@mastra/mcp-docs-server 1.2.7-alpha.10 → 1.2.7-alpha.14

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.
Files changed (35) hide show
  1. package/.docs/docs/agent-builder/integrations.md +44 -2
  2. package/.docs/docs/editor/tools.md +2 -2
  3. package/.docs/docs/getting-started/file-based-agents.md +2 -0
  4. package/.docs/models/environment-variables.md +8 -0
  5. package/.docs/models/gateways/openrouter.md +1 -3
  6. package/.docs/models/gateways/vercel.md +5 -1
  7. package/.docs/models/index.md +1 -1
  8. package/.docs/models/providers/abacus.md +44 -14
  9. package/.docs/models/providers/ai-router.md +77 -0
  10. package/.docs/models/providers/ambient.md +4 -3
  11. package/.docs/models/providers/blueclaw.md +74 -0
  12. package/.docs/models/providers/daoxe.md +81 -0
  13. package/.docs/models/providers/databricks.md +4 -2
  14. package/.docs/models/providers/deepinfra.md +2 -2
  15. package/.docs/models/providers/empiriolabs.md +106 -0
  16. package/.docs/models/providers/hpc-ai.md +16 -10
  17. package/.docs/models/providers/inferx.md +78 -0
  18. package/.docs/models/providers/llmgateway.md +2 -3
  19. package/.docs/models/providers/model-oracle-ai.md +87 -0
  20. package/.docs/models/providers/neon.md +1 -1
  21. package/.docs/models/providers/nvidia.md +1 -3
  22. package/.docs/models/providers/openai.md +2 -1
  23. package/.docs/models/providers/opencode.md +5 -2
  24. package/.docs/models/providers/pioneer.md +148 -0
  25. package/.docs/models/providers/routing-run.md +4 -1
  26. package/.docs/models/providers/unorouter.md +95 -0
  27. package/.docs/models/providers/vivgrid.md +5 -2
  28. package/.docs/models/providers/wafer.ai.md +9 -12
  29. package/.docs/models/providers/zenmux.md +5 -1
  30. package/.docs/models/providers.md +8 -0
  31. package/.docs/reference/file-based-agents/logger.md +26 -0
  32. package/.docs/reference/file-based-agents/scorers.md +54 -0
  33. package/.docs/reference/index.md +2 -0
  34. package/CHANGELOG.md +14 -0
  35. package/package.json +4 -4
package/.docs/models/providers/daoxe.md ADDED
@@ -0,0 +1,81 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![DaoXE logo](https://models.dev/logos/daoxe.svg)DaoXE
4
+
5
+ Access 9 DaoXE models through Mastra's model router. Authentication is handled automatically using the `DAOXE_API_KEY` environment variable.
6
+
7
+ Learn more in the [DaoXE documentation](https://daoxe.com/pricing).
8
+
9
+ ```bash
10
+ DAOXE_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: "daoxe/claude-haiku-4-5-20251001"
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 [DaoXE documentation](https://daoxe.com/pricing) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `daoxe/claude-haiku-4-5-20251001` | 200K | | | | | | $1 | $5 |
40
+ | `daoxe/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
41
+ | `daoxe/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
42
+ | `daoxe/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
43
+ | `daoxe/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
44
+ | `daoxe/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
45
+ | `daoxe/grok-4.3` | 1.0M | | | | | | $1 | $3 |
46
+ | `daoxe/grok-4.5` | 500K | | | | | | $2 | $6 |
47
+ | `daoxe/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
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://daoxe.com/v1",
59
+ id: "daoxe/claude-haiku-4-5-20251001",
60
+ apiKey: process.env.DAOXE_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
+ ? "daoxe/kimi-k2.5"
78
+ : "daoxe/claude-haiku-4-5-20251001";
79
+ }
80
+ });
81
+ ```
package/.docs/models/providers/databricks.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Databricks logo](https://models.dev/logos/databricks.svg)Databricks
4
4
 
5
- Access 25 Databricks models through Mastra's model router. Authentication is handled automatically using the `DATABRICKS_TOKEN` environment variable. Configure `DATABRICKS_HOST` as well.
5
+ Access 27 Databricks models through Mastra's model router. Authentication is handled automatically using the `DATABRICKS_TOKEN` environment variable. Configure `DATABRICKS_HOST` as well.
6
6
 
7
7
  Learn more in the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/).
8
8
 
