@mastra/mcp-docs-server 1.1.1 → 1.1.2
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/deployment/cloud-providers.md +1 -1
- package/.docs/docs/deployment/overview.md +1 -1
- package/.docs/docs/deployment/studio.md +234 -0
- package/.docs/docs/memory/observational-memory.md +86 -11
- package/.docs/docs/streaming/events.md +23 -0
- package/.docs/docs/workspace/filesystem.md +72 -1
- package/.docs/docs/workspace/overview.md +95 -12
- package/.docs/docs/workspace/sandbox.md +2 -0
- package/.docs/guides/agent-frameworks/ai-sdk.md +6 -2
- package/.docs/guides/deployment/cloudflare.md +99 -0
- package/.docs/models/gateways/openrouter.md +6 -3
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/cerebras.md +2 -1
- package/.docs/models/providers/fireworks-ai.md +2 -1
- package/.docs/models/providers/friendli.md +3 -2
- package/.docs/models/providers/huggingface.md +3 -2
- package/.docs/models/providers/jiekou.md +4 -2
- package/.docs/models/providers/minimax-cn-coding-plan.md +3 -2
- package/.docs/models/providers/minimax-cn.md +3 -2
- package/.docs/models/providers/minimax-coding-plan.md +3 -2
- package/.docs/models/providers/minimax.md +3 -2
- package/.docs/models/providers/nano-gpt.md +12 -4
- package/.docs/models/providers/novita-ai.md +4 -2
- package/.docs/models/providers/ollama-cloud.md +3 -1
- package/.docs/models/providers/openai.md +15 -14
- package/.docs/models/providers/opencode.md +31 -32
- package/.docs/models/providers/stackit.md +78 -0
- package/.docs/models/providers/synthetic.md +1 -1
- package/.docs/models/providers/zai-coding-plan.md +3 -2
- package/.docs/models/providers/zai.md +3 -2
- package/.docs/models/providers/zhipuai-coding-plan.md +3 -2
- package/.docs/models/providers/zhipuai.md +3 -2
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/ai-sdk/with-mastra.md +1 -1
- package/.docs/reference/cli/mastra.md +1 -1
- package/.docs/reference/deployer/cloudflare.md +35 -12
- package/.docs/reference/index.md +3 -0
- package/.docs/reference/memory/observational-memory.md +318 -9
- package/.docs/reference/streaming/workflows/stream.md +1 -0
- package/.docs/reference/workflows/workflow-methods/foreach.md +30 -0
- package/.docs/reference/workspace/e2b-sandbox.md +299 -0
- package/.docs/reference/workspace/gcs-filesystem.md +170 -0
- package/.docs/reference/workspace/s3-filesystem.md +169 -0
- package/CHANGELOG.md +14 -0
- package/package.json +6 -6
- package/.docs/guides/deployment/cloudflare-deployer.md +0 -102
|
@@ -19,6 +19,7 @@ When you assign a workspace with a sandbox to an agent, Mastra automatically inc
|
|
|
19
19
|
Available providers:
|
|
20
20
|
|
|
21
21
|
- [`LocalSandbox`](https://mastra.ai/reference/workspace/local-sandbox) - Executes commands on the local machine
|
|
22
|
+
- [`E2BSandbox`](https://mastra.ai/reference/workspace/e2b-sandbox) - Executes commands in isolated E2B cloud sandboxes
|
|
22
23
|
|
|
23
24
|
## Basic usage
|
|
24
25
|
|
|
@@ -57,5 +58,6 @@ When you configure a sandbox on a workspace, agents receive the `execute_command
|
|
|
57
58
|
## Related
|
|
58
59
|
|
|
59
60
|
- [`LocalSandbox` reference](https://mastra.ai/reference/workspace/local-sandbox)
|
|
61
|
+
- [`E2BSandbox` reference](https://mastra.ai/reference/workspace/e2b-sandbox)
|
|
60
62
|
- [Workspace overview](https://mastra.ai/docs/workspace/overview)
|
|
61
63
|
- [Filesystem](https://mastra.ai/docs/workspace/filesystem)
|
|
@@ -83,9 +83,11 @@ const storage = new LibSQLStore({
|
|
|
83
83
|
});
|
|
84
84
|
await storage.init();
|
|
85
85
|
|
|
86
|
+
const memoryStorage = await storage.getStore('memory');
|
|
87
|
+
|
|
86
88
|
const model = withMastra(openai('gpt-4o'), {
|
|
87
89
|
memory: {
|
|
88
|
-
storage
|
|
90
|
+
storage: memoryStorage!,
|
|
89
91
|
threadId: 'user-thread-123',
|
|
90
92
|
resourceId: 'user-123',
|
|
91
93
|
lastMessages: 10,
|
|
@@ -111,11 +113,13 @@ import { LibSQLStore } from '@mastra/libsql';
|
|
|
111
113
|
const storage = new LibSQLStore({ id: 'my-app', url: 'file:./data.db' });
|
|
112
114
|
await storage.init();
|
|
113
115
|
|
|
116
|
+
const memoryStorage = await storage.getStore('memory');
|
|
117
|
+
|
|
114
118
|
const model = withMastra(openai('gpt-4o'), {
|
|
115
119
|
inputProcessors: [myGuardProcessor],
|
|
116
120
|
outputProcessors: [myLoggingProcessor],
|
|
117
121
|
memory: {
|
|
118
|
-
storage
|
|
122
|
+
storage: memoryStorage!,
|
|
119
123
|
threadId: 'thread-123',
|
|
120
124
|
resourceId: 'user-123',
|
|
121
125
|
lastMessages: 10,
|
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
# Deploy Mastra to Cloudflare
|
|
2
|
+
|
|
3
|
+
Use `@mastra/deployer-cloudflare` to deploy your Mastra server to Cloudflare Workers. The deployer bundles your code and generates a `wrangler.jsonc` file conforming to Cloudflare's [wrangler configuration](https://developers.cloudflare.com/workers/wrangler/configuration/), ready to deploy with no additional configuration.
