agent',
|
|
45
|
+
name: 'iMessage Agent',
|
|
46
|
+
instructions: 'Answer questions and help with tasks over iMessage.',
|
|
47
|
+
model: 'openai/gpt-5.6-sol',
|
|
48
|
+
channels: {
|
|
49
|
+
adapters: {
|
|
50
|
+
imessage: {
|
|
51
|
+
adapter: createiMessageAdapter(),
|
|
52
|
+
toolDisplay: 'text',
|
|
53
|
+
},
|
|
54
|
+
},
|
|
55
|
+
threadContext: { maxMessages: 0 },
|
|
56
|
+
},
|
|
57
|
+
})
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
Register the agent on the Mastra instance:
|
|
61
|
+
|
|
62
|
+
```typescript
|
|
63
|
+
import { Mastra } from '@mastra/core'
|
|
64
|
+
import { imessageAgent } from './agents/imessage-agent'
|
|
65
|
+
|
|
66
|
+
export const mastra = new Mastra({
|
|
67
|
+
agents: { imessageAgent },
|
|
68
|
+
})
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
Use `imessage` as the adapter key. Mastra derives the webhook path and the `platform` value on `requestContext` from this key.
|
|
72
|
+
|
|
73
|
+
`toolDisplay: 'text'` describes tool calls in the message, since iMessage has no interactive cards for Approve and Deny actions. `threadContext: { maxMessages: 0 }` skips the platform history lookup Mastra runs when an agent is first mentioned in a group chat, which the adapter can't perform. Both override defaults that assume platform features iMessage lacks.
|
|
74
|
+
|
|
75
|
+
## Adapter setup
|
|
76
|
+
|
|
77
|
+
Follow the [Photon iMessage adapter docs](https://github.com/photon-hq/vercel-chat-adapter-imessage) for iMessage-specific setup, including number provisioning, hosted and self-hosted modes, and webhook registration. The adapter picks its mode from the environment variables you set.
|
|
78
|
+
|
|
79
|
+
For the hosted service, create a project at [app.photon.codes](https://app.photon.codes) and use the project credentials:
|
|
80
|
+
|
|
81
|
+
```bash
|
|
82
|
+
IMESSAGE_PROJECT_ID=your-project-id
|
|
83
|
+
IMESSAGE_PROJECT_SECRET=your-project-secret
|
|
84
|
+
IMESSAGE_WEBHOOK_SECRET=your-webhook-signing-secret
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
For a self-hosted server, point the adapter at its gRPC address, written as `host:port`. The adapter strips any URL scheme and appends `:443` to a bare host:
|
|
88
|
+
|
|
89
|
+
```bash
|
|
90
|
+
IMESSAGE_SERVER_URL=imessage.example.com:443
|
|
91
|
+
IMESSAGE_API_KEY=your-server-token
|
|
92
|
+
IMESSAGE_PHONE=+15551234567
|
|
93
|
+
```
|
|
94
|
+
|
|
95
|
+
`IMESSAGE_PHONE` is optional and routes messages when a self-hosted server has several numbers. You can also pass these values to `createiMessageAdapter()` directly, including a `credentials` function that resolves the project ID and secret at first use from a secret store.
|
|
96
|
+
|
|
97
|
+
## Webhook URL
|
|
98
|
+
|
|
99
|
+
Mastra generates the iMessage webhook route from the agent ID and adapter key:
|
|
100
|
+
|
|
101
|
+
```text
|
|
102
|
+
/api/agents/imessage-agent/channels/imessage/webhook
|
|
103
|
+
```
|
|
104
|
+
|
|
105
|
+
Use your public Mastra server URL as the base URL:
|
|
106
|
+
|
|
107
|
+
```text
|
|
108
|
+
https://your-app.example.com/api/agents/imessage-agent/channels/imessage/webhook
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
Register this URL in the [Photon dashboard](https://app.photon.codes), then set the signing secret it returns as `IMESSAGE_WEBHOOK_SECRET`. The secret is shown once at registration. The adapter verifies the signature on every delivery and rejects requests that don't match. Webhooks are available in hosted mode only.