@@ -51,6 +51,7 @@ for await (const chunk of stream) {
51
51
  | `databricks/databricks-gemini-3-1-pro` | 1.0M | | | | | | $2 | $12 |
52
52
  | `databricks/databricks-gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
53
53
  | `databricks/databricks-gemini-3-pro` | 1.0M | | | | | | $2 | $12 |
54
+ | `databricks/databricks-glm-5-2` | 1.0M | | | | | | $1 | $4 |
54
55
  | `databricks/databricks-gpt-5` | 400K | | | | | | $1 | $10 |
55
56
  | `databricks/databricks-gpt-5-1` | 400K | | | | | | $1 | $10 |
56
57
  | `databricks/databricks-gpt-5-2` | 400K | | | | | | $2 | $14 |
@@ -62,6 +63,7 @@ for await (const chunk of stream) {
62
63
  | `databricks/databricks-gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
63
64
  | `databricks/databricks-gpt-oss-120b` | 131K | | | | | | $0.07 | $0.28 |
64
65
  | `databricks/databricks-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
66
+ | `databricks/databricks-kimi-k2-7-code` | 262K | | | | | | $0.95 | $4 |
65
67
 
66
68
  ## Advanced configuration
67
69
 
@@ -91,7 +93,7 @@ const agent = new Agent({
91
93
  model: ({ requestContext }) => {
92
94
  const useAdvanced = requestContext.task === "complex";
93
95
  return useAdvanced
94
- ? "databricks/databricks-gpt-oss-20b"
96
+ ? "databricks/databricks-kimi-k2-7-code"
95
97
  : "databricks/databricks-claude-haiku-4-5";
96
98
  }
97
99
  });
package/.docs/models/providers/deepinfra.md CHANGED
@@ -41,7 +41,7 @@ for await (const chunk of stream) {
41
41
  | `deepinfra/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.07 | $0.34 |
42
42
  | `deepinfra/google/gemma-4-31B-it` | 262K | | | | | | $0.13 | $0.38 |
43
43
  | `deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo` | 131K | | | | | | $0.10 | $0.32 |
44
- | `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M | | | | | | $0.15 | $0.60 |
44
+ | `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M | | | | | | $0.20 | $0.80 |
45
45
  | `deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct` | 328K | | | | | | $0.10 | $0.30 |
46
46
  | `deepinfra/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.15 | $1 |
47
47
  | `deepinfra/MiniMaxAI/MiniMax-M2.7` | 197K | | | | | | $0.25 | $1 |
@@ -68,7 +68,7 @@ for await (const chunk of stream) {
68
68
  | `deepinfra/Qwen/Qwen3.7-Max` | 256K | | | | | | $3 | $8 |
69
69
  | `deepinfra/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.40 | $2 |
70
70
  | `deepinfra/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
71
- | `deepinfra/zai-org/GLM-4.6` | 203K | | | | | | $0.43 | $2 |
71
+ | `deepinfra/zai-org/GLM-4.6` | 203K | | | | | | $0.50 | $2 |
72
72
  | `deepinfra/zai-org/GLM-4.7` | 203K | | | | | | $0.40 | $2 |
73
73
  | `deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
74
74
  | `deepinfra/zai-org/GLM-5` | 203K | | | | | | $0.60 | $2 |
package/.docs/models/providers/empiriolabs.md ADDED
@@ -0,0 +1,106 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![EmpirioLabs AI logo](https://models.dev/logos/empiriolabs.svg)EmpirioLabs AI
4
+
5
+ Access 34 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
6
+
7
+ Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
8
+
9
+ ```bash
10
+ EMPIRIOLABS_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: "empiriolabs/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 [EmpirioLabs AI documentation](https://docs.empiriolabs.ai) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `empiriolabs/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
40
+ | `empiriolabs/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
41
+ | `empiriolabs/fugu-ultra` | 1.0M | | | | | | $8 | $45 |
42
+ | `empiriolabs/gemma-4-26b-a4b` | 262K | | | | | | $0.05 | $0.29 |
43
+ | `empiriolabs/glm-4-5-flash` | 200K | | | | | | — | — |
44
+ | `empiriolabs/glm-4-7-flash` | 200K | | | | | | — | — |
45
+ | `empiriolabs/glm-5-1` | 202K | | | | | | $0.82 | $3 |
