@mastra/mcp-docs-server 1.2.10-alpha.3 → 1.2.10-alpha.6
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/models/environment-variables.md +2 -0
- package/.docs/models/gateways/netlify.md +2 -1
- package/.docs/models/gateways/openrouter.md +3 -1
- package/.docs/models/gateways/vercel.md +3 -6
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/aiand.md +81 -0
- package/.docs/models/providers/alibaba-token-plan-cn.md +4 -1
- package/.docs/models/providers/alibaba-token-plan.md +4 -1
- package/.docs/models/providers/ambient.md +2 -2
- package/.docs/models/providers/anthropic.md +2 -1
- package/.docs/models/providers/baseten.md +3 -2
- package/.docs/models/providers/dinference.md +2 -1
- package/.docs/models/providers/empiriolabs.md +1 -2
- package/.docs/models/providers/google.md +11 -11
- package/.docs/models/providers/hetzner.md +73 -0
- package/.docs/models/providers/kimi-for-coding.md +2 -1
- package/.docs/models/providers/llmgateway.md +2 -1
- package/.docs/models/providers/openai.md +1 -20
- package/.docs/models/providers/opencode.md +3 -1
- package/.docs/models/providers/xai.md +3 -2
- package/.docs/models/providers.md +2 -0
- package/.docs/reference/agents/channels.md +1 -1
- package/.docs/reference/channels/slack-provider.md +1 -1
- package/CHANGELOG.md +7 -0
- package/dist/{chunk-HGADBLKG.js → chunk-GLPCVXXO.js} +2 -2
- package/dist/{chunk-HGADBLKG.js.map → chunk-GLPCVXXO.js.map} +1 -1
- package/dist/index.js +1 -1
- package/dist/stdio.js +1 -1
- package/dist/tools/docs.d.ts.map +1 -1
- package/package.json +6 -5
|
@@ -10,6 +10,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
10
10
|
| [Abacus](https://mastra.ai/models/providers/abacus) | `abacus/*` | `ABACUS_API_KEY` |
|
|
11
11
|
| [abliteration.ai](https://mastra.ai/models/providers/abliteration-ai) | `abliteration-ai/*` | `ABLIT_KEY` |
|
|
12
12
|
| [AI-ROUTER](https://mastra.ai/models/providers/ai-router) | `ai-router/*` | `AI_ROUTER_API_KEY` |
|
|
13
|
+
| [ai&](https://mastra.ai/models/providers/aiand) | `aiand/*` | `AIAND_API_KEY` |
|
|
13
14
|
| [AKI.IO](https://mastra.ai/models/providers/aki-io) | `aki-io/*` | `AKI_IO_API_KEY` |
|
|
14
15
|
| [Alibaba](https://mastra.ai/models/providers/alibaba) | `alibaba/*` | `DASHSCOPE_API_KEY` |
|
|
15
16
|
| [Alibaba (China)](https://mastra.ai/models/providers/alibaba-cn) | `alibaba-cn/*` | `DASHSCOPE_API_KEY` |
|
|
@@ -56,6 +57,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
56
57
|
| [Google](https://mastra.ai/models/providers/google) | `google/*` | `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY` |
|
|
57
58
|
| [Groq](https://mastra.ai/models/providers/groq) | `groq/*` | `GROQ_API_KEY` |
|
|
58
59
|
| [Helicone](https://mastra.ai/models/providers/helicone) | `helicone/*` | `HELICONE_API_KEY` |
|
|
60
|
+
| [Hetzner](https://mastra.ai/models/providers/hetzner) | `hetzner/*` | `HETZNER_API_KEY` |
|
|
59
61
|
| [HPC-AI](https://mastra.ai/models/providers/hpc-ai) | `hpc-ai/*` | `HPC_AI_API_KEY` |
|
|
60
62
|
| [Hugging Face](https://mastra.ai/models/providers/huggingface) | `huggingface/*` | `HF_TOKEN` |
|
|
61
63
|
| [iFlow](https://mastra.ai/models/providers/iflowcn) | `iflowcn/*` | `IFLOW_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 68 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
|
|
|
@@ -46,6 +46,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
46
46
|
| `anthropic/claude-opus-4-6` |
|
|
47
47
|
| `anthropic/claude-opus-4-7` |
|
|
48
48
|
| `anthropic/claude-opus-4-8` |
|
|
49
|
+
| `anthropic/claude-opus-5` |
|
|
49
50
|
| `anthropic/claude-sonnet-4-5` |
|
|
50
51
|
| `anthropic/claude-sonnet-4-5-20250929` |
|
|
51
52
|
| `anthropic/claude-sonnet-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 343 models through Mastra's model router.
