@mastra/mcp-docs-server 1.2.19-alpha.15 → 1.2.19-alpha.16
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/channels.md +27 -1
- package/.docs/docs/memory/semantic-recall.md +19 -0
- package/.docs/docs/observability/metrics/overview.md +31 -44
- package/.docs/docs/server/server-adapters.md +97 -26
- package/.docs/models/environment-variables.md +4 -0
- package/.docs/models/gateways/netlify.md +2 -1
- package/.docs/models/gateways/openrouter.md +3 -1
- package/.docs/models/gateways/vercel.md +5 -2
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/agnes.md +74 -0
- package/.docs/models/providers/cline-pass.md +4 -2
- package/.docs/models/providers/deepseek.md +4 -6
- package/.docs/models/providers/digitalocean.md +3 -3
- package/.docs/models/providers/edenai.md +4 -5
- package/.docs/models/providers/iteracompute.md +73 -0
- package/.docs/models/providers/kilo.md +9 -7
- package/.docs/models/providers/nano-gpt.md +8 -8
- package/.docs/models/providers/neosmith.md +104 -0
- package/.docs/models/providers/openai.md +2 -2
- package/.docs/models/providers/standardcompute.md +73 -0
- package/.docs/models/providers/vivgrid.md +2 -1
- package/.docs/models/providers/wandb.md +2 -1
- package/.docs/models/providers/zai.md +2 -1
- package/.docs/models/providers.md +4 -0
- package/.docs/reference/index.md +2 -0
- package/.docs/reference/observability/metrics/automatic-metrics.md +1 -1
- package/.docs/reference/observability/metrics/queries.md +462 -0
- package/.docs/reference/server/elysia-adapter.md +184 -0
- package/CHANGELOG.md +7 -0
- package/package.json +4 -4
- package/.docs/docs/observability/metrics/querying.md +0 -314
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# Agnes AI
|
|
4
|
+
|
|
5
|
+
Access 2 Agnes AI models through Mastra's model router. Authentication is handled automatically using the `AGNES_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [Agnes AI documentation](https://agnes-ai.com/doc).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
AGNES_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: "agnes/agnes-2.0-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
|
+
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Agnes AI documentation](https://agnes-ai.com/doc) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ----------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `agnes/agnes-2.0-flash` | 512K | | | | | | — | — |
|
|
40
|
+
| `agnes/agnes-2.5-flash` | 512K | | | | | | — | — |
|
|
41
|
+
|
|
42
|
+
## Advanced configuration
|
|
43
|
+
|
|
44
|
+
### Custom headers
|
|
45
|
+
|
|
46
|
+
```typescript
|
|
47
|
+
const agent = new Agent({
|
|
48
|
+
id: "custom-agent",
|
|
49
|
+
name: "custom-agent",
|
|
50
|
+
model: {
|
|
51
|
+
url: "https://apihub.agnes-ai.com/v1",
|
|
52
|
+
id: "agnes/agnes-2.0-flash",
|
|
53
|
+
apiKey: process.env.AGNES_API_KEY,
|
|
54
|
+
headers: {
|
|
55
|
+
"X-Custom-Header": "value"
|
|
56
|
+
}
|
|
57
|
+
}
|
|
58
|
+
});
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
### Dynamic model selection
|
|
62
|
+
|
|
63
|
+
```typescript
|
|
64
|
+
const agent = new Agent({
|
|
65
|
+
id: "dynamic-agent",
|
|
66
|
+
name: "Dynamic Agent",
|
|
67
|
+
model: ({ requestContext }) => {
|
|
68
|
+
const useAdvanced = requestContext.task === "complex";
|
|
69
|
+
return useAdvanced
|
|
70
|
+
? "agnes/agnes-2.5-flash"
|
|
71
|
+
: "agnes/agnes-2.0-flash";
|
|
72
|
+
}
|
|
73
|
+
});
|
|
74
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# ClinePass
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 13 ClinePass models through Mastra's model router. Authentication is handled automatically using the `CLINE_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [ClinePass documentation](https://docs.cline.bot/getting-started/clinepass).