46
+ | `empiriolabs/glm-5-2` | 1.0M | | | | | | $1 | $4 |
47
+ | `empiriolabs/kimi-k2-6` | 256K | | | | | | $0.89 | $4 |
48
+ | `empiriolabs/kimi-k2-7-code` | 256K | | | | | | $0.95 | $4 |
49
+ | `empiriolabs/kimi-k2-7-code-highspeed` | 256K | | | | | | $2 | $8 |
50
+ | `empiriolabs/mimo-v2-5` | 1.0M | | | | | | $0.70 | $1 |
51
+ | `empiriolabs/mimo-v2-5-pro` | 1.0M | | | | | | $2 | $4 |
52
+ | `empiriolabs/minimax-m2-7` | 200K | | | | | | $0.15 | $0.60 |
53
+ | `empiriolabs/minimax-m2-7-highspeed` | 200K | | | | | | $0.30 | $1 |
54
+ | `empiriolabs/minimax-m3` | 1.0M | | | | | | $0.23 | $0.90 |
55
+ | `empiriolabs/muse-spark-1-1` | 1.0M | | | | | | $1 | $4 |
56
+ | `empiriolabs/qwen3-5-122b-a10b` | 256K | | | | | | $0.12 | $0.92 |
57
+ | `empiriolabs/qwen3-5-27b` | 256K | | | | | | $0.09 | $0.69 |
58
+ | `empiriolabs/qwen3-5-35b-a3b` | 256K | | | | | | $0.06 | $0.46 |
59
+ | `empiriolabs/qwen3-5-397b-a17b` | 256K | | | | | | $0.17 | $1 |
60
+ | `empiriolabs/qwen3-5-4b` | 262K | | | | | | $0.04 | $0.07 |
61
+ | `empiriolabs/qwen3-5-9b` | 262K | | | | | | $0.09 | $0.13 |
62
+ | `empiriolabs/qwen3-5-plus` | 1.0M | | | | | | $0.36 | $2 |
63
+ | `empiriolabs/qwen3-6-27b` | 256K | | | | | | $0.41 | $2 |
64
+ | `empiriolabs/qwen3-6-flash` | 1.0M | | | | | | $0.25 | $2 |
65
+ | `empiriolabs/qwen3-6-max-preview` | 256K | | | | | | $1 | $8 |
66
+ | `empiriolabs/qwen3-6-plus` | 1.0M | | | | | | $0.50 | $3 |
67
+ | `empiriolabs/qwen3-7-max` | 1.0M | | | | | | $3 | $8 |
68
+ | `empiriolabs/qwen3-7-plus` | 1.0M | | | | | | $0.40 | $2 |
69
+ | `empiriolabs/qwen3-max` | 256K | | | | | | $1 | $6 |
70
+ | `empiriolabs/step-3-5-flash` | 256K | | | | | | $0.10 | $0.30 |
71
+ | `empiriolabs/step-3-5-flash-2603` | 256K | | | | | | $0.10 | $0.30 |
72
+ | `empiriolabs/step-3-7-flash` | 256K | | | | | | $0.20 | $1 |
73
+
74
+ ## Advanced configuration
75
+
76
+ ### Custom headers
77
+
78
+ ```typescript
79
+ const agent = new Agent({
80
+ id: "custom-agent",
81
+ name: "custom-agent",
82
+ model: {
83
+ url: "https://api.empiriolabs.ai/v1",
84
+ id: "empiriolabs/deepseek-v4-flash",
85
+ apiKey: process.env.EMPIRIOLABS_API_KEY,
86
+ headers: {
87
+ "X-Custom-Header": "value"
88
+ }
89
+ }
90
+ });
91
+ ```
92
+
93
+ ### Dynamic model selection
94
+
95
+ ```typescript
96
+ const agent = new Agent({
97
+ id: "dynamic-agent",
98
+ name: "Dynamic Agent",
99
+ model: ({ requestContext }) => {
100
+ const useAdvanced = requestContext.task === "complex";
101
+ return useAdvanced
102
+ ? "empiriolabs/step-3-7-flash"
103
+ : "empiriolabs/deepseek-v4-flash";
104
+ }
105
+ });
106
+ ```
package/.docs/models/providers/hpc-ai.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![HPC-AI logo](https://models.dev/logos/hpc-ai.svg)HPC-AI
4
4
 
5
- Access 3 HPC-AI models through Mastra's model router. Authentication is handled automatically using the `HPC_AI_API_KEY` environment variable.
5
+ Access 9 HPC-AI models through Mastra's model router. Authentication is handled automatically using the `HPC_AI_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [HPC-AI documentation](https://www.hpc-ai.com/doc/docs/quickstart/).
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: "hpc-ai/minimax/minimax-m2.5"
20
+ model: "hpc-ai/anthropic/claude-opus-4.7"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -34,11 +34,17 @@ for await (const chunk of stream) {
34
34
 
35
35
  ## Models
36
36
 
37
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
- | ----------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
- | `hpc-ai/minimax/minimax-m2.5` | 1.0M | | | | | | $0.30 | $1 |
40
- | `hpc-ai/moonshotai/kimi-k2.5` | 262K | | | | | | $0.30 | $2 |
41
- | `hpc-ai/zai-org/glm-5.1` | 202K | | | | | | $0.61 | $2 |
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | ----------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `hpc-ai/anthropic/claude-opus-4.7` | 1.0M | | | | | | $5 | $25 |