|
|
6
6
|
|
|
7
7
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
8
8
|
|
|
@@ -69,6 +69,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
69
69
|
| `anthropic/claude-opus-4.7-fast` |
|
|
70
70
|
| `anthropic/claude-opus-4.8` |
|
|
71
71
|
| `anthropic/claude-opus-4.8-fast` |
|
|
72
|
+
| `anthropic/claude-opus-5` |
|
|
73
|
+
| `anthropic/claude-opus-5-fast` |
|
|
72
74
|
| `anthropic/claude-sonnet-4` |
|
|
73
75
|
| `anthropic/claude-sonnet-4.5` |
|
|
74
76
|
| `anthropic/claude-sonnet-4.6` |
|
|
@@ -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 304 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
|
|
|
@@ -86,6 +86,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
86
86
|
| `anthropic/claude-opus-4.7-fast` |
|
|
87
87
|
| `anthropic/claude-opus-4.8` |
|
|
88
88
|
| `anthropic/claude-opus-4.8-fast` |
|
|
89
|
+
| `anthropic/claude-opus-5` |
|
|
90
|
+
| `anthropic/claude-opus-5-fast` |
|
|
89
91
|
| `anthropic/claude-sonnet-4` |
|
|
90
92
|
| `anthropic/claude-sonnet-4.5` |
|
|
91
93
|
| `anthropic/claude-sonnet-4.6` |
|
|
@@ -217,10 +219,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
217
219
|
| `nvidia/nemotron-nano-12b-v2-vl` |
|
|
218
220
|
| `nvidia/nemotron-nano-9b-v2` |
|
|
219
221
|
| `openai/gpt-3.5-turbo` |
|
|
220
|
-
| `openai/gpt-4-turbo` |
|
|
221
222
|
| `openai/gpt-4.1` |
|
|
222
223
|
| `openai/gpt-4.1-mini` |
|
|
223
|
-
| `openai/gpt-4.1-nano` |
|
|
224
224
|
| `openai/gpt-4o` |
|
|
225
225
|
| `openai/gpt-4o-mini` |
|
|
226
226
|
| `openai/gpt-4o-mini-search-preview` |
|
|
@@ -264,12 +264,9 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
264
264
|
| `openai/gpt-realtime-2.1` |
|
|
265
265
|
| `openai/gpt-realtime-mini` |
|
|
266
266
|
| `openai/gpt-realtime-whisper` |
|
|
267
|
-
| `openai/o1` |
|
|
268
267
|
| `openai/o3` |
|
|
269
268
|
| `openai/o3-deep-research` |
|
|
270
|
-
| `openai/o3-mini` |
|
|
271
269
|
| `openai/o3-pro` |
|
|
272
|
-
| `openai/o4-mini` |
|
|
273
270
|
| `openai/text-embedding-3-large` |
|
|
274
271
|
| `openai/text-embedding-3-small` |
|
|
275
272
|
| `openai/text-embedding-ada-002` |
|
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 4945 models from 161 providers through a single API.