|
|
4
|
+
|
|
5
|
+
> **Info:** If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
|
|
6
|
+
|
|
7
|
+
## Before you begin
|
|
8
|
+
|
|
9
|
+
You'll need a [Mastra application](https://mastra.ai/guides/getting-started/quickstart) and a [Cloudflare](https://cloudflare.com/) account.
|
|
10
|
+
|
|
11
|
+
Cloudflare Workers use an ephemeral filesystem, so any storage you configure (including observability storage) must be hosted externally. If you're using [LibSQLStore](https://mastra.ai/reference/storage/libsql) with a file URL, switch to a remotely hosted database.
|
|
12
|
+
|
|
13
|
+
## Installation
|
|
14
|
+
|
|
15
|
+
Add the `@mastra/deployer-cloudflare` package to your project:
|
|
16
|
+
|
|
17
|
+
**npm**:
|
|
18
|
+
|
|
19
|
+
```bash
|
|
20
|
+
npm install @mastra/deployer-cloudflare@latest
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
**pnpm**:
|
|
24
|
+
|
|
25
|
+
```bash
|
|
26
|
+
pnpm add @mastra/deployer-cloudflare@latest
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
**Yarn**:
|
|
30
|
+
|
|
31
|
+
```bash
|
|
32
|
+
yarn add @mastra/deployer-cloudflare@latest
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
**Bun**:
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
bun add @mastra/deployer-cloudflare@latest
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
Import [`CloudflareDeployer`](https://mastra.ai/reference/deployer/cloudflare) and set it as the deployer in your Mastra configuration:
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
import { Mastra } from "@mastra/core";
|
|
45
|
+
import { CloudflareDeployer } from "@mastra/deployer-cloudflare";
|
|
46
|
+
|
|
47
|
+
export const mastra = new Mastra({
|
|
48
|
+
deployer: new CloudflareDeployer({
|
|
49
|
+
name: "your-project-name",
|
|
50
|
+
vars: {
|
|
51
|
+
NODE_ENV: "production",
|
|
52
|
+
},
|
|
53
|
+
}),
|
|
54
|
+
});
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
In order to test your Cloudflare Worker locally, also install the [`wrangler` CLI](https://developers.cloudflare.com/workers/wrangler/install-and-update/):
|
|
58
|
+
|
|
59
|
+
**npm**:
|
|
60
|
+
|
|
61
|
+
```bash
|
|
62
|
+
npm install -D wrangler
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
**pnpm**:
|
|
66
|
+
|
|
67
|
+
```bash
|
|
68
|
+
pnpm add -D wrangler
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
**Yarn**:
|
|
72
|
+
|
|
73
|
+
```bash
|
|
74
|
+
yarn add --dev wrangler
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
**Bun**:
|
|
78
|
+
|
|
79
|
+
```bash
|
|
80
|
+
bun add --dev wrangler
|
|
81
|
+
```
|
|
82
|
+
|
|
83
|
+
## Usage
|
|
84
|
+
|
|
85
|
+
After setting up your project, push it to your remote Git provider of choice (e.g. GitHub).
|
|
86
|
+
|
|
87
|
+
1. Connect your repository to Cloudflare. On the "Workers & Pages" dashboard, select **Create application** and choose your Git provider in the next step. Continue with the setup process and select the repository you want to deploy.