40
+ | `hpc-ai/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
41
+ | `hpc-ai/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
42
+ | `hpc-ai/minimax/minimax-m2.5` | 196K | | | | | | $0.30 | $1 |
43
+ | `hpc-ai/moonshotai/kimi-k2.5` | 256K | | | | | | $0.60 | $3 |
44
+ | `hpc-ai/moonshotai/kimi-k2.7-code` | 256K | | | | | | $0.95 | $4 |
45
+ | `hpc-ai/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
46
+ | `hpc-ai/zai-org/glm-5.1` | 202K | | | | | | $0.61 | $2 |
47
+ | `hpc-ai/zai-org/glm-5.2` | 1.0M | | | | | | $1 | $4 |
42
48
 
43
49
  ## Advanced configuration
44
50
 
@@ -50,7 +56,7 @@ const agent = new Agent({
50
56
  name: "custom-agent",
51
57
  model: {
52
58
  url: "https://api.hpc-ai.com/inference/v1",
53
- id: "hpc-ai/minimax/minimax-m2.5",
59
+ id: "hpc-ai/anthropic/claude-opus-4.7",
54
60
  apiKey: process.env.HPC_AI_API_KEY,
55
61
  headers: {
56
62
  "X-Custom-Header": "value"
@@ -68,8 +74,8 @@ const agent = new Agent({
68
74
  model: ({ requestContext }) => {
69
75
  const useAdvanced = requestContext.task === "complex";
70
76
  return useAdvanced
71
- ? "hpc-ai/zai-org/glm-5.1"
72
- : "hpc-ai/minimax/minimax-m2.5";
77
+ ? "hpc-ai/zai-org/glm-5.2"
78
+ : "hpc-ai/anthropic/claude-opus-4.7";
73
79
  }
74
80
  });
75
81
  ```
package/.docs/models/providers/inferx.md ADDED
@@ -0,0 +1,78 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![InferX logo](https://models.dev/logos/inferx.svg)InferX
4
+
5
+ Access 6 InferX models through Mastra's model router. Authentication is handled automatically using the `INFERX_API_KEY` environment variable.
6
+
7
+ Learn more in the [InferX documentation](https://model.inferx.net/endpoints).
8
+
9
+ ```bash
10
+ INFERX_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: "inferx/google/gemma-4-31b-it-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 [InferX documentation](https://model.inferx.net/endpoints) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `inferx/google/gemma-4-31b-it-fp8` | 262K | | | | | | — | — |
40
+ | `inferx/qwen/qwen3-coder-next-fp8` | 256K | | | | | | — | — |
41
+ | `inferx/qwen/qwen3-coder-next-fp8-1m` | 1.0M | | | | | | — | — |
42
+ | `inferx/qwen/qwen3.5-122b-a10b-nvfp4` | 256K | | | | | | — | — |
43
+ | `inferx/qwen/qwen3.6-27b-fp8` | 262K | | | | | | — | — |
44
+ | `inferx/qwen/qwen3.6-35b-a3b-fp8` | 262K | | | | | | — | — |
45
+
46
+ ## Advanced configuration
47
+
48
+ ### Custom headers
49
+
50
+ ```typescript
51
+ const agent = new Agent({
52
+ id: "custom-agent",
53
+ name: "custom-agent",
54
+ model: {
55
+ url: "https://model.inferx.net/v1",
56
+ id: "inferx/google/gemma-4-31b-it-fp8",
57
+ apiKey: process.env.INFERX_API_KEY,
58
+ headers: {
59
+ "X-Custom-Header": "value"
60
+ }
61
+ }
62
+ });
63
+ ```
64
+
65
+ ### Dynamic model selection
66
+
67
+ ```typescript
68
+ const agent = new Agent({
69
+ id: "dynamic-agent",
70
+ name: "Dynamic Agent",
71
+ model: ({ requestContext }) => {
72
+ const useAdvanced = requestContext.task === "complex";
73
+ return useAdvanced
74
+ ? "inferx/qwen/qwen3.6-35b-a3b-fp8"
75
+ : "inferx/google/gemma-4-31b-it-fp8";
76
+ }
77
+ });
78
+ ```
package/.docs/models/providers/llmgateway.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway.svg)LLM Gateway
4
4
 
5
- Access 181 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
5
+ Access 180 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
 
@@ -143,8 +143,6 @@ for await (const chunk of stream) {
143
143
  | `llmgateway/llama-3.3-70b-instruct` | 131K | | | | | | $0.13 | $0.40 |
144
144
  | `llmgateway/llama-4-maverick-17b-instruct` | 1.0M | | | | | | $0.27 | $0.85 |
145
145
  | `llmgateway/llama-4-scout-17b-instruct` | 131K | | | | | | $0.18 | $0.59 |
146
- | `llmgateway/mimo-v2-omni` | 256K | | | | | | $0.40 | $2 |