|
|
6
6
|
|
|
7
7
|
## Features
|
|
8
8
|
|
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# ai&
|
|
4
|
+
|
|
5
|
+
Access 9 ai& models through Mastra's model router. Authentication is handled automatically using the `AIAND_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [ai& documentation](https://docs.aiand.com/).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
AIAND_API_KEY=your-api-key
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
```typescript
|
|
14
|
+
import { Agent } from "@mastra/core/agent";
|
|
15
|
+
|
|
16
|
+
const agent = new Agent({
|
|
17
|
+
id: "my-agent",
|
|
18
|
+
name: "My Agent",
|
|
19
|
+
instructions: "You are a helpful assistant",
|
|
20
|
+
model: "aiand/deepseek-ai/deepseek-v4-flash"
|
|
21
|
+
});
|
|
22
|
+
|
|
23
|
+
// Generate a response
|
|
24
|
+
const response = await agent.generate("Hello!");
|
|
25
|
+
|
|
26
|
+
// Stream a response
|
|
27
|
+
const stream = await agent.stream("Tell me a story");
|
|
28
|
+
for await (const chunk of stream) {
|
|
29
|
+
console.log(chunk);
|
|
30
|
+
}
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [ai& documentation](https://docs.aiand.com/) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `aiand/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.25 |
|
|
40
|
+
| `aiand/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
|
|
41
|
+
| `aiand/google/gemma-4-31b-it` | 262K | | | | | | $0.20 | $0.50 |
|
|
42
|
+
| `aiand/moonshotai/kimi-k2.6` | 262K | | | | | | $0.85 | $4 |
|
|
43
|
+
| `aiand/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.75 | $4 |
|
|
44
|
+
| `aiand/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
45
|
+
| `aiand/qwen/qwen3.6-27b` | 262K | | | | | | — | — |
|
|
46
|
+
| `aiand/zai-org/glm-5.1` | 200K | | | | | | $1 | $4 |
|
|
47
|
+
| `aiand/zai-org/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
48
|
+
|
|
49
|
+
## Advanced configuration
|
|
50
|
+
|
|
51
|
+
### Custom headers
|
|
52
|
+
|
|
53
|
+
```typescript
|
|
54
|
+
const agent = new Agent({
|
|
55
|
+
id: "custom-agent",
|
|
56
|
+
name: "custom-agent",
|
|
57
|
+
model: {
|
|
58
|
+
url: "https://api.aiand.com/v1",
|
|
59
|
+
id: "aiand/deepseek-ai/deepseek-v4-flash",
|
|
60
|
+
apiKey: process.env.AIAND_API_KEY,
|
|
61
|
+
headers: {
|
|
62
|
+
"X-Custom-Header": "value"
|
|
63
|
+
}
|
|
64
|
+
}
|
|
65
|
+
});
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
### Dynamic model selection
|
|
69
|
+
|
|
70
|
+
```typescript
|
|
71
|
+
const agent = new Agent({
|
|
72
|
+
id: "dynamic-agent",
|
|
73
|
+
name: "Dynamic Agent",
|
|
74
|
+
model: ({ requestContext }) => {
|
|
75
|
+
const useAdvanced = requestContext.task === "complex";
|
|
76
|
+
return useAdvanced
|
|
77
|
+
? "aiand/zai-org/glm-5.2"
|
|
78
|
+
: "aiand/deepseek-ai/deepseek-v4-flash";
|
|
79
|
+
}
|
|
80
|
+
});
|
|
81
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan (China)
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 22 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
|
|
|
@@ -42,6 +42,9 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `alibaba-token-plan-cn/glm-5` | 203K | | | | | | — | — |
|
|
43
43
|
| `alibaba-token-plan-cn/glm-5.1` | 203K | | | | | | — | — |
|
|
44
44
|
| `alibaba-token-plan-cn/glm-5.2` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-i2v` | — | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-r2v` | — | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan-cn/happyhorse-1.1-t2v` | — | | | | | | — | — |
|
|
45
48
|
| `alibaba-token-plan-cn/kimi-k2.5` | 262K | | | | | | — | — |
|
|
46
49
|
| `alibaba-token-plan-cn/kimi-k2.6` | 262K | | | | | | — | — |
|
|
47
50
|
| `alibaba-token-plan-cn/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 22 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
|
|
|
@@ -42,6 +42,9 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `alibaba-token-plan/glm-5` | 203K | | | | | | — | — |
|
|
43
43
|
| `alibaba-token-plan/glm-5.1` | 203K | | | | | | — | — |
|
|
44
44
|
| `alibaba-token-plan/glm-5.2` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan/happyhorse-1.1-i2v` | — | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan/happyhorse-1.1-r2v` | — | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan/happyhorse-1.1-t2v` | — | | | | | | — | — |
|
|
45
48
|
| `alibaba-token-plan/kimi-k2.5` | 262K | | | | | | — | — |
|
|
46
49
|
| `alibaba-token-plan/kimi-k2.6` | 262K | | | | | | — | — |
|
|
47
50
|
| `alibaba-token-plan/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
@@ -37,9 +37,9 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
38
|
| ------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
39
|
| `ambient/ambient/large` | 101K | | | | | | $1 | $4 |
|
|
40
|
-
| `ambient/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.