|
|
112
|
+
|
|
113
|
+
Photon retries failed deliveries with backoff and delivers at least once, so the same message can arrive twice. Chat SDK drops the repeat using the channel state adapter, and Mastra's default keeps those dedup keys in memory. That covers a single long-running server.
|
|
114
|
+
|
|
115
|
+
A repeat can still reach the agent after a restart, or on serverless where the retry is routed to a different instance. Pass a shared state adapter on `channels.state` so dedup keys are visible everywhere. Install one alongside the adapter:
|
|
116
|
+
|
|
117
|
+
**npm**:
|
|
118
|
+
|
|
119
|
+
```bash
|
|
120
|
+
npm install @chat-adapter/state-redis
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
**pnpm**:
|
|
124
|
+
|
|
125
|
+
```bash
|
|
126
|
+
pnpm add @chat-adapter/state-redis
|
|
127
|
+
```
|
|
128
|
+
|
|
129
|
+
**Yarn**:
|
|
130
|
+
|
|
131
|
+
```bash
|
|
132
|
+
yarn add @chat-adapter/state-redis
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
**Bun**:
|
|
136
|
+
|
|
137
|
+
```bash
|
|
138
|
+
bun add @chat-adapter/state-redis
|
|
139
|
+
```
|
|
140
|
+
|
|
141
|
+
`createRedisState()` reads the `REDIS_URL` environment variable:
|
|
142
|
+
|
|
143
|
+
```typescript
|
|
144
|
+
import { createRedisState } from '@chat-adapter/state-redis'
|
|
145
|
+
|
|
146
|
+
channels: {
|
|
147
|
+
adapters: {
|
|
148
|
+
imessage: {
|
|
149
|
+
adapter: createiMessageAdapter(),
|
|
150
|
+
toolDisplay: 'text',
|
|
151
|
+
},
|
|
152
|
+
},
|
|
153
|
+
threadContext: { maxMessages: 0 },
|
|
154
|
+
state: createRedisState(),
|
|
155
|
+
},
|
|
156
|
+
```
|
|
157
|
+
|
|
158
|
+
This matters most for tools with side effects, where handling the same message twice is visible to the user.
|
|
159
|
+
|
|
160
|
+
> **Note:** Photon delivers to public HTTPS endpoints only. It won't deliver to `http://`, to private addresses like `localhost`, or through a redirect. For local development, use a tunnel as described in the [Channels overview](https://mastra.ai/docs/capabilities/channels/overview).
|
|
161
|
+
|
|
162
|
+
## Gateway listener
|
|
163
|
+
|
|
164
|
+
The adapter can hold an open connection and stream messages in real time instead of receiving webhooks. This works in both hosted and self-hosted modes.
|
|
165
|
+
|
|
166
|
+
Mastra starts this listener during initialization and reconnects it if it drops, so no cron job or extra route is needed on a long-running server. Set `gateway: false` on the adapter config to turn it off when you use webhooks:
|
|
167
|
+
|
|
168
|
+
```typescript
|
|
169
|
+
imessage: {
|
|
170
|
+
adapter: createiMessageAdapter(),
|
|
171
|
+
toolDisplay: 'text',
|
|
172
|
+
gateway: false,
|
|
173
|
+
},
|
|
174
|
+
```
|
|
175
|
+
|
|
176
|
+
On serverless platforms, prefer webhooks. A gateway listener needs a process that stays alive. See [Serverless deployment](https://mastra.ai/docs/capabilities/channels/overview).