|
|
8
8
|
|
|
@@ -39,6 +39,7 @@ for await (const chunk of stream) {
|
|
|
39
39
|
| `cline-pass/cline-pass/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
40
40
|
| `cline-pass/cline-pass/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
41
41
|
| `cline-pass/cline-pass/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
42
|
+
| `cline-pass/cline-pass/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
42
43
|
| `cline-pass/cline-pass/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
43
44
|
| `cline-pass/cline-pass/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
44
45
|
| `cline-pass/cline-pass/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
@@ -47,6 +48,7 @@ for await (const chunk of stream) {
|
|
|
47
48
|
| `cline-pass/cline-pass/minimax-m3` | 512K | | | | | | $0.30 | $1 |
|
|
48
49
|
| `cline-pass/cline-pass/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
49
50
|
| `cline-pass/cline-pass/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
51
|
+
| `cline-pass/cline-pass/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
50
52
|
|
|
51
53
|
## Advanced configuration
|
|
52
54
|
|
|
@@ -76,7 +78,7 @@ const agent = new Agent({
|
|
|
76
78
|
model: ({ requestContext }) => {
|
|
77
79
|
const useAdvanced = requestContext.task === "complex";
|
|
78
80
|
return useAdvanced
|
|
79
|
-
? "cline-pass/cline-pass/qwen3.
|
|
81
|
+
? "cline-pass/cline-pass/qwen3.8-max"
|
|
80
82
|
: "cline-pass/cline-pass/deepseek-v4-flash";
|
|
81
83
|
}
|
|
82
84
|
});
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# DeepSeek
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 3 DeepSeek models through Mastra's model router. Authentication is handled automatically using the `DEEPSEEK_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [DeepSeek documentation](https://api-docs.deepseek.com/quick_start/pricing).
|
|
8
8
|
|
|
@@ -17,7 +17,7 @@ const agent = new Agent({
|
|
|
17
17
|
id: "my-agent",
|
|
18
18
|
name: "My Agent",
|
|
19
19
|
instructions: "You are a helpful assistant",
|
|
20
|
-
model: "deepseek/deepseek-
|
|
20
|
+
model: "deepseek/deepseek-v4-flash"
|
|
21
21
|
});
|
|
22
22
|
|
|
23
23
|
// Generate a response
|
|
@@ -34,8 +34,6 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `deepseek/deepseek-chat` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
38
|
-
| `deepseek/deepseek-reasoner` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
39
37
|
| `deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
40
38
|
| `deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
41
39
|
| `deepseek/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
@@ -50,7 +48,7 @@ const agent = new Agent({
|
|
|
50
48
|
name: "custom-agent",
|
|
51
49
|
model: {
|
|
52
50
|
url: "https://api.deepseek.com",
|
|
53
|
-
id: "deepseek/deepseek-
|
|
51
|
+
id: "deepseek/deepseek-v4-flash",
|
|
54
52
|
apiKey: process.env.DEEPSEEK_API_KEY,
|
|
55
53
|
headers: {
|
|
56
54
|
"X-Custom-Header": "value"
|
|
@@ -69,7 +67,7 @@ const agent = new Agent({
|
|
|
69
67
|
const useAdvanced = requestContext.task === "complex";
|
|
70
68
|
return useAdvanced
|
|
71
69
|
? "deepseek/deepseek-v4-pro"
|
|
72
|
-
: "deepseek/deepseek-
|
|
70
|
+
: "deepseek/deepseek-v4-flash";
|
|
73
71
|
}
|
|
74
72
|
});
|
|
75
73
|
```
|
|
@@ -104,9 +104,9 @@ for await (const chunk of stream) {
|
|
|
104
104
|
| `digitalocean/openai-gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
|
|
105
105
|
| `digitalocean/openai-gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
|
|
106
106
|
| `digitalocean/openai-gpt-5.5` | 1.0M | | | | | | $5 | $30 |
|
|
107
|
-
| `digitalocean/openai-gpt-5.6-luna` | 1.1M | | | | | | $0.
|
|
108
|
-
| `digitalocean/openai-gpt-5.6-sol` | 1.1M | | | | | | $
|
|
109
|
-
| `digitalocean/openai-gpt-5.6-terra` | 1.1M | | | | | | $
|
|
107
|
+
| `digitalocean/openai-gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
108
|
+
| `digitalocean/openai-gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
109
|
+
| `digitalocean/openai-gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
110
110
|
| `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
|
|
111
111
|
| `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
|
|
112
112
|
| `digitalocean/openai-gpt-image-2` | — | | | | | | $8 | $30 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Eden AI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 231 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Eden AI documentation](https://docs.edenai.co).
|
|
8
8
|
|
|
@@ -94,7 +94,6 @@ for await (const chunk of stream) {
|
|
|
94
94
|
| `edenai/deepinfra/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.45 | $1 |
|
|
95
95
|
| `edenai/deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
96
96
|
| `edenai/deepseek/deepseek-chat` | 131K | | | | | | $0.28 | $0.42 |
|
|
97
|
-
| `edenai/deepseek/deepseek-reasoner` | 131K | | | | | | $0.28 | $0.42 |
|
|
98
97
|
| `edenai/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.44 | $1 |
|
|
99
98
|
| `edenai/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
100
99
|
| `edenai/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -139,7 +138,7 @@ for await (const chunk of stream) {
|
|
|
139
138
|
| `edenai/minimax/MiniMax-M2.7` | 205K | | | | | | $0.30 | $1 |
|
|
140
139
|
| `edenai/minimax/MiniMax-M3` | 524K | | | | | | $0.30 | $1 |
|
|
141
140
|
| `edenai/mistral/codestral-latest` | 256K | | | | | | $0.30 | $0.90 |
|
|
142
|
-
| `edenai/mistral/devstral-2512` | 262K | | | | | | $0.
|
|
141
|
+
| `edenai/mistral/devstral-2512` | 262K | | | | | | $0.44 | $2 |
|
|
143
142
|
| `edenai/mistral/devstral-medium-latest` | 262K | | | | | | $0.40 | $2 |
|
|
144
143
|
| `edenai/mistral/magistral-medium-latest` | 262K | | | | | | $2 | $5 |
|
|
145
144
|
| `edenai/mistral/mistral-large-2512` | 262K | | | | | | $0.50 | $2 |
|
|
@@ -199,8 +198,8 @@ for await (const chunk of stream) {
|
|
|
199
198
|
| `edenai/perplexityai/sonar-deep-research` | 128K | | | | | | $2 | $8 |
|
|
200
199
|
| `edenai/perplexityai/sonar-pro` | 200K | | | | | | $3 | $15 |
|
|
201
200
|
| `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
202
|
-
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
203
|
-
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $
|
|
201
|
+
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.35 | $1 |
|
|
202
|
+
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
204
203
|
| `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
|
|
205
204
|
| `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
|
|
206
205
|
| `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# IteraCompute
|
|
4
|
+
|
|
5
|
+
Access 1 IteraCompute model through Mastra's model router. Authentication is handled automatically using the `ITERACOMPUTE_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [IteraCompute documentation](https://iteracompute.com/docs.html).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
ITERACOMPUTE_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: "iteracompute/iteracompute/qwen3.8-27b"
|
|
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
|
+
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [IteraCompute documentation](https://iteracompute.com/docs.html) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `iteracompute/iteracompute/qwen3.8-27b` | 262K | | | | | | $0.35 | $3 |
|
|
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://api.iteracompute.com/v1",
|
|
51
|
+
id: "iteracompute/iteracompute/qwen3.8-27b",
|
|
52
|
+
apiKey: process.env.ITERACOMPUTE_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
|
+
? "iteracompute/iteracompute/qwen3.8-27b"
|
|
70
|
+
: "iteracompute/iteracompute/qwen3.8-27b";
|
|
71
|
+
}
|
|
72
|
+
});
|
|
73
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Kilo Gateway
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 367 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
8
8
|
|
|
@@ -40,10 +40,10 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
|
|
41
41
|
| `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
|
|
42
42
|
| `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
|
|
43
|
-
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.
|
|
43
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.10 |
|
|
44
44
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.38 | $2 |
|
|
45
45
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
46
|
-
| `kilo/~moonshotai/kimi-latest` |
|
|
46
|
+
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $3 | $14 |
|
|
47
47
|
| `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
|
|
48
48
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
49
49
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
@@ -174,7 +174,9 @@ for await (const chunk of stream) {
|
|
|
174
174
|
| `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
|
|
175
175
|
| `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
|
|
176
176
|
| `kilo/minimax/minimax-m2.7` | 197K | | | | | | $0.30 | $1 |
|
|
177
|
+
| `kilo/minimax/minimax-m2.7:free` | 197K | | | | | | — | — |
|
|
177
178
|
| `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
|
|
179
|
+
| `kilo/minimax/minimax-m3:free` | 1.0M | | | | | | — | — |
|
|
178
180
|
| `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
|
|
179
181
|
| `kilo/mistralai/devstral-2512` | 262K | | | | | | $0.44 | $2 |
|
|
180
182
|
| `kilo/mistralai/ministral-14b-2512` | 262K | | | | | | $0.20 | $0.20 |
|
|
@@ -268,7 +270,7 @@ for await (const chunk of stream) {
|
|
|
268
270
|
| `kilo/openai/gpt-audio-mini` | 128K | | | | | | $0.60 | $2 |
|
|
269
271
|
| `kilo/openai/gpt-chat-latest` | 400K | | | | | | $5 | $30 |
|
|
270
272
|
| `kilo/openai/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.17 |
|
|
271
|
-
| `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.
|
|
273
|
+
| `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.02 | $0.10 |
|
|
272
274
|
| `kilo/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
273
275
|
| `kilo/openai/o1` | 200K | | | | | | $15 | $60 |
|
|
274
276
|
| `kilo/openai/o1-pro` | 200K | | | | | | $150 | $600 |
|
|
@@ -341,7 +343,7 @@ for await (const chunk of stream) {
|
|
|
341
343
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
342
344
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
343
345
|
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
344
|
-
| `kilo/qwen/qwen3.8-27b` |
|
|
346
|
+
| `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
|
|
345
347
|
| `kilo/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
346
348
|
| `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
|
|
347
349
|
| `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
|
|
@@ -365,7 +367,7 @@ for await (const chunk of stream) {
|
|
|
365
367
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
366
368
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
367
369
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
368
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
370
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
369
371
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
370
372
|
| `kilo/tencent/hy3:free` | 262K | | | | | | — | — |
|
|
371
373
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
@@ -397,7 +399,7 @@ for await (const chunk of stream) {
|
|
|
397
399
|
| `kilo/z-ai/glm-4.7-flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