|
|
40
|
+
| `ambient/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
41
41
|
| `ambient/moonshotai/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
42
|
-
| `ambient/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.
|
|
42
|
+
| `ambient/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.82 | $4 |
|
|
43
43
|
| `ambient/stepfun/step-3.7-flash` | 262K | | | | | | $0.19 | $1 |
|
|
44
44
|
| `ambient/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
|
|
45
45
|
| `ambient/z-ai/glm-5.2` | 101K | | | | | | $1 | $4 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Anthropic
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 13 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
|
|
8
8
|
|
|
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `anthropic/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
43
43
|
| `anthropic/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
|
|
44
44
|
| `anthropic/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
|
|
45
|
+
| `anthropic/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
|
|
45
46
|
| `anthropic/claude-sonnet-4-5` | 1.0M | | | | | | $3 | $15 |
|
|
46
47
|
| `anthropic/claude-sonnet-4-5-20250929` | 1.0M | | | | | | $3 | $15 |
|
|
47
48
|
| `anthropic/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Baseten
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 13 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Baseten documentation](https://docs.baseten.co).
|
|
8
8
|
|
|
@@ -48,6 +48,7 @@ for await (const chunk of stream) {
|
|
|
48
48
|
| `baseten/zai-org/GLM-5` | 203K | | | | | | $0.95 | $3 |
|
|
49
49
|
| `baseten/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
50
50
|
| `baseten/zai-org/GLM-5.2` | 524K | | | | | | $1 | $4 |
|
|
51
|
+
| `baseten/zai-org/GLM-5.2-Fast` | 524K | | | | | | $2 | $7 |
|
|
51
52
|
|
|
52
53
|
## Advanced configuration
|
|
53
54
|
|
|
@@ -77,7 +78,7 @@ const agent = new Agent({
|
|
|
77
78
|
model: ({ requestContext }) => {
|
|
78
79
|
const useAdvanced = requestContext.task === "complex";
|
|
79
80
|
return useAdvanced
|
|
80
|
-
? "baseten/zai-org/GLM-5.2"
|
|
81
|
+
? "baseten/zai-org/GLM-5.2-Fast"
|
|
81
82
|
: "baseten/deepseek-ai/DeepSeek-V4-Pro";
|
|
82
83
|
}
|
|
83
84
|
});
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# DInference
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 6 DInference models through Mastra's model router. Authentication is handled automatically using the `DINFERENCE_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [DInference documentation](https://dinference.com).
|
|
8
8
|
|
|
@@ -39,6 +39,7 @@ for await (const chunk of stream) {
|
|
|
39
39
|
| `dinference/glm-4.7` | 200K | | | | | | $0.45 | $2 |
|
|
40
40
|
| `dinference/glm-5` | 200K | | | | | | $0.75 | $2 |
|
|
41
41
|
| `dinference/glm-5.1` | 200K | | | | | | $1 | $4 |
|
|
42
|
+
| `dinference/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
42
43
|
| `dinference/gpt-oss-120b` | 131K | | | | | | $0.07 | $0.27 |
|
|
43
44
|
| `dinference/minimax-m2.5` | 200K | | | | | | $0.22 | $0.88 |
|
|
44
45
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# EmpirioLabs AI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 36 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
|
|
8
8
|
|
|
@@ -38,7 +38,6 @@ for await (const chunk of stream) {
|
|
|
38
38
|
| -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
39
|
| `empiriolabs/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
40
40
|
| `empiriolabs/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
41
|
-
| `empiriolabs/fugu-ultra` | 1.0M | | | | | | $8 | $45 |
|
|
42
41
|
| `empiriolabs/gemma-4-26b-a4b` | 262K | | | | | | $0.05 | $0.29 |
|
|
43
42
|