|
|
88
|
+
|
|
89
|
+
> **Note:** Remember to set your environment variables needed to run your application (e.g. your [model provider](https://mastra.ai/models/providers) API key).
|
|
90
|
+
|
|
91
|
+
2. Once you're ready, click the **Deploy** button and wait for the first deployment to complete.
|
|
92
|
+
|
|
93
|
+
3. Try out your newly deployed function by going to `https://<your-project-name>.<slug>.workers.dev/api/agents`. You should get a JSON response listing all available agents.
|
|
94
|
+
|
|
95
|
+
Since the [Mastra server](https://mastra.ai/docs/server/mastra-server) prefixes every API endpoint with `/api`, you have to add it to your URLs when making requests.
|
|
96
|
+
|
|
97
|
+
4. You can now call your Mastra endpoints over HTTP.
|
|
98
|
+
|
|
99
|
+
> **Note:** Set up [authentication](https://mastra.ai/docs/server/auth) before exposing your endpoints publicly.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OpenRouter
|
|
2
2
|
|
|
3
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
3
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 179 models through Mastra's model router.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
6
6
|
|
|
@@ -101,6 +101,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
101
101
|
| `minimax/minimax-m1` |
|
|
102
102
|
| `minimax/minimax-m2` |
|
|
103
103
|
| `minimax/minimax-m2.1` |
|
|
104
|
+
| `minimax/minimax-m2.5` |
|
|
104
105
|
| `mistralai/codestral-2508` |
|
|
105
106
|
| `mistralai/devstral-2512` |
|
|
106
107
|
| `mistralai/devstral-2512:free` |
|
|
@@ -156,7 +157,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
156
157
|
| `openai/gpt-oss-20b:free` |
|
|
157
158
|
| `openai/gpt-oss-safeguard-20b` |
|
|
158
159
|
| `openai/o4-mini` |
|
|
159
|
-
| `openrouter/pony-alpha` |
|
|
160
160
|
| `openrouter/sherlock-dash-alpha` |
|
|
161
161
|
| `openrouter/sherlock-think-alpha` |
|
|
162
162
|
| `qwen/qwen-2.5-coder-32b-instruct` |
|
|
@@ -190,6 +190,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
190
190
|
| `sourceful/riverflow-v2-fast-preview` |
|
|
191
191
|
| `sourceful/riverflow-v2-max-preview` |
|
|
192
192
|
| `sourceful/riverflow-v2-standard-preview` |
|
|
193
|
+
| `stepfun/step-3.5-flash` |
|
|
194
|
+
| `stepfun/step-3.5-flash:free` |
|
|
193
195
|
| `thudm/glm-z1-32b:free` |
|
|
194
196
|
| `tngtech/deepseek-r1t2-chimera:free` |
|
|
195
197
|
| `tngtech/tng-r1t-chimera:free` |
|
|
@@ -209,4 +211,5 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
209
211
|
| `z-ai/glm-4.6` |
|
|
210
212
|
| `z-ai/glm-4.6:exacto` |
|
|
211
213
|
| `z-ai/glm-4.7` |
|
|
212
|
-
| `z-ai/glm-4.7-flash` |
|
|
214
|
+
| `z-ai/glm-4.7-flash` |
|
|
215
|
+
| `z-ai/glm-5` |
|
package/.docs/models/index.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Model Providers
|
|
2
2
|
|
|
3
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
3
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 2211 models from 79 providers through a single API.
|
|
4
4
|
|
|
5
5
|
## Features
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Baseten
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 7 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Baseten documentation](https://docs.baseten.co/development/model-apis/overview).
|
|
6
6
|
|
|
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| `baseten/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.30 | $0.45 |
|
|
38
38
|
| `baseten/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $0.60 | $3 |
|
|
39
39
|
| `baseten/moonshotai/Kimi-K2-Thinking` | 262K | | | | | | $0.60 | $3 |
|
|
40
|
+
| `baseten/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
40
41
|
| `baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $0.38 | $2 |
|
|
41
42
|
| `baseten/zai-org/GLM-4.6` | 200K | | | | | | $0.60 | $2 |
|
|
42
43
|
| `baseten/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Cerebras
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 4 Cerebras models through Mastra's model router. Authentication is handled automatically using the `CEREBRAS_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Cerebras documentation](https://inference-docs.cerebras.ai/models/overview).