|
|
177
|
+
|
|
178
|
+
## Related
|
|
179
|
+
|
|
180
|
+
- [Channels overview](https://mastra.ai/docs/capabilities/channels/overview)
|
|
181
|
+
- [More](https://mastra.ai/docs/capabilities/channels/other-adapters)
|
|
@@ -13,6 +13,7 @@ Start with the page for your platform:
|
|
|
13
13
|
- [Discord](https://mastra.ai/docs/capabilities/channels/discord)
|
|
14
14
|
- [Telegram](https://mastra.ai/docs/capabilities/channels/telegram)
|
|
15
15
|
- [WhatsApp](https://mastra.ai/docs/capabilities/channels/whatsapp)
|
|
16
|
+
- [iMessage](https://mastra.ai/docs/capabilities/channels/imessage)
|
|
16
17
|
|
|
17
18
|
[More](https://mastra.ai/docs/capabilities/channels/other-adapters) lists additional platforms. Mastra channels work with compatible [Chat SDK adapters](https://chat-sdk.dev/adapters) beyond the platforms listed here, and the same Mastra configuration pattern applies across adapters.
|
|
18
19
|
|
|
@@ -155,6 +155,39 @@ When `startExperimentAsync()` runs with `experiments: 'none'`, it doesn't persis
|
|
|
155
155
|
|
|
156
156
|
Use synchronous `startExperiment()` when the caller needs the returned summary. An experiment event observer can receive lifecycle events and the terminal summary.
|
|
157
157
|
|
|
158
|
+
## Observe experiment events
|
|
159
|
+
|
|
160
|
+
Use `onEvent` to receive versioned, JSON-safe lifecycle events while an experiment runs. This works with `startExperiment()`, `startExperimentAsync()`, and `runExperiment()`.
|
|
161
|
+
|
|
162
|
+
```typescript
|
|
163
|
+
import type { ExperimentEvent } from '@mastra/core/datasets'
|
|
164
|
+
|
|
165
|
+
const events: ExperimentEvent[] = []
|
|
166
|
+
|
|
167
|
+
await dataset.startExperimentAsync({
|
|
168
|
+
task: async ({ input }) => processItem(input),
|
|
169
|
+
persistence: { experiments: 'none' },
|
|
170
|
+
onEvent: async event => {
|
|
171
|
+
events.push(event)
|
|
172
|
+
await publishEvent(event)
|
|
173
|
+
},
|
|
174
|
+
})
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
The observer receives these event types:
|
|
178
|
+
|
|
179
|
+
- `experiment.run.started`: Identifies the run, target, resolved dataset version, and item count.
|
|
180
|
+
- `experiment.item.completed`: Reports a committed item result after scoring, including scores, errors, retry count, tool mock details, and stable item identity.
|
|
181
|
+
- `experiment.run.finished`: Reports the terminal outcome and summary counters.
|
|
182
|
+
|
|
183
|
+
Mastra awaits each observer call before delivering the next event. This serialized delivery applies backpressure and ensures event `sequence` values match delivery order, while item execution can remain concurrent.
|
|
184
|
+
|
|
185
|
+
If the observer throws or rejects, Mastra aborts the remaining run and rejects `runExperiment()` with a `MastraError` whose `id` is `EXPERIMENT_EVENT_OBSERVER_FAILED`. It doesn't send a terminal event through the failed observer. For `startExperimentAsync()`, the method has already returned when a detached observer fails, so handle delivery failures inside the observer when the caller needs direct error reporting.
|
|
186
|
+
|
|
187
|
+
The `experiment.run.finished` event is awaited before Mastra persists the final experiment status. Treat the event as the authoritative terminal signal when experiment persistence is disabled, but don't use it as a read-after-write signal for storage.
|
|
188
|
+
|
|
189
|
+
The exported event types are `ExperimentEvent`, `ExperimentRunStartedEvent`, `ExperimentItemCompletedEvent`, and `ExperimentRunFinishedEvent`. Use the discriminated `type` field to narrow an event before reading event-specific properties.
|
|
190
|
+
|
|
158
191
|
## Tool mocks
|
|
159
192
|
|
|
160
193
|
When an experiment runs an agent that calls side-effecting tools, attach static tool mocks to individual dataset items to make the run deterministic. During the experiment, a mocked tool returns its declared output instead of executing. Tools without a mock on the item run live by default.