| `empiriolabs/glm-4-5-flash` | 200K | | | | | | — | — |
|
|
44
43
|
| `empiriolabs/glm-4-7-flash` | 200K | | | | | | — | — |
|
|
@@ -35,9 +35,9 @@ for await (const chunk of stream) {
|
|
|
35
35
|
|
|
36
36
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
37
37
|
| ------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
38
|
-
| `google/deep-research-max-preview-04-2026` |
|
|
39
|
-
| `google/deep-research-preview-04-2026` |
|
|
40
|
-
| `google/gemini-2.5-computer-use-preview-10-2025` |
|
|
38
|
+
| `google/deep-research-max-preview-04-2026` | 131K | | | | | | $2 | $12 |
|
|
39
|
+
| `google/deep-research-preview-04-2026` | 131K | | | | | | $2 | $12 |
|
|
40
|
+
| `google/gemini-2.5-computer-use-preview-10-2025` | 131K | | | | | | $1 | $10 |
|
|
41
41
|
| `google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
42
42
|
| `google/gemini-2.5-flash-image` | 33K | | | | | | $0.30 | $30 |
|
|
43
43
|
| `google/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
@@ -45,9 +45,9 @@ for await (const chunk of stream) {
|
|
|
45
45
|
| `google/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
|
|
46
46
|
| `google/gemini-2.5-pro-preview-tts` | 8K | | | | | | $1 | $20 |
|
|
47
47
|
| `google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
|
|
48
|
-
| `google/gemini-3-pro-image` |
|
|
48
|
+
| `google/gemini-3-pro-image` | 131K | | | | | | $2 | $120 |
|
|
49
49
|
| `google/gemini-3-pro-image-preview` | 131K | | | | | | $2 | $120 |
|
|
50
|
-
| `google/gemini-3.1-flash-image` |
|
|
50
|
+
| `google/gemini-3.1-flash-image` | 66K | | | | | | $0.50 | $60 |
|
|
51
51
|
| `google/gemini-3.1-flash-image-preview` | 66K | | | | | | $0.50 | $60 |
|
|
52
52
|
| `google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
|
|
53
53
|
| `google/gemini-3.1-flash-lite-image` | 66K | | | | | | $0.25 | $30 |
|
|
@@ -57,7 +57,7 @@ for await (const chunk of stream) {
|
|
|
57
57
|
| `google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
|
|
58
58
|
| `google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
|
|
59
59
|
| `google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
60
|
-
| `google/gemini-3.5-live-translate-preview` |
|
|
60
|
+
| `google/gemini-3.5-live-translate-preview` | 16K | | | | | | $4 | $21 |
|
|
61
61
|
| `google/gemini-3.6-flash` | 1.0M | | | | | | $2 | $8 |
|
|
62
62
|
| `google/gemini-embedding-001` | 2K | | | | | | $0.15 | — |
|
|
63
63
|
| `google/gemini-embedding-2` | 8K | | | | | | $0.20 | — |
|
|
@@ -67,11 +67,11 @@ for await (const chunk of stream) {
|
|
|
67
67
|
| `google/gemini-robotics-er-1.6-preview` | 131K | | | | | | $1 | $5 |
|
|
68
68
|
| `google/gemma-4-26b-a4b-it` | 262K | | | | | | — | — |
|
|
69
69
|
| `google/gemma-4-31b-it` | 262K | | | | | | — | — |
|
|
70
|
-
| `google/lyria-3-clip-preview` |
|
|
71
|
-
| `google/lyria-3-pro-preview` |
|
|
72
|
-
| `google/veo-3.1-fast-generate-preview` |
|
|
73
|
-
| `google/veo-3.1-generate-preview` |
|
|
74
|
-
| `google/veo-3.1-lite-generate-preview` |
|
|
70
|
+
| `google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
|
|
71
|
+
| `google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
72
|
+
| `google/veo-3.1-fast-generate-preview` | 480 | | | | | | — | — |
|
|
73
|
+
| `google/veo-3.1-generate-preview` | 480 | | | | | | — | — |
|
|
74
|
+
| `google/veo-3.1-lite-generate-preview` | 480 | | | | | | — | — |
|
|
75
75
|
|
|
76
76
|
## Advanced configuration
|
|
77
77
|
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# Hetzner
|
|
4
|
+
|
|
5
|
+
Access 1 Hetzner model through Mastra's model router. Authentication is handled automatically using the `HETZNER_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [Hetzner documentation](https://experiments.hetzner.com).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