|
|
6
6
|
|
|
@@ -33,6 +33,7 @@ for await (const chunk of stream) {
|
|
|
33
33
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
34
34
|
| ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
35
35
|
| `cerebras/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
|
|
36
|
+
| `cerebras/llama3.1-8b` | 32K | | | | | | $0.10 | $0.10 |
|
|
36
37
|
| `cerebras/qwen-3-235b-a22b-instruct-2507` | 131K | | | | | | $0.60 | $1 |
|
|
37
38
|
| `cerebras/zai-glm-4.7` | 131K | | | | | | — | — |
|
|
38
39
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Fireworks AI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 18 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
|
|
6
6
|
|
|
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `fireworks-ai/accounts/fireworks/models/glm-4p5-air` | 131K | | | | | | $0.22 | $0.88 |
|
|
43
43
|
| `fireworks-ai/accounts/fireworks/models/glm-4p6` | 198K | | | | | | $0.55 | $2 |
|
|
44
44
|
| `fireworks-ai/accounts/fireworks/models/glm-4p7` | 198K | | | | | | $0.60 | $2 |
|
|
45
|
+
| `fireworks-ai/accounts/fireworks/models/glm-5` | 203K | | | | | | $1 | $3 |
|
|
45
46
|
| `fireworks-ai/accounts/fireworks/models/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
46
47
|
| `fireworks-ai/accounts/fireworks/models/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
|
|
47
48
|
| `fireworks-ai/accounts/fireworks/models/kimi-k2-instruct` | 128K | | | | | | $1 | $3 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Friendli
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 8 Friendli models through Mastra's model router. Authentication is handled automatically using the `FRIENDLI_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Friendli documentation](https://friendli.ai/docs/guides/serverless_endpoints/introduction).
|
|
6
6
|
|
|
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `friendli/MiniMaxAI/MiniMax-M2.1` | 197K | | | | | | $0.30 | $1 |
|
|
42
42
|
| `friendli/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.20 | $0.80 |
|
|
43
43
|
| `friendli/zai-org/GLM-4.7` | 203K | | | | | | — | — |
|
|
44
|
+
| `friendli/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
44
45
|
|
|
45
46
|
## Advanced Configuration
|
|
46
47
|
|
|
@@ -70,7 +71,7 @@ const agent = new Agent({
|
|
|
70
71
|
model: ({ requestContext }) => {
|
|
71
72
|
const useAdvanced = requestContext.task === "complex";
|
|
72
73
|
return useAdvanced
|
|
73
|
-
? "friendli/zai-org/GLM-
|
|
74
|
+
? "friendli/zai-org/GLM-5"
|
|
74
75
|
: "friendli/LGAI-EXAONE/EXAONE-4.0.1-32B";
|
|
75
76
|
}
|
|
76
77
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Hugging Face
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 17 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Hugging Face documentation](https://huggingface.co).
|
|
6
6
|
|
|
@@ -50,6 +50,7 @@ for await (const chunk of stream) {
|
|
|
50
50
|
| `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
51
51
|
| `huggingface/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
52
52
|
| `huggingface/zai-org/GLM-4.7-Flash` | 200K | | | | | | — | — |
|
|
53
|
+
| `huggingface/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
53
54
|
|
|
54
55
|
## Advanced Configuration
|
|
55
56
|
|
|
@@ -79,7 +80,7 @@ const agent = new Agent({
|
|
|
79
80
|
model: ({ requestContext }) => {
|
|
80
81
|
const useAdvanced = requestContext.task === "complex";
|
|
81
82
|
return useAdvanced
|
|
82
|
-
? "huggingface/zai-org/GLM-
|
|
83
|
+
? "huggingface/zai-org/GLM-5"
|
|
83
84
|
: "huggingface/MiniMaxAI/MiniMax-M2.1";
|
|
84
85
|
}
|
|
85
86
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Jiekou.AI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 61 Jiekou.AI models through Mastra's model router. Authentication is handled automatically using the `JIEKOU_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Jiekou.AI documentation](https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev).