|
|
@@ -53,7 +53,6 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
53
53
|
| [FreeModel](https://mastra.ai/models/providers/freemodel) | `freemodel/*` | `FREEMODEL_API_KEY` |
|
|
54
54
|
| [Friendli](https://mastra.ai/models/providers/friendli) | `friendli/*` | `FRIENDLI_TOKEN` |
|
|
55
55
|
| [FrogBot](https://mastra.ai/models/providers/frogbot) | `frogbot/*` | `FROGBOT_API_KEY` |
|
|
56
|
-
| [GitHub Models](https://mastra.ai/models/providers/github-models) | `github-models/*` | `GITHUB_TOKEN` |
|
|
57
56
|
| [GMI Cloud](https://mastra.ai/models/providers/gmicloud) | `gmicloud/*` | `GMICLOUD_API_KEY` |
|
|
58
57
|
| [Google](https://mastra.ai/models/providers/google) | `google/*` | `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY` |
|
|
59
58
|
| [GreenPT](https://mastra.ai/models/providers/greenpt) | `greenpt/*` | `GREENPT_API_KEY` |
|
|
@@ -63,10 +62,12 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
63
62
|
| [HPC-AI](https://mastra.ai/models/providers/hpc-ai) | `hpc-ai/*` | `HPC_AI_API_KEY` |
|
|
64
63
|
| [Hugging Face](https://mastra.ai/models/providers/huggingface) | `huggingface/*` | `HF_TOKEN` |
|
|
65
64
|
| [iFlow](https://mastra.ai/models/providers/iflowcn) | `iflowcn/*` | `IFLOW_API_KEY` |
|
|
65
|
+
| [Impossibl](https://mastra.ai/models/providers/impossibl) | `impossibl/*` | `IMPOSSIBL_API_KEY` |
|
|
66
66
|
| [Inception](https://mastra.ai/models/providers/inception) | `inception/*` | `INCEPTION_API_KEY` |
|
|
67
67
|
| [Inceptron](https://mastra.ai/models/providers/inceptron) | `inceptron/*` | `INCEPTRON_API_KEY` |
|
|
68
68
|
| [Inference](https://mastra.ai/models/providers/inference) | `inference/*` | `INFERENCE_API_KEY` |
|
|
69
69
|
| [InferX](https://mastra.ai/models/providers/inferx) | `inferx/*` | `INFERX_API_KEY` |
|
|
70
|
+
| [Infomaniak](https://mastra.ai/models/providers/infomaniak) | `infomaniak/*` | `INFOMANIAK_PRODUCT_ID`, `INFOMANIAK_API_KEY` |
|
|
70
71
|
| [IO.NET](https://mastra.ai/models/providers/io-net) | `io-net/*` | `IOINTELLIGENCE_API_KEY` |
|
|
71
72
|
| [Jiekou.AI](https://mastra.ai/models/providers/jiekou) | `jiekou/*` | `JIEKOU_API_KEY` |
|
|
72
73
|
| [Kenari](https://mastra.ai/models/providers/kenari) | `kenari/*` | `KENARI_API_KEY` |
|
|
@@ -92,6 +93,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
92
93
|
| [Moark](https://mastra.ai/models/providers/moark) | `moark/*` | `MOARK_API_KEY` |
|
|
93
94
|
| [Modal](https://mastra.ai/models/providers/modal) | `modal/*` | `MODAL_PROXY_TOKEN` |
|
|
94
95
|
| [Model Oracle AI](https://mastra.ai/models/providers/model-oracle-ai) | `model-oracle-ai/*` | `MODEL_ORACLE_API_KEY` |
|
|
96
|
+
| [Modelis](https://mastra.ai/models/providers/modelis) | `modelis/*` | `MODELIS_API_KEY` |
|
|
95
97
|
| [ModelScope](https://mastra.ai/models/providers/modelscope) | `modelscope/*` | `MODELSCOPE_API_KEY` |
|
|
96
98
|
| [Moonshot AI](https://mastra.ai/models/providers/moonshotai) | `moonshotai/*` | `MOONSHOT_API_KEY` |