HETZNER_API_KEY=your-api-key
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
```typescript
|
|
14
|
+
import { Agent } from "@mastra/core/agent";
|
|
15
|
+
|
|
16
|
+
const agent = new Agent({
|
|
17
|
+
id: "my-agent",
|
|
18
|
+
name: "My Agent",
|
|
19
|
+
instructions: "You are a helpful assistant",
|
|
20
|
+
model: "hetzner/Qwen/Qwen3.6-35B-A3B-FP8"
|
|
21
|
+
});
|
|
22
|
+
|
|
23
|
+
// Generate a response
|
|
24
|
+
const response = await agent.generate("Hello!");
|
|
25
|
+
|
|
26
|
+
// Stream a response
|
|
27
|
+
const stream = await agent.stream("Tell me a story");
|
|
28
|
+
for await (const chunk of stream) {
|
|
29
|
+
console.log(chunk);
|
|
30
|
+
}
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Hetzner documentation](https://experiments.hetzner.com) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `hetzner/Qwen/Qwen3.6-35B-A3B-FP8` | 262K | | | | | | — | — |
|
|
40
|
+
|
|
41
|
+
## Advanced configuration
|
|
42
|
+
|
|
43
|
+
### Custom headers
|
|
44
|
+
|
|
45
|
+
```typescript
|
|
46
|
+
const agent = new Agent({
|
|
47
|
+
id: "custom-agent",
|
|
48
|
+
name: "custom-agent",
|
|
49
|
+
model: {
|
|
50
|
+
url: "https://inference.hetzner.com/api/v1",
|
|
51
|
+
id: "hetzner/Qwen/Qwen3.6-35B-A3B-FP8",
|
|
52
|
+
apiKey: process.env.HETZNER_API_KEY,
|
|
53
|
+
headers: {
|
|
54
|
+
"X-Custom-Header": "value"
|
|
55
|
+
}
|
|
56
|
+
}
|
|
57
|
+
});
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
### Dynamic model selection
|
|
61
|
+
|
|
62
|
+
```typescript
|
|
63
|
+
const agent = new Agent({
|
|
64
|
+
id: "dynamic-agent",
|
|
65
|
+
name: "Dynamic Agent",
|
|
66
|
+
model: ({ requestContext }) => {
|
|
67
|
+
const useAdvanced = requestContext.task === "complex";
|
|
68
|
+
return useAdvanced
|
|
69
|
+
? "hetzner/Qwen/Qwen3.6-35B-A3B-FP8"
|
|
70
|
+
: "hetzner/Qwen/Qwen3.6-35B-A3B-FP8";
|
|
71
|
+
}
|
|
72
|
+
});
|
|
73
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Kimi For Coding
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 4 Kimi For Coding models through Mastra's model router. Authentication is handled automatically using the `KIMI_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Kimi For Coding documentation](https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html).
|
|
8
8
|
|
|
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
38
|
| ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
39
|
| `kimi-for-coding/k3` | 1.0M | | | | | | — | — |
|
|
40
|
+
| `kimi-for-coding/k3-256k` | 262K | | | | | | — | — |
|
|
40
41
|
| `kimi-for-coding/kimi-for-coding` | 262K | | | | | | — | — |
|
|
41
42
|
| `kimi-for-coding/kimi-for-coding-highspeed` | 262K | | | | | | — | — |
|
|
42
43
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# LLM Gateway
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 182 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
8
8
|
|
|
@@ -47,6 +47,7 @@ for await (const chunk of stream) {
|
|
|
47
47
|
| `llmgateway/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
48
48
|
| `llmgateway/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
|
|
49
49
|
| `llmgateway/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
|
|
50
|
+
| `llmgateway/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
|
|
50
51
|
| `llmgateway/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
|
|
51
52
|
| `llmgateway/claude-sonnet-4-5-20250929` | 200K | | | | | | $3 | $15 |
|
|
52
53
|
| `llmgateway/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# OpenAI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 37 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [OpenAI documentation](https://platform.openai.com/docs/models).