398
400
|
| `kilo/z-ai/glm-5` | 198K | | | | | | $0.60 | $2 |
|
|
399
401
|
| `kilo/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
|
|
400
|
-
| `kilo/z-ai/glm-5.1` |
|
|
402
|
+
| `kilo/z-ai/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
401
403
|
| `kilo/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
402
404
|
| `kilo/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
403
405
|
| `kilo/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
|
|
@@ -210,8 +210,8 @@ for await (const chunk of stream) {
|
|
|
210
210
|
| `nano-gpt/Gemma-4-31B-Cognitive-Unshackled` | 262K | | | | | | $0.31 | $0.31 |
|
|
211
211
|
| `nano-gpt/Gemma-4-31B-DarkIdol` | 262K | | | | | | $0.31 | $0.31 |
|
|
212
212
|
| `nano-gpt/Gemma-4-31B-GarnetV2` | 262K | | | | | | $0.31 | $0.31 |
|
|
213
|
-
| `nano-gpt/Gemma-4-31B-MeroMero-v2` |
|
|
214
|
-
| `nano-gpt/Gemma-4-31B-MeroMero-v2:thinking` |
|
|
213
|
+
| `nano-gpt/Gemma-4-31B-MeroMero-v2` | 262K | | | | | | $0.08 | $0.33 |
|
|
214
|
+
| `nano-gpt/Gemma-4-31B-MeroMero-v2:thinking` | 262K | | | | | | $0.08 | $0.33 |
|
|
215
215
|
| `nano-gpt/Gemma-4-31B-Queen` | 262K | | | | | | $0.31 | $0.31 |
|
|
216
216
|
| `nano-gpt/gemma-4-e2b-it` | 131K | | | | | | $0.02 | $0.10 |
|
|
217
217
|
| `nano-gpt/gemma-4-e4b-it` | 131K | | | | | | $0.04 | $0.20 |
|
|
@@ -246,8 +246,8 @@ for await (const chunk of stream) {
|
|
|
246
246
|
| `nano-gpt/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
247
247
|
| `nano-gpt/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.08 | $0.33 |
|
|
248
248
|
| `nano-gpt/google/gemma-4-26b-a4b-it:thinking` | 262K | | | | | | $0.13 | $0.40 |
|
|
249
|
-
| `nano-gpt/google/gemma-4-26b-a4b-uncensored` |
|
|
250
|
-
| `nano-gpt/google/gemma-4-26b-a4b-uncensored:thinking` |
|
|
249
|
+
| `nano-gpt/google/gemma-4-26b-a4b-uncensored` | 262K | | | | | | $0.08 | $0.33 |
|
|
250
|
+
| `nano-gpt/google/gemma-4-26b-a4b-uncensored:thinking` | 262K | | | | | | $0.08 | $0.33 |
|
|
251
251
|
| `nano-gpt/google/gemma-4-31b-it` | 262K | | | | | | $0.08 | $0.33 |
|
|
252
252
|
| `nano-gpt/google/gemma-4-31b-it:thinking` | 262K | | | | | | $0.10 | $0.35 |
|
|
253
253
|
| `nano-gpt/Gryphe/MythoMax-L2-13b` | 4K | | | | | | $0.10 | $0.10 |
|
|
@@ -427,8 +427,8 @@ for await (const chunk of stream) {
|
|
|
427
427
|
| `nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking` | 262K | | | | | | $0.10 | $0.40 |
|
|
428
428
|
| `nano-gpt/ornith-ai/ornith-1.5-397b` | 262K | | | | | | $0.90 | $4 |
|
|
429
429
|
| `nano-gpt/ornith-ai/ornith-1.5-397b:thinking` | 262K | | | | | | $0.90 | $4 |
|
|
430
|
-
| `nano-gpt/ornith-ai/ornith-1.5-9b` |
|
|
431
|
-
| `nano-gpt/ornith-ai/ornith-1.5-9b:thinking` |
|
|
430
|
+
| `nano-gpt/ornith-ai/ornith-1.5-9b` | 262K | | | | | | $0.05 | $0.10 |
|
|
431
|
+
| `nano-gpt/ornith-ai/ornith-1.5-9b:thinking` | 262K | | | | | | $0.05 | $0.10 |
|
|
432
432
|
| `nano-gpt/pamanseau/OpenReasoning-Nemotron-32B` | 33K | | | | | | $0.10 | $0.40 |
|
|
433
433
|
| `nano-gpt/perceptron/perceptron-mk1` | 33K | | | | | | $0.15 | $2 |
|
|
434
434
|
| `nano-gpt/perplexity-academic-researcher` | 127K | | | | | | $2 | $8 |
|
|
@@ -467,8 +467,8 @@ for await (const chunk of stream) {