|
|
97
99
|
| [Moonshot AI (China)](https://mastra.ai/models/providers/moonshotai-cn) | `moonshotai-cn/*` | `MOONSHOT_API_KEY` |
|
|
@@ -125,6 +127,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
125
127
|
| [Sakana AI](https://mastra.ai/models/providers/sakana) | `sakana/*` | `SAKANA_API_KEY` |
|
|
126
128
|
| [Sarvam AI](https://mastra.ai/models/providers/sarvam) | `sarvam/*` | `SARVAM_API_KEY` |
|
|
127
129
|
| [Scaleway](https://mastra.ai/models/providers/scaleway) | `scaleway/*` | `SCALEWAY_API_KEY` |
|
|
130
|
+
| [SCX.ai](https://mastra.ai/models/providers/scx) | `scx/*` | `SCX_API_KEY` |
|
|
128
131
|
| [SiliconFlow](https://mastra.ai/models/providers/siliconflow) | `siliconflow/*` | `SILICONFLOW_API_KEY` |
|
|
129
132
|
| [SiliconFlow (China)](https://mastra.ai/models/providers/siliconflow-cn) | `siliconflow-cn/*` | `SILICONFLOW_CN_API_KEY` |
|
|
130
133
|
| [Snowflake Cortex](https://mastra.ai/models/providers/snowflake-cortex) | `snowflake-cortex/*` | `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_CORTEX_PAT` |
|
|
@@ -139,6 +142,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
139
142
|
| [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan) | `tencent-coding-plan/*` | `TENCENT_CODING_PLAN_API_KEY` |
|
|
140
143
|
| [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan) | `tencent-token-plan/*` | `TENCENT_TOKEN_PLAN_API_KEY` |
|
|
141
144
|
| [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub) | `tencent-tokenhub/*` | `TENCENT_TOKENHUB_API_KEY` |
|
|
145
|
+
| [TensorX](https://mastra.ai/models/providers/tensorx) | `tensorx/*` | `TENSORX_API_KEY` |
|
|
142
146
|
| [The Grid AI](https://mastra.ai/models/providers/the-grid-ai) | `the-grid-ai/*` | `THEGRID_API_KEY` |
|
|
143
147
|
| [Thinking Machines](https://mastra.ai/models/providers/thinkingmachines) | `thinkingmachines/*` | `TINKER_API_KEY` |
|
|
144
148
|
| [Tinfoil](https://mastra.ai/models/providers/tinfoil) | `tinfoil/*` | `TINFOIL_API_KEY` |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Netlify
|
|
4
4
|
|
|
5
|
-
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access
|
|
5
|
+
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 67 models through Mastra's model router.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
|
|
8
8
|
|
|
@@ -40,7 +40,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
40
40
|
| `anthropic/claude-fable-5` |
|
|
41
41
|
| `anthropic/claude-haiku-4-5` |
|
|
42
42
|
| `anthropic/claude-haiku-4-5-20251001` |
|
|
43
|
-
| `anthropic/claude-opus-4-1-20250805` |
|
|
44
43
|
| `anthropic/claude-opus-4-5` |
|
|
45
44
|
| `anthropic/claude-opus-4-5-20251101` |
|
|
46
45
|
| `anthropic/claude-opus-4-6` |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# OpenRouter
|
|
4
4
|
|
|
5
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
5
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 337 models through Mastra's model router.