|
|
8
8
|
|
|
@@ -35,31 +35,19 @@ for await (const chunk of stream) {
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| ------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `openai/chatgpt-image-latest` | — | | | | | | — | — |
|
|
38
|
-
| `openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
39
|
-
| `openai/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
40
|
-
| `openai/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
|
|
41
38
|
| `openai/gpt-4.1` | 1.0M | | | | | | $2 | $8 |
|
|
42
39
|
| `openai/gpt-4.1-mini` | 1.0M | | | | | | $0.40 | $2 |
|
|
43
|
-
| `openai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
44
40
|
| `openai/gpt-4o` | 128K | | | | | | $3 | $10 |
|
|
45
|
-
| `openai/gpt-4o-2024-05-13` | 128K | | | | | | $5 | $15 |
|
|
46
41
|
| `openai/gpt-4o-2024-08-06` | 128K | | | | | | $3 | $10 |
|
|
47
42
|
| `openai/gpt-4o-2024-11-20` | 128K | | | | | | $3 | $10 |
|
|
48
43
|
| `openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
49
44
|
| `openai/gpt-5` | 400K | | | | | | $1 | $10 |
|
|
50
|
-
| `openai/gpt-5-chat-latest` | 400K | | | | | | $1 | $10 |
|
|
51
|
-
| `openai/gpt-5-codex` | 400K | | | | | | $1 | $10 |
|
|
52
45
|
| `openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
53
46
|
| `openai/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
|
|
54
47
|
| `openai/gpt-5-pro` | 400K | | | | | | $15 | $120 |
|
|
55
48
|
| `openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
|
|
56
|
-
| `openai/gpt-5.1-chat-latest` | 128K | | | | | | $1 | $10 |
|
|
57
|
-
| `openai/gpt-5.1-codex` | 400K | | | | | | $1 | $10 |
|
|
58
|
-
| `openai/gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
|
|
59
|
-
| `openai/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
|
|
60
49
|
| `openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
|
|
61
50
|
| `openai/gpt-5.2-chat-latest` | 128K | | | | | | $2 | $14 |
|
|
62
|
-
| `openai/gpt-5.2-codex` | 400K | | | | | | $2 | $14 |
|
|
63
51
|
| `openai/gpt-5.2-pro` | 400K | | | | | | $21 | $168 |
|
|
64
52
|
| `openai/gpt-5.3-chat-latest` | 128K | | | | | | $2 | $14 |
|
|
65
53
|
| `openai/gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
|
|
@@ -74,19 +62,12 @@ for await (const chunk of stream) {
|
|
|
74
62
|
| `openai/gpt-5.6-luna` | 1.1M | | | | | | $1 | $6 |
|
|
75
63
|
| `openai/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
76
64
|
| `openai/gpt-5.6-terra` | 1.1M | | | | | | $3 | $15 |
|
|
77
|
-
| `openai/gpt-image-1` | — | | | | | | — | — |
|
|
78
65
|
| `openai/gpt-image-1-mini` | — | | | | | | — | — |
|
|
79
66
|
| `openai/gpt-image-1.5` | — | | | | | | — | — |
|
|
80
67
|
| `openai/gpt-image-2` | — | | | | | | $5 | $30 |
|
|
81
68
|
| `openai/gpt-realtime-2.1` | 128K | | | | | | $4 | $24 |
|
|
82
|
-
| `openai/o1` | 200K | | | | | | $15 | $60 |
|
|
83
|
-
| `openai/o1-pro` | 200K | | | | | | $150 | $600 |
|
|
84
69
|
| `openai/o3` | 200K | | | | | | $2 | $8 |
|
|
85
|
-
| `openai/o3-deep-research` | 200K | | | | | | $10 | $40 |
|
|
86
|
-
| `openai/o3-mini` | 200K | | | | | | $1 | $4 |
|
|
87
70
|
| `openai/o3-pro` | 200K | | | | | | $20 | $80 |
|
|
88
|
-
| `openai/o4-mini` | 200K | | | | | | $1 | $4 |
|
|
89
|
-
| `openai/o4-mini-deep-research` | 200K | | | | | | $2 | $8 |
|
|
90
71
|
| `openai/text-embedding-3-large` | 8K | | | | | | $0.13 | — |
|
|
91
72
|
| `openai/text-embedding-3-small` | 8K | | | | | | $0.02 | — |
|
|
92
73
|