|
|
|
467
467
|
| `nano-gpt/qwen/qwen3.5-plus` | 984K | | | | | | $0.40 | $2 |
|
|
468
468
|
| `nano-gpt/qwen/qwen3.5-plus-thinking` | 984K | | | | | | $0.40 | $2 |
|
|
469
469
|
| `nano-gpt/qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.11 | $0.80 |
|
|
470
|
-
| `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored` |
|
|
471
|
-
| `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored:thinking` |
|
|
470
|
+
| `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored` | 262K | | | | | | $0.15 | $0.50 |
|
|
471
|
+
| `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored:thinking` | 262K | | | | | | $0.15 | $0.50 |
|
|
472
472
|
| `nano-gpt/qwen/Qwen3.6-35B-A3B:thinking` | 262K | | | | | | $0.11 | $0.80 |
|
|
473
473
|
| `nano-gpt/qwen/qwen3.8-27b-obliterated` | 262K | | | | | | $0.18 | $0.50 |
|
|
474
474
|
| `nano-gpt/qwen/qwen3.8-27b-obliterated:thinking` | 262K | | | | | | $0.18 | $0.50 |
|
|
@@ -0,0 +1,104 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# NeoSmith
|
|
4
|
+
|
|
5
|
+
Access 4 NeoSmith models through Mastra's model router. Authentication is handled automatically using the `NEOSMITH_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [NeoSmith documentation](https://neosmith.ai/docs).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
NEOSMITH_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: "neosmith/neosmith.intelligent-basic"
|
|
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
|
+
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [NeoSmith documentation](https://neosmith.ai/docs) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `neosmith/neosmith.intelligent-basic` | 1.0M | | | | | | $1 | $4 |
|
|
40
|
+
| `neosmith/neosmith.intelligent-maestro` | 1.0M | | | | | | $2 | $12 |
|
|
41
|
+
| `neosmith/neosmith.intelligent-pro` | 1.0M | | | | | | $2 | $8 |
|
|
42
|
+
| `neosmith/neosmith.neolite` | 512K | | | | | | $0.60 | $2 |
|
|
43
|
+
|
|
44
|
+
## Advanced configuration
|
|
45
|
+
|
|
46
|
+
### Custom headers
|
|
47
|
+
|
|
48
|
+
```typescript
|
|
49
|
+
const agent = new Agent({
|
|
50
|
+
id: "custom-agent",
|
|
51
|
+
name: "custom-agent",
|
|
52
|
+
model: {
|
|
53
|
+
url: "https://router.neosmith.ai/v1",
|
|
54
|
+
id: "neosmith/neosmith.intelligent-basic",
|
|
55
|
+
apiKey: process.env.NEOSMITH_API_KEY,
|
|
56
|
+
headers: {
|
|
57
|
+
"X-Custom-Header": "value"
|
|
58
|
+
}
|
|
59
|
+
}
|
|
60
|
+
});
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
### Dynamic model selection
|
|
64
|
+
|
|
65
|
+
```typescript
|
|
66
|
+
const agent = new Agent({
|
|
67
|
+
id: "dynamic-agent",
|
|
68
|
+
name: "Dynamic Agent",
|
|
69
|
+
model: ({ requestContext }) => {
|
|
70
|
+
const useAdvanced = requestContext.task === "complex";
|
|
71
|
+
return useAdvanced
|
|
72
|
+
? "neosmith/neosmith.neolite"
|
|
73
|
+
: "neosmith/neosmith.intelligent-basic";
|
|
74
|
+
}
|
|
75
|
+
});
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
## Direct provider installation
|
|
79
|
+
|
|
80
|
+
This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the [package documentation](https://www.npmjs.com/package/@ai-sdk/openai) for more details.