|
|
6
6
|
|
|
@@ -40,6 +40,7 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| `jiekou/claude-opus-4-1-20250805` | 200K | | | | | | $14 | $68 |
|
|
41
41
|
| `jiekou/claude-opus-4-20250514` | 200K | | | | | | $14 | $68 |
|
|
42
42
|
| `jiekou/claude-opus-4-5-20251101` | 200K | | | | | | $5 | $23 |
|
|
43
|
+
| `jiekou/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
43
44
|
| `jiekou/claude-sonnet-4-20250514` | 200K | | | | | | $3 | $14 |
|
|
44
45
|
| `jiekou/claude-sonnet-4-5-20250929` | 200K | | | | | | $3 | $14 |
|
|
45
46
|
| `jiekou/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
|
|
@@ -59,6 +60,7 @@ for await (const chunk of stream) {
|
|
|
59
60
|
| `jiekou/gpt-5-mini` | 400K | | | | | | $0.23 | $2 |
|
|
60
61
|
| `jiekou/gpt-5-nano` | 400K | | | | | | $0.04 | $0.36 |
|
|
61
62
|
| `jiekou/gpt-5-pro` | 400K | | | | | | $14 | $108 |
|
|
63
|
+
| `jiekou/gpt-5.1` | 400K | | | | | | $1 | $9 |
|
|
62
64
|
| `jiekou/gpt-5.1-codex` | 400K | | | | | | $1 | $9 |
|
|
63
65
|
| `jiekou/gpt-5.1-codex-max` | 400K | | | | | | $1 | $9 |
|
|
64
66
|
| `jiekou/gpt-5.1-codex-mini` | 400K | | | | | | $0.23 | $2 |
|
|
@@ -79,13 +81,13 @@ for await (const chunk of stream) {
|
|
|
79
81
|
| `jiekou/o3` | 131K | | | | | | $10 | $40 |
|
|
80
82
|
| `jiekou/o3-mini` | 131K | | | | | | $1 | $4 |
|
|
81
83
|
| `jiekou/o4-mini` | 200K | | | | | | $1 | $4 |
|
|
82
|
-
| `jiekou/qwen/qwen2.5-vl-72b-instruct` | 33K | | | | | | $0.80 | $0.80 |
|
|
83
84
|
| `jiekou/qwen/qwen3-235b-a22b-fp8` | 41K | | | | | | $0.20 | $0.80 |
|
|
84
85
|
| `jiekou/qwen/qwen3-235b-a22b-instruct-2507` | 131K | | | | | | $0.15 | $0.80 |
|
|
85
86
|
| `jiekou/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.30 | $3 |
|
|
86
87
|
| `jiekou/qwen/qwen3-30b-a3b-fp8` | 41K | | | | | | $0.09 | $0.45 |
|
|
87
88
|
| `jiekou/qwen/qwen3-32b-fp8` | 41K | | | | | | $0.10 | $0.45 |
|
|
88
89
|
| `jiekou/qwen/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.29 | $1 |
|
|
90
|
+
| `jiekou/qwen/qwen3-coder-next` | 262K | | | | | | $0.20 | $2 |
|
|
89
91
|
| `jiekou/qwen/qwen3-next-80b-a3b-instruct` | 66K | | | | | | $0.15 | $2 |
|
|
90
92
|
| `jiekou/qwen/qwen3-next-80b-a3b-thinking` | 66K | | | | | | $0.15 | $2 |
|
|
91
93
|
| `jiekou/xiaomimimo/mimo-v2-flash` | 262K | | | | | | — | — |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# MiniMax Coding Plan (minimaxi.com)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 3 MiniMax Coding Plan (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [MiniMax Coding Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/coding-plan/intro).
|
|
6
6
|
|
|
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `minimax-cn-coding-plan/MiniMax-M2` | 197K | | | | | | — | — |
|
|
38
38
|
| `minimax-cn-coding-plan/MiniMax-M2.1` | 205K | | | | | | — | — |
|
|
39
|
+
| `minimax-cn-coding-plan/MiniMax-M2.5` | 205K | | | | | | — | — |
|
|
39
40
|
|
|
40
41
|
## Advanced Configuration
|
|
41
42
|
|
|
@@ -65,7 +66,7 @@ const agent = new Agent({
|
|
|
65
66
|
model: ({ requestContext }) => {
|
|
66
67
|
const useAdvanced = requestContext.task === "complex";
|
|
67
68
|
return useAdvanced
|
|
68
|
-
? "minimax-cn-coding-plan/MiniMax-M2.
|
|
69
|
+
? "minimax-cn-coding-plan/MiniMax-M2.5"
|
|
69
70
|
: "minimax-cn-coding-plan/MiniMax-M2";
|
|
70
71
|
}
|
|
71
72
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# MiniMax (minimaxi.com)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 3 MiniMax (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [MiniMax (minimaxi.com) documentation](https://platform.minimaxi.com/docs/guides/quickstart).
|
|
6
6
|
|
|
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| ------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `minimax-cn/MiniMax-M2` | 197K | | | | | | $0.30 | $1 |
|
|
38
38
|
| `minimax-cn/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
39
|
+
| `minimax-cn/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
39
40
|
|
|
40
41
|
## Advanced Configuration
|
|
41
42
|
|
|
@@ -65,7 +66,7 @@ const agent = new Agent({
|
|
|
65
66
|
model: ({ requestContext }) => {
|
|
66
67
|
const useAdvanced = requestContext.task === "complex";
|
|
67
68
|
return useAdvanced
|
|
68
|
-
? "minimax-cn/MiniMax-M2.
|
|
69
|
+
? "minimax-cn/MiniMax-M2.5"
|
|
69
70
|
: "minimax-cn/MiniMax-M2";
|
|
70
71
|
}
|
|
71
72
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# MiniMax Coding Plan (minimax.io)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 3 MiniMax Coding Plan (minimax.io) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [MiniMax Coding Plan (minimax.io) documentation](https://platform.minimax.io/docs/coding-plan/intro).
|
|
6
6
|
|
|
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `minimax-coding-plan/MiniMax-M2` | 197K | | | | | | — | — |
|
|
38
38
|
| `minimax-coding-plan/MiniMax-M2.1` | 205K | | | | | | — | — |
|
|
39
|
+
| `minimax-coding-plan/MiniMax-M2.5` | 205K | | | | | | — | — |
|
|
39
40
|
|
|
40
41
|
## Advanced Configuration
|
|
41
42
|
|
|
@@ -65,7 +66,7 @@ const agent = new Agent({
|
|
|
65
66
|
model: ({ requestContext }) => {
|
|
66
67
|
const useAdvanced = requestContext.task === "complex";
|
|
67
68
|
return useAdvanced
|
|
68
|
-
? "minimax-coding-plan/MiniMax-M2.
|
|
69
|
+
? "minimax-coding-plan/MiniMax-M2.5"
|
|
69
70
|
: "minimax-coding-plan/MiniMax-M2";
|
|
70
71
|
}
|
|
71
72
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# MiniMax (minimax.io)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 3 MiniMax (minimax.io) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [MiniMax (minimax.io) documentation](https://platform.minimax.io/docs/guides/quickstart).
|
|
6
6
|
|
|
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| ---------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `minimax/MiniMax-M2` | 197K | | | | | | $0.30 | $1 |
|
|
38
38
|
| `minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
39
|
+
| `minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
39
40
|
|
|
40
41
|
## Advanced Configuration
|
|
41
42
|
|
|
@@ -65,7 +66,7 @@ const agent = new Agent({
|
|
|
65
66
|
model: ({ requestContext }) => {
|
|
66
67
|
const useAdvanced = requestContext.task === "complex";
|
|
67
68
|
return useAdvanced
|
|
68
|
-
? "minimax/MiniMax-M2.
|
|
69
|
+
? "minimax/MiniMax-M2.5"
|
|
69
70
|
: "minimax/MiniMax-M2";
|
|
70
71
|
}
|
|
71
72
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# NanoGPT
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 29 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
|
|
6
6
|
|
|
@@ -39,22 +39,30 @@ for await (const chunk of stream) {
|
|
|
39
39
|
| `nano-gpt/meta-llama/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $2 |
|
|
40
40
|
| `nano-gpt/meta-llama/llama-4-maverick` | 128K | | | | | | $1 | $2 |
|
|
41
41
|
| `nano-gpt/minimax/minimax-m2.1` | 128K | | | | | | $1 | $2 |
|
|
42
|
+
| `nano-gpt/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
43
|
+
| `nano-gpt/minimax/minimax-m2.5-official` | 205K | | | | | | $0.30 | $1 |
|
|
42
44
|
| `nano-gpt/mistralai/devstral-2-123b-instruct-2512` | 131K | | | | | | $1 | $2 |
|
|
43
45
|
| `nano-gpt/mistralai/ministral-14b-instruct-2512` | 131K | | | | | | $1 | $2 |
|
|
44
46
|
| `nano-gpt/mistralai/mistral-large-3-675b-instruct-2512` | 131K | | | | | | $1 | $2 |
|
|
45
47
|
| `nano-gpt/moonshotai/kimi-k2-instruct` | 131K | | | | | | $1 | $2 |
|
|
46
48
|
| `nano-gpt/moonshotai/kimi-k2-thinking` | 33K | | | | | | $1 | $2 |
|
|
49
|
+
| `nano-gpt/moonshotai/kimi-k2.5` | 256K | | | | | | $0.30 | $2 |
|
|
50
|
+
| `nano-gpt/moonshotai/kimi-k2.5-thinking` | 256K | | | | | | $0.30 | $2 |
|
|
47
51
|
| `nano-gpt/nousresearch/hermes-4-405b:thinking` | 128K | | | | | | $1 | $2 |
|
|
48
52
|