|
|
6
6
|
|
|
7
7
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
8
8
|
|
|
@@ -40,6 +40,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
40
40
|
| `~anthropic/claude-haiku-latest` |
|
|
41
41
|
| `~anthropic/claude-opus-latest` |
|
|
42
42
|
| `~anthropic/claude-sonnet-latest` |
|
|
43
|
+
| `~deepseek/deepseek-v4-flash-latest` |
|
|
43
44
|
| `~google/gemini-flash-latest` |
|
|
44
45
|
| `~google/gemini-pro-latest` |
|
|
45
46
|
| `~moonshotai/kimi-latest` |
|
|
@@ -330,6 +331,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
330
331
|
| `qwen/qwen3.7-flash` |
|
|
331
332
|
| `qwen/qwen3.7-max` |
|
|
332
333
|
| `qwen/qwen3.7-plus` |
|
|
334
|
+
| `qwen/qwen3.8-max` |
|
|
333
335
|
| `rekaai/reka-edge` |
|
|
334
336
|
| `rekaai/reka-flash-3` |
|
|
335
337
|
| `relace/relace-apply-3` |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Vercel
|
|
4
4
|
|
|
5
|
-
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
5
|
+
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 315 models through Mastra's model router.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
|
|
8
8
|
|
|
@@ -64,6 +64,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
64
64
|
| `alibaba/qwen3.7-flash` |
|
|
65
65
|
| `alibaba/qwen3.7-max` |
|
|
66
66
|
| `alibaba/qwen3.7-plus` |
|
|
67
|
+
| `alibaba/qwen3.8-max` |
|
|
67
68
|
| `alibaba/wan-v2.5-t2v-preview` |
|
|
68
69
|
| `alibaba/wan-v2.6-i2v` |
|
|
69
70
|
| `alibaba/wan-v2.6-i2v-flash` |
|
|
@@ -128,6 +129,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
128
129
|
| `deepseek/deepseek-v3.2` |
|
|
129
130
|
| `deepseek/deepseek-v3.2-thinking` |
|
|
130
131
|
| `deepseek/deepseek-v4-flash` |
|
|
132
|
+
| `deepseek/deepseek-v4-flash-0731` |
|
|
131
133
|
| `deepseek/deepseek-v4-pro` |
|
|
132
134
|
| `google/gemini-2.5-flash` |
|
|
133
135
|
| `google/gemini-2.5-flash-image` |
|
|
@@ -157,6 +159,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
157
159
|
| `google/veo-3.0-generate-001` |
|
|
158
160
|
| `google/veo-3.1-fast-generate-001` |
|
|
159
161
|
| `google/veo-3.1-generate-001` |
|
|
162
|
+
| `google/veo-3.1-lite-generate-001` |
|
|
160
163
|
| `inception/mercury-2` |
|
|
161
164
|
| `inception/mercury-coder-small` |
|
|
162
165
|
| `inclusionai/ling-3.0-flash-free` |
|
|
@@ -277,6 +280,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
277
280
|
| `openai/tts-1` |
|
|
278
281
|
| `openai/tts-1-hd` |
|
|
279
282
|
| `openai/whisper-1` |
|
|
283
|
+
| `perplexity/pplx-embed-v1-0.6b` |
|
|
284
|
+
| `perplexity/pplx-embed-v1-4b` |
|
|
280
285
|
| `perplexity/sonar` |
|
|
281
286
|
| `perplexity/sonar-pro` |
|
|
282
287
|
| `perplexity/sonar-reasoning-pro` |
|
package/.docs/models/index.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Model Providers
|
|
4
4
|
|
|
5
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
5
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 5288 models from 168 providers through a single API.
|
|
6
6
|
|
|
7
7
|
## Features
|
|
8
8
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba (China)
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 86 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba (China) documentation](https://www.alibabacloud.com/help/en/model-studio/models).
|
|
8
8
|
|
|
@@ -111,8 +111,10 @@ for await (const chunk of stream) {
|
|
|
111
111
|
| `alibaba-cn/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
112
112
|
| `alibaba-cn/qwen3.6-max-preview` | 246K | | | | | | $1 | $8 |
|
|
113
113
|
| `alibaba-cn/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
114
|
+
| `alibaba-cn/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.12 |
|
|
114
115
|
| `alibaba-cn/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
115
116
|
| `alibaba-cn/qwen3.7-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
117
|
+
| `alibaba-cn/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
|
|
116
118
|
| `alibaba-cn/qwq-32b` | 131K | | | | | | $0.29 | $0.86 |
|
|
117
119
|
| `alibaba-cn/qwq-plus` | 131K | | | | | | $0.23 | $0.57 |
|
|
118
120
|
| `alibaba-cn/siliconflow/deepseek-r1-0528` | 164K | | | | | | $0.50 | $2 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan (China)
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 24 Alibaba Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba Token Plan (China) documentation](https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview).
|
|
8
8
|
|
|
@@ -34,30 +34,32 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `alibaba-token-plan-cn/deepseek-v3.2`
|
|
40
|
-
| `alibaba-token-plan-cn/deepseek-v4-flash`
|
|
41
|
-
| `alibaba-token-plan-cn/deepseek-v4-
|
|
42
|
-
| `alibaba-token-plan-cn/
|
|
43
|
-
| `alibaba-token-plan-cn/glm-5
|
|
44
|
-
| `alibaba-token-plan-cn/glm-5.
|
|
45
|
-
| `alibaba-token-plan-cn/
|
|
46
|
-
| `alibaba-token-plan-cn/happyhorse-1.1-
|
|
47
|
-
| `alibaba-token-plan-cn/happyhorse-1.1-
|
|
48
|
-
| `alibaba-token-plan-cn/
|
|
49
|
-
| `alibaba-token-plan-cn/kimi-k2.
|
|
50
|
-
| `alibaba-token-plan-cn/kimi-k2.
|
|
51
|
-
| `alibaba-token-plan-cn/
|
|
52
|
-
| `alibaba-token-plan-cn/
|
|
53
|
-
| `alibaba-token-plan-cn/qwen-image-2.0
|
|
54
|
-
| `alibaba-token-plan-cn/
|
|
55
|
-
| `alibaba-token-plan-cn/qwen3.6-
|
|
56
|
-
| `alibaba-token-plan-cn/qwen3.
|
|
57
|
-
| `alibaba-token-plan-cn/qwen3.7-
|
|
58
|
-
| `alibaba-token-plan-cn/qwen3.
|
|
59
|
-
| `alibaba-token-plan-cn/
|
|
60
|
-
| `alibaba-token-plan-cn/
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `alibaba-token-plan-cn/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan-cn/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan-cn/deepseek-v4-flash-0731` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan-cn/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan-cn/glm-5` | 203K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan-cn/glm-5.1` | 203K | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan-cn/glm-5.2` | 1.0M | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-i2v` | — | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-r2v` | — | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-t2v` | — | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan-cn/kimi-k2.5` | 262K | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan-cn/kimi-k2.6` | 262K | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan-cn/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan-cn/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan-cn/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan-cn/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
55
|
+
| `alibaba-token-plan-cn/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
56
|
+
| `alibaba-token-plan-cn/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
57
|
+
| `alibaba-token-plan-cn/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
58
|
+
| `alibaba-token-plan-cn/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
59
|
+
| `alibaba-token-plan-cn/qwen3.8-max` | 1.0M | | | | | | — | — |
|
|
60
|
+
| `alibaba-token-plan-cn/qwen3.8-max-preview` | 1.0M | | | | | | — | — |
|
|
61
|
+
| `alibaba-token-plan-cn/wan2.7-image` | 8K | | | | | | — | — |
|
|
62
|
+
| `alibaba-token-plan-cn/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
61
63
|
|
|
62
64
|
## Advanced configuration
|
|
63
65
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 24 Alibaba Token Plan models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba Token Plan documentation](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview).
|
|
8
8
|
|
|
@@ -34,30 +34,32 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `alibaba-token-plan/deepseek-v3.2`
|
|
40
|
-
| `alibaba-token-plan/deepseek-v4-flash`
|
|
41
|
-
| `alibaba-token-plan/deepseek-v4-
|
|
42
|
-
| `alibaba-token-plan/
|
|
43
|
-
| `alibaba-token-plan/glm-5
|
|
44
|
-
| `alibaba-token-plan/glm-5.
|
|
45
|
-
| `alibaba-token-plan/
|
|
46
|
-
| `alibaba-token-plan/happyhorse-1.1-
|
|
47
|
-
| `alibaba-token-plan/happyhorse-1.1-
|
|
48
|
-
| `alibaba-token-plan/
|
|
49
|
-
| `alibaba-token-plan/kimi-k2.