147
- | `llmgateway/mimo-v2-pro` | 1.0M | | | | | | $1 | $3 |
148
146
  | `llmgateway/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
149
147
  | `llmgateway/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
150
148
  | `llmgateway/minimax-m2` | 197K | | | | | | $0.20 | $1 |
@@ -162,6 +160,7 @@ for await (const chunk of stream) {
162
160
  | `llmgateway/mistral-large-2512` | 262K | | | | | | $0.50 | $2 |
163
161
  | `llmgateway/mistral-large-latest` | 128K | | | | | | $4 | $12 |
164
162
  | `llmgateway/mistral-small-2506` | 128K | | | | | | $0.10 | $0.30 |
163
+ | `llmgateway/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
165
164
  | `llmgateway/nemotron-3-ultra-550b` | 262K | | | | | | $0.50 | $3 |
166
165
  | `llmgateway/o1` | 200K | | | | | | $15 | $60 |
167
166
  | `llmgateway/o3` | 200K | | | | | | $2 | $8 |
package/.docs/models/providers/model-oracle-ai.md ADDED
@@ -0,0 +1,87 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![Model Oracle AI logo](https://models.dev/logos/model-oracle-ai.svg)Model Oracle AI
4
+
5
+ Access 15 Model Oracle AI models through Mastra's model router. Authentication is handled automatically using the `MODEL_ORACLE_API_KEY` environment variable.
6
+
7
+ Learn more in the [Model Oracle AI documentation](https://modeloracle.com/setup/).
8
+
9
+ ```bash
10
+ MODEL_ORACLE_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: "model-oracle-ai/auto"
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 [Model Oracle AI documentation](https://modeloracle.com/setup/) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `model-oracle-ai/auto` | 1.0M | | | | | | — | — |
40
+ | `model-oracle-ai/claude-fable-5` | 1.0M | | | | | | — | — |
41
+ | `model-oracle-ai/claude-haiku-4.5` | 200K | | | | | | — | — |
42
+ | `model-oracle-ai/claude-opus-4.8` | 1.0M | | | | | | — | — |
43
+ | `model-oracle-ai/claude-sonnet-5` | 1.0M | | | | | | — | — |
44
+ | `model-oracle-ai/deepseek-v4-pro` | 1.0M | | | | | | — | — |
45
+ | `model-oracle-ai/glm-5.2` | 1.0M | | | | | | — | — |
46
+ | `model-oracle-ai/gpt-4.1` | 1.0M | | | | | | — | — |
47
+ | `model-oracle-ai/gpt-4.1-mini` | 1.0M | | | | | | — | — |
48
+ | `model-oracle-ai/gpt-5` | 400K | | | | | | — | — |
49
+ | `model-oracle-ai/gpt-5.4` | 1.1M | | | | | | — | — |
50
+ | `model-oracle-ai/gpt-5.4-mini` | 400K | | | | | | — | — |
51
+ | `model-oracle-ai/gpt-5.4-nano` | 400K | | | | | | — | — |
52
+ | `model-oracle-ai/gpt-5.5` | 1.1M | | | | | | — | — |
53
+ | `model-oracle-ai/o4-mini` | 200K | | | | | | — | — |
54
+
55
+ ## Advanced configuration
56
+
57
+ ### Custom headers
58
+
59
+ ```typescript
60
+ const agent = new Agent({
61
+ id: "custom-agent",
62
+ name: "custom-agent",
63
+ model: {
64
+ url: "https://api.modeloracle.com/api/v1",
65
+ id: "model-oracle-ai/auto",
66
+ apiKey: process.env.MODEL_ORACLE_API_KEY,
67
+ headers: {
68
+ "X-Custom-Header": "value"
69
+ }
70
+ }
71
+ });
72
+ ```
73
+
74
+ ### Dynamic model selection
75
+
76
+ ```typescript
77
+ const agent = new Agent({
78
+ id: "dynamic-agent",
79
+ name: "Dynamic Agent",
80
+ model: ({ requestContext }) => {
81
+ const useAdvanced = requestContext.task === "complex";
82
+ return useAdvanced
83
+ ? "model-oracle-ai/o4-mini"
84
+ : "model-oracle-ai/auto";
85
+ }
86
+ });
87
+ ```
package/.docs/models/providers/neon.md CHANGED
@@ -83,7 +83,7 @@ const agent = new Agent({
83
83
  id: "custom-agent",
84
84
  name: "custom-agent",
85
85
  model: {
86
- url: "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1",
86
+ url: "${NEON_AI_GATEWAY_BASE_URL}/v1",
87
87
  id: "neon/claude-haiku-4-5",
88
88
  apiKey: process.env.NEON_AI_GATEWAY_TOKEN,
89
89
  headers: {
package/.docs/models/providers/nvidia.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Nvidia logo](https://models.dev/logos/nvidia.svg)Nvidia
4
4
 