| `openai/text-embedding-ada-002` | 8K | | | | | | $0.10 | — |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# OpenCode Zen
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 59 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
|
|
8
8
|
|
|
@@ -44,6 +44,7 @@ for await (const chunk of stream) {
|
|
|
44
44
|
| `opencode/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
45
45
|
| `opencode/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
|
|
46
46
|
| `opencode/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
|
|
47
|
+
| `opencode/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
|
|
47
48
|
| `opencode/claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
|
|
48
49
|
| `opencode/claude-sonnet-4-5` | 1.0M | | | | | | $3 | $15 |
|
|
49
50
|
| `opencode/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
|
|
@@ -85,6 +86,7 @@ for await (const chunk of stream) {
|
|
|
85
86
|
| `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
86
87
|
| `opencode/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
87
88
|
| `opencode/laguna-s-2.1-free` | 256K | | | | | | — | — |
|
|
89
|
+
| `opencode/ling-3.0-flash-free` | 262K | | | | | | — | — |
|
|
88
90
|
| `opencode/mimo-v2.5-free` | 200K | | | | | | — | — |
|
|
89
91
|
| `opencode/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
90
92
|
| `opencode/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# xAI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 10 xAI models through Mastra's model router. Authentication is handled automatically using the `XAI_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [xAI documentation](https://docs.x.ai/docs/models).
|
|
8
8
|
|
|
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
|
|
|
43
43
|
| `xai/grok-imagine-image` | 8K | | | | | | — | — |
|
|
44
44
|
| `xai/grok-imagine-image-quality` | 8K | | | | | | — | — |
|
|
45
45
|
| `xai/grok-imagine-video` | 1K | | | | | | — | — |
|
|
46
|
+
| `xai/grok-imagine-video-1.5` | 1K | | | | | | — | — |
|
|
46
47
|
|
|
47
48
|
## Advanced configuration
|
|
48
49
|
|
|
@@ -71,7 +72,7 @@ const agent = new Agent({
|
|
|
71
72
|
model: ({ requestContext }) => {
|
|
72
73
|
const useAdvanced = requestContext.task === "complex";
|
|
73
74
|
return useAdvanced
|
|
74
|
-
? "xai/grok-imagine-video"
|
|
75
|
+
? "xai/grok-imagine-video-1.5"
|
|
75
76
|
: "xai/grok-4.20-0309-non-reasoning";
|
|
76
77
|
}
|
|
77
78
|
});
|
|
@@ -15,6 +15,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
15
15
|
- [Abacus](https://mastra.ai/models/providers/abacus)
|
|
16
16
|
- [abliteration.ai](https://mastra.ai/models/providers/abliteration-ai)
|
|
17
17
|
- [AI-ROUTER](https://mastra.ai/models/providers/ai-router)
|
|
18
|
+
- [ai&](https://mastra.ai/models/providers/aiand)
|
|
18
19
|
- [AKI.IO](https://mastra.ai/models/providers/aki-io)
|
|
19
20
|
- [Alibaba](https://mastra.ai/models/providers/alibaba)
|
|
20
21
|
- [Alibaba (China)](https://mastra.ai/models/providers/alibaba-cn)
|
|
@@ -57,6 +58,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
57
58
|
- [GitHub Models](https://mastra.ai/models/providers/github-models)
|
|
58
59
|
- [GMI Cloud](https://mastra.ai/models/providers/gmicloud)
|
|
59
60
|
- [Helicone](https://mastra.ai/models/providers/helicone)
|
|
61
|
+
- [Hetzner](https://mastra.ai/models/providers/hetzner)
|
|
60
62
|
- [HPC-AI](https://mastra.ai/models/providers/hpc-ai)
|
|
61
63
|
- [Hugging Face](https://mastra.ai/models/providers/huggingface)
|
|
62
64
|
- [iFlow](https://mastra.ai/models/providers/iflowcn)
|