|
|
50
|
-
| `alibaba-token-plan/kimi-k2.
|
|
51
|
-
| `alibaba-token-plan/
|
|
52
|
-
| `alibaba-token-plan/
|
|
53
|
-
| `alibaba-token-plan/qwen-image-2.0
|
|
54
|
-
| `alibaba-token-plan/
|
|
55
|
-
| `alibaba-token-plan/qwen3.6-
|
|
56
|
-
| `alibaba-token-plan/qwen3.
|
|
57
|
-
| `alibaba-token-plan/qwen3.7-
|
|
58
|
-
| `alibaba-token-plan/qwen3.
|
|
59
|
-
| `alibaba-token-plan/
|
|
60
|
-
| `alibaba-token-plan/
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `alibaba-token-plan/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan/deepseek-v4-flash-0731` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan/glm-5` | 203K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan/glm-5.1` | 203K | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan/glm-5.2` | 1.0M | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan/happyhorse-1.1-i2v` | — | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan/happyhorse-1.1-r2v` | — | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan/happyhorse-1.1-t2v` | — | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan/kimi-k2.5` | 262K | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan/kimi-k2.6` | 262K | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
55
|
+
| `alibaba-token-plan/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
56
|
+
| `alibaba-token-plan/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
57
|
+
| `alibaba-token-plan/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
58
|
+
| `alibaba-token-plan/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
59
|
+
| `alibaba-token-plan/qwen3.8-max` | 1.0M | | | | | | — | — |
|
|
60
|
+
| `alibaba-token-plan/qwen3.8-max-preview` | 1.0M | | | | | | — | — |
|
|
61
|
+
| `alibaba-token-plan/wan2.7-image` | 8K | | | | | | — | — |
|
|
62
|
+
| `alibaba-token-plan/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
61
63
|
|
|
62
64
|
## Advanced configuration
|
|
63
65
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 52 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba documentation](https://www.alibabacloud.com/help/en/model-studio/models).
|
|
8
8
|
|
|
@@ -86,6 +86,7 @@ for await (const chunk of stream) {
|
|
|
86
86
|
| `alibaba/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
87
87
|
| `alibaba/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
88
88
|
| `alibaba/qwen3.7-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
89
|
+
| `alibaba/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
89
90
|
| `alibaba/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
90
91
|
|
|
91
92
|
## Advanced configuration
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Ambient
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 10 Ambient models through Mastra's model router. Authentication is handled automatically using the `AMBIENT_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Ambient documentation](https://ambient.xyz).
|
|
8
8
|
|
|
@@ -34,17 +34,18 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `ambient/ambient/large`
|
|
40
|
-
| `ambient/deepseek/deepseek-v4-flash`
|
|
41
|
-
| `ambient/
|
|
42
|
-
| `ambient/moonshotai/kimi-k2.
|
|
43
|
-
| `ambient/
|
|
44
|
-
| `ambient/
|
|
45
|
-
| `ambient/
|
|
46
|
-
| `ambient/
|
|
47
|
-
| `ambient/zai-org/GLM-5.
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `ambient/ambient/large` | 203K | | | | | | $1 | $4 |
|
|
40
|
+
| `ambient/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
41
|
+
| `ambient/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
42
|
+
| `ambient/moonshotai/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
43
|
+
| `ambient/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.73 | $4 |
|
|
44
|
+
| `ambient/stepfun/step-3.7-flash` | 262K | | | | | | $0.19 | $1 |
|
|
45
|
+
| `ambient/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
|
|
46
|
+
| `ambient/z-ai/glm-5.2` | 203K | | | | | | $1 | $4 |
|
|
47
|
+
| `ambient/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
48
|
+
| `ambient/zai-org/GLM-5.2-FP8` | 203K | | | | | | $1 | $4 |
|
|
48
49
|
|
|
49
50
|
## Advanced configuration
|
|
50
51
|
|