| `nano-gpt/nvidia/llama-3_3-nemotron-super-49b-v1_5` | 128K | | | | | | $1 | $2 |
|
|
49
53
|
| `nano-gpt/openai/gpt-oss-120b` | 128K | | | | | | $1 | $2 |
|
|
50
54
|
| `nano-gpt/qwen/qwen3-235b-a22b-thinking-2507` | 262K | | | | | | $1 | $2 |
|
|
51
55
|
| `nano-gpt/qwen/qwen3-coder` | 106K | | | | | | $1 | $2 |
|
|
52
|
-
| `nano-gpt/z-ai/glm-4.6` | 200K | | | | | | $1 | $2 |
|
|
53
|
-
| `nano-gpt/z-ai/glm-4.6:thinking` | 128K | | | | | | $1 | $2 |
|
|
54
56
|
| `nano-gpt/zai-org/glm-4.5-air` | 128K | | | | | | $1 | $2 |
|
|
55
57
|
| `nano-gpt/zai-org/glm-4.5-air:thinking` | 128K | | | | | | $1 | $2 |
|
|
58
|
+
| `nano-gpt/zai-org/glm-4.6` | 200K | | | | | | $1 | $2 |
|
|
59
|
+
| `nano-gpt/zai-org/glm-4.6:thinking` | 128K | | | | | | $1 | $2 |
|
|
56
60
|
| `nano-gpt/zai-org/glm-4.7` | 205K | | | | | | $1 | $2 |
|
|
57
61
|
| `nano-gpt/zai-org/glm-4.7:thinking` | 128K | | | | | | $1 | $2 |
|
|
62
|
+
| `nano-gpt/zai-org/glm-5` | 200K | | | | | | $0.80 | $3 |
|
|
63
|
+
| `nano-gpt/zai-org/glm-5-original` | 200K | | | | | | $0.80 | $3 |
|
|
64
|
+
| `nano-gpt/zai-org/glm-5-original:thinking` | 200K | | | | | | $0.80 | $3 |
|
|
65
|
+
| `nano-gpt/zai-org/glm-5:thinking` | 200K | | | | | | $0.80 | $3 |
|
|
58
66
|
|
|
59
67
|
## Advanced Configuration
|
|
60
68
|
|
|
@@ -84,7 +92,7 @@ const agent = new Agent({
|
|
|
84
92
|
model: ({ requestContext }) => {
|
|
85
93
|
const useAdvanced = requestContext.task === "complex";
|
|
86
94
|
return useAdvanced
|
|
87
|
-
? "nano-gpt/zai-org/glm-
|
|
95
|
+
? "nano-gpt/zai-org/glm-5:thinking"
|
|
88
96
|
: "nano-gpt/deepseek/deepseek-r1";
|
|
89
97
|
}
|
|
90
98
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# NovitaAI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 83 NovitaAI models through Mastra's model router. Authentication is handled automatically using the `NOVITA_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [NovitaAI documentation](https://novita.ai/docs/guides/introduction).
|
|
6
6
|
|
|
@@ -67,6 +67,7 @@ for await (const chunk of stream) {
|
|
|
67
67
|
| `novita-ai/microsoft/wizardlm-2-8x22b` | 66K | | | | | | $0.62 | $0.62 |
|
|
68
68
|
| `novita-ai/minimax/minimax-m2` | 205K | | | | | | $0.30 | $1 |
|
|
69
69
|
| `novita-ai/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
|
|
70
|
+
| `novita-ai/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
70
71
|
| `novita-ai/minimaxai/minimax-m1-80k` | 1.0M | | | | | | $0.55 | $2 |
|
|
71
72
|
| `novita-ai/mistralai/mistral-nemo` | 60K | | | | | | $0.04 | $0.17 |
|
|
72
73
|
| `novita-ai/moonshotai/kimi-k2-0905` | 262K | | | | | | $0.60 | $3 |
|
|
@@ -115,6 +116,7 @@ for await (const chunk of stream) {
|
|
|
115
116
|
| `novita-ai/zai-org/glm-4.6v` | 131K | | | | | | $0.30 | $0.90 |
|
|
116
117
|
| `novita-ai/zai-org/glm-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
117
118
|
| `novita-ai/zai-org/glm-4.7-flash` | 200K | | | | | | $0.07 | $0.40 |
|
|
119
|
+
| `novita-ai/zai-org/glm-5` | 203K | | | | | | $1 | $3 |
|
|
118
120
|
|
|
119
121
|
## Advanced Configuration
|
|
120
122
|
|
|
@@ -144,7 +146,7 @@ const agent = new Agent({
|
|
|
144
146
|
model: ({ requestContext }) => {
|
|
145
147
|
const useAdvanced = requestContext.task === "complex";
|
|
146
148
|
return useAdvanced
|
|
147
|
-
? "novita-ai/zai-org/glm-
|
|
149
|
+
? "novita-ai/zai-org/glm-5"
|
|
148
150
|
: "novita-ai/baichuan/baichuan-m2-32b";
|
|
149
151
|
}
|
|
150
152
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Ollama Cloud
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 32 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
|
|
6
6
|
|
|
@@ -46,6 +46,7 @@ for await (const chunk of stream) {
|
|
|
46
46
|
| `ollama-cloud/gemma3:4b` | 131K | | | | | | — | — |
|
|
47
47
|
| `ollama-cloud/glm-4.6` | 203K | | | | | | — | — |
|
|
48
48
|
| `ollama-cloud/glm-4.7` | 203K | | | | | | — | — |
|
|
49
|
+
| `ollama-cloud/glm-5` | 203K | | | | | | — | — |
|
|
49
50
|
| `ollama-cloud/gpt-oss:120b` | 131K | | | | | | — | — |
|
|
50
51
|
| `ollama-cloud/gpt-oss:20b` | 131K | | | | | | — | — |
|
|
51
52
|
| `ollama-cloud/kimi-k2-thinking` | 262K | | | | | | — | — |
|
|
@@ -53,6 +54,7 @@ for await (const chunk of stream) {
|
|
|
53
54
|
| `ollama-cloud/kimi-k2.5` | 262K | | | | | | — | — |
|
|
54
55
|
| `ollama-cloud/minimax-m2` | 205K | | | | | | — | — |
|
|
55
56
|
| `ollama-cloud/minimax-m2.1` | 205K | | | | | | — | — |
|
|
57
|
+
| `ollama-cloud/minimax-m2.5` | 205K | | | | | | — | — |
|
|
56
58
|
| `ollama-cloud/ministral-3:14b` | 262K | | | | | | — | — |
|
|
57
59
|
| `ollama-cloud/ministral-3:3b` | 262K | | | | | | — | — |
|
|
58
60
|
| `ollama-cloud/ministral-3:8b` | 262K | | | | | | — | — |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OpenAI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 42 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OpenAI documentation](https://platform.openai.com/docs/models).
|
|
6
6
|
|
|
@@ -44,22 +44,23 @@ for await (const chunk of stream) {
|
|
|
44
44
|
| `openai/gpt-4o-2024-08-06` | 128K | | | | | | $3 | $10 |
|
|
45
45
|
| `openai/gpt-4o-2024-11-20` | 128K | | | | | | $3 | $10 |
|
|
46
46
|
| `openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
47
|
-
| `openai/gpt-5` |
|
|
48
|
-
| `openai/gpt-5-chat-latest` |
|
|
49
|
-
| `openai/gpt-5-codex` |
|
|
50
|
-
| `openai/gpt-5-mini` |
|
|
51
|
-
| `openai/gpt-5-nano` |
|
|
47
|
+
| `openai/gpt-5` | 400K | | | | | | $1 | $10 |
|
|
48
|
+
| `openai/gpt-5-chat-latest` | 400K | | | | | | $1 | $10 |
|
|
49
|
+
| `openai/gpt-5-codex` | 400K | | | | | | $1 | $10 |
|
|
50
|
+
| `openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
51
|
+
| `openai/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
|
|
52
52
|
| `openai/gpt-5-pro` | 400K | | | | | | $15 | $120 |
|
|
53
|
-
| `openai/gpt-5.1` |
|
|
53
|
+
| `openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
|
|
54
54
|
| `openai/gpt-5.1-chat-latest` | 128K | | | | | | $1 | $10 |
|
|
55
|
-
| `openai/gpt-5.1-codex` |
|
|
56
|
-
| `openai/gpt-5.1-codex-max` |
|
|
57
|
-
| `openai/gpt-5.1-codex-mini` |
|
|
58
|
-
| `openai/gpt-5.2` |
|
|
55
|
+
| `openai/gpt-5.1-codex` | 400K | | | | | | $1 | $10 |
|
|
56
|
+
| `openai/gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
|
|
57
|
+
| `openai/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
|
|
58
|
+
| `openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
|
|
59
59
|
| `openai/gpt-5.2-chat-latest` | 128K | | | | | | $2 | $14 |
|
|
60
|
-
| `openai/gpt-5.2-codex` |
|
|
61
|
-
| `openai/gpt-5.2-pro` |
|
|
62
|
-
| `openai/gpt-5.3-codex` |
|
|
60
|
+
| `openai/gpt-5.2-codex` | 400K | | | | | | $2 | $14 |
|
|
61
|
+
| `openai/gpt-5.2-pro` | 400K | | | | | | $21 | $168 |
|
|
62
|
+
| `openai/gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
|
|
63
|
+
| `openai/gpt-5.3-codex-spark` | 128K | | | | | | $2 | $14 |
|
|
63
64
|
| `openai/o1` | 200K | | | | | | $15 | $60 |
|
|
64
65
|
| `openai/o1-mini` | 128K | | | | | | $1 | $4 |
|
|
65
66
|
| `openai/o1-preview` | 128K | | | | | | $15 | $60 |
|