|
|
81
|
+
|
|
82
|
+
**npm**:
|
|
83
|
+
|
|
84
|
+
```bash
|
|
85
|
+
npm install @ai-sdk/openai
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
**pnpm**:
|
|
89
|
+
|
|
90
|
+
```bash
|
|
91
|
+
pnpm add @ai-sdk/openai
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
**Yarn**:
|
|
95
|
+
|
|
96
|
+
```bash
|
|
97
|
+
yarn add @ai-sdk/openai
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
**Bun**:
|
|
101
|
+
|
|
102
|
+
```bash
|
|
103
|
+
bun add @ai-sdk/openai
|
|
104
|
+
```
|
|
@@ -58,9 +58,9 @@ for await (const chunk of stream) {
|
|
|
58
58
|
| `openai/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
|
|
59
59
|
| `openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
|
|
60
60
|
| `openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
|
|
61
|
-
| `openai/gpt-5.6` | 1.1M | | | | | | $
|
|
61
|
+
| `openai/gpt-5.6` | 1.1M | | | | | | $4 | $20 |
|
|
62
62
|
| `openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
63
|
-
| `openai/gpt-5.6-sol` | 1.1M | | | | | | $
|
|
63
|
+
| `openai/gpt-5.6-sol` | 1.1M | | | | | | $4 | $20 |
|
|
64
64
|
| `openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
65
65
|
| `openai/gpt-image-1-mini` | — | | | | | | — | — |
|
|
66
66
|
| `openai/gpt-image-1.5` | — | | | | | | — | — |
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# Standard Compute
|
|
4
|
+
|
|
5
|
+
Access 1 Standard Compute model through Mastra's model router. Authentication is handled automatically using the `STANDARDCOMPUTE_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [Standard Compute documentation](https://standardcompute.com/models).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
STANDARDCOMPUTE_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: "standardcompute/standardcompute"
|
|
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
|
+
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Standard Compute documentation](https://standardcompute.com/models) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `standardcompute/standardcompute` | 1.0M | | | | | | — | — |
|
|
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://api.stdcmpt.com/v1",
|
|
51
|
+
id: "standardcompute/standardcompute",
|
|
52
|
+
apiKey: process.env.STANDARDCOMPUTE_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
|
+
? "standardcompute/standardcompute"
|
|
70
|
+
: "standardcompute/standardcompute";
|
|
71
|
+
}
|
|
72
|
+
});
|
|
73
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Vivgrid
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 21 Vivgrid models through Mastra's model router. Authentication is handled automatically using the `VIVGRID_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Vivgrid documentation](https://docs.vivgrid.com/models).
|
|
8
8
|
|
|
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `vivgrid/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
42
42
|
| `vivgrid/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
|
|
43
43
|
| `vivgrid/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
44
|
+
| `vivgrid/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
44
45
|
| `vivgrid/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
45
46
|
| `vivgrid/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
46
47
|
| `vivgrid/gpt-5-mini` | 272K | | | | | | $0.25 | $2 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Weights & Biases
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 30 Weights & Biases models through Mastra's model router. Authentication is handled automatically using the `WANDB_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Weights & Biases documentation](https://docs.wandb.ai).
|
|
8
8
|
|
|
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `wandb/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
43
43
|
| `wandb/google/gemma-4-31B-it` | 262K | | | | | | $0.10 | $0.34 |
|
|
44
44
|
| `wandb/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
|
|
45
|
+
| `wandb/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
|
|
45
46
|
| `wandb/JetBrains/Mellum2-12B-A2.5B-Instruct` | 131K | | | | | | $0.05 | $0.10 |
|
|
46
47
|
| `wandb/meta-llama/Llama-3.1-70B-Instruct` | 128K | | | | | | $0.80 | $0.80 |
|
|
47
48
|
| `wandb/meta-llama/Llama-3.1-8B-Instruct` | 128K | | | | | | $0.22 | $0.22 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Z.AI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 15 Z.AI models through Mastra's model router. Authentication is handled automatically using the `ZHIPU_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Z.AI documentation](https://docs.z.ai/guides/overview/pricing).
|
|
8
8
|
|
|
@@ -49,6 +49,7 @@ for await (const chunk of stream) {
|
|
|
49
49
|
| `zai/glm-5-turbo` | 200K | | | | | | $1 | $4 |
|
|
50
50
|
| `zai/glm-5.1` | 200K | | | | | | $1 | $4 |
|
|
51
51
|
| `zai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
52
|
+
| `zai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
52
53
|
| `zai/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
|
|
53
54
|
|
|
54
55
|
## Advanced configuration
|