5
- Access 84 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
5
+ Access 82 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
8
8
 
@@ -73,8 +73,6 @@ for await (const chunk of stream) {
73
73
  | `nvidia/mistralai/mistral-small-4-119b-2603` | 128K | | | | | | — | — |
74
74
  | `nvidia/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | — | — |
75
75
  | `nvidia/mistralai/mixtral-8x7b-instruct` | 33K | | | | | | — | — |
76
- | `nvidia/moonshotai/kimi-k2-instruct-0905` | 262K | | | | | | — | — |
77
- | `nvidia/moonshotai/kimi-k2.6` | 262K | | | | | | — | — |
78
76
  | `nvidia/nvidia/active-speaker-detection` | — | | | | | | — | — |
79
77
  | `nvidia/nvidia/bevformer` | 128K | | | | | | — | — |
80
78
  | `nvidia/nvidia/cosmos-predict1-5b` | — | | | | | | — | — |
package/.docs/models/providers/openai.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![OpenAI logo](https://models.dev/logos/openai.svg)OpenAI
4
4
 
5
- Access 55 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
5
+ Access 56 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
 
@@ -78,6 +78,7 @@ for await (const chunk of stream) {
78
78
  | `openai/gpt-image-1-mini` | — | | | | | | — | — |
79
79
  | `openai/gpt-image-1.5` | — | | | | | | — | — |
80
80
  | `openai/gpt-image-2` | — | | | | | | $5 | $30 |
81
+ | `openai/gpt-realtime-2.1` | 128K | | | | | | $4 | $24 |
81
82
  | `openai/o1` | 200K | | | | | | $15 | $60 |
82
83
  | `openai/o1-pro` | 200K | | | | | | $150 | $600 |
83
84
  | `openai/o3` | 200K | | | | | | $2 | $8 |
package/.docs/models/providers/opencode.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
4
4
 
5
- Access 52 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
5
+ Access 55 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
 
@@ -74,9 +74,12 @@ for await (const chunk of stream) {
74
74
  | `opencode/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
75
75
  | `opencode/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
76
76
  | `opencode/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
77
+ | `opencode/gpt-5.6-luna` | 1.1M | | | | | | $1 | $6 |
78
+ | `opencode/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
79
+ | `opencode/gpt-5.6-terra` | 1.1M | | | | | | $3 | $15 |
77
80
  | `opencode/grok-4.5` | 500K | | | | | | $2 | $6 |
78
81
  | `opencode/grok-build-0.1` | 256K | | | | | | $1 | $2 |
79
- | `opencode/hy3-free` | 256K | | | | | | — | — |
82
+ | `opencode/hy3-free` | 190K | | | | | | — | — |
80
83
  | `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
81
84
  | `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
82
85
  | `opencode/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |