@mastra/mcp-docs-server 1.2.11-alpha.1 → 1.2.11-alpha.4

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 (63) hide show
  1. package/.docs/docs/agent-controller/channels.md +109 -0
  2. package/.docs/docs/capabilities/channels/overview.md +1 -0
  3. package/.docs/docs/deployment/cloud-providers.md +1 -0
  4. package/.docs/docs/deployment/overview.md +1 -0
  5. package/.docs/docs/mastra-platform/overview.md +4 -2
  6. package/.docs/docs/mastra-platform/trace-intelligence.md +123 -0
  7. package/.docs/docs/rag/vector-databases.md +17 -0
  8. package/.docs/docs/voice/overview.md +5 -0
  9. package/.docs/docs/voice/{livekit.md → realtime-voice.md} +5 -3
  10. package/.docs/docs/workspace/filesystem.md +1 -0
  11. package/.docs/docs/workspace/sandbox.md +5 -0
  12. package/.docs/guides/deployment/kubernetes.md +298 -0
  13. package/.docs/guides/deployment/netlify.md +1 -1
  14. package/.docs/models/environment-variables.md +1 -0
  15. package/.docs/models/gateways/openrouter.md +2 -2
  16. package/.docs/models/gateways/vercel.md +8 -1
  17. package/.docs/models/index.md +1 -1
  18. package/.docs/models/providers/abliteration-ai.md +6 -5
  19. package/.docs/models/providers/aiand.md +2 -1
  20. package/.docs/models/providers/ambient.md +2 -2
  21. package/.docs/models/providers/anthropic.md +1 -1
  22. package/.docs/models/providers/anyapi.md +1 -1
  23. package/.docs/models/providers/baseten.md +5 -4
  24. package/.docs/models/providers/crof.md +2 -1
  25. package/.docs/models/providers/deepinfra.md +5 -4
  26. package/.docs/models/providers/digitalocean.md +1 -1
  27. package/.docs/models/providers/fireworks-ai.md +4 -2
  28. package/.docs/models/providers/google.md +1 -1
  29. package/.docs/models/providers/huggingface.md +2 -1
  30. package/.docs/models/providers/hyper.md +92 -0
  31. package/.docs/models/providers/llmgateway.md +7 -5
  32. package/.docs/models/providers/mistral.md +1 -1
  33. package/.docs/models/providers/nebius.md +2 -1
  34. package/.docs/models/providers/nvidia.md +23 -9
  35. package/.docs/models/providers/ollama-cloud.md +2 -1
  36. package/.docs/models/providers/openai.md +1 -1
  37. package/.docs/models/providers/opencode-go.md +1 -1
  38. package/.docs/models/providers/opencode.md +3 -2
  39. package/.docs/models/providers/poe.md +1 -1
  40. package/.docs/models/providers/scaleway.md +1 -1
  41. package/.docs/models/providers/synthetic.md +2 -1
  42. package/.docs/models/providers/togetherai.md +2 -1
  43. package/.docs/models/providers/wandb.md +1 -1
  44. package/.docs/models/providers/xiaomi-token-plan-ams.md +4 -4
  45. package/.docs/models/providers/xiaomi-token-plan-cn.md +4 -4
  46. package/.docs/models/providers/xiaomi-token-plan-sgp.md +4 -4
  47. package/.docs/models/providers/xiaomi.md +4 -4
  48. package/.docs/models/providers.md +1 -0
  49. package/.docs/reference/agents/channels.md +10 -0
  50. package/.docs/reference/evals/mastra-scorer.md +56 -0
  51. package/.docs/reference/storage/duckdb.md +4 -0
  52. package/.docs/reference/vectors/mongodb.md +185 -4
  53. package/.docs/reference/voice/livekit.md +3 -3
  54. package/CHANGELOG.md +14 -0
  55. package/dist/index.js +2 -3
  56. package/dist/src-BZcgzbk9.js +1774 -0
  57. package/dist/src-BZcgzbk9.js.map +1 -0
  58. package/dist/stdio.js +28 -30
  59. package/dist/stdio.js.map +1 -1
  60. package/package.json +6 -6
  61. package/dist/chunk-GLPCVXXO.js +0 -2075
  62. package/dist/chunk-GLPCVXXO.js.map +0 -1
  63. package/dist/index.js.map +0 -1
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
4
4
 
5
- Access 52 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
5
+ Access 53 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
6
6
 
7
7
  Learn more in the [Hugging Face documentation](https://huggingface.co).
8
8
 
@@ -55,6 +55,7 @@ for await (const chunk of stream) {
55
55
  | `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
56
56
  | `huggingface/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
57
57
  | `huggingface/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
58
+ | `huggingface/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
58
59
  | `huggingface/openai/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
59
60
  | `huggingface/openai/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
60
61
  | `huggingface/Qwen/Qwen3-235B-A22B` | 41K | | | | | | $0.20 | $0.80 |
@@ -0,0 +1,92 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![Charm Hyper logo](https://models.dev/logos/hyper.svg)Charm Hyper
4
+
5
+ Access 20 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
6
+
7
+ Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
8
+
9
+ ```bash
10
+ HYPER_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: "hyper/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 [Charm Hyper documentation](https://hyper.charm.land) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `hyper/deepseek-v4-flash` | 1.0M | | | | | | $0.20 | $0.40 |
40
+ | `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
41
+ | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.40 |
42
+ | `hyper/glm-5` | 203K | | | | | | $0.91 | $3 |
43
+ | `hyper/glm-5.1` | 203K | | | | | | $2 | $5 |
44
+ | `hyper/glm-5.2` | 1.0M | | | | | | $1 | $4 |
45
+ | `hyper/gpt-oss-120b` | 131K | | | | | | $0.18 | $0.68 |
46
+ | `hyper/kimi-k2.5` | 262K | | | | | | $0.53 | $3 |
47
+ | `hyper/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
48
+ | `hyper/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
49
+ | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
50
+ | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.92 |
51
+ | `hyper/minimax-m2.7` | 205K | | | | | | $0.42 | $2 |
52
+ | `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.60 | $2 |
53
+ | `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
54
+ | `hyper/qwen3.6-flash` | 1.0M | | | | | | $1 | $4 |
55
+ | `hyper/qwen3.6-max` | 256K | | | | | | $2 | $12 |
56
+ | `hyper/qwen3.6-plus` | 1.0M | | | | | | $2 | $6 |
57
+ | `hyper/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
58
+ | `hyper/qwen3.7-plus` | 1.0M | | | | | | $1 | $5 |
59
+
60
+ ## Advanced configuration
61
+
62
+ ### Custom headers
63
+
64
+ ```typescript
65
+ const agent = new Agent({
66
+ id: "custom-agent",
67
+ name: "custom-agent",
68
+ model: {
69
+ url: "https://hyper.charm.land/v1",
70
+ id: "hyper/deepseek-v4-flash",
71
+ apiKey: process.env.HYPER_API_KEY,
72
+ headers: {
73
+ "X-Custom-Header": "value"
74
+ }
75
+ }
76
+ });
77
+ ```
78
+
79
+ ### Dynamic model selection
80
+
81
+ ```typescript
82
+ const agent = new Agent({
83
+ id: "dynamic-agent",
84
+ name: "Dynamic Agent",
85
+ model: ({ requestContext }) => {
86
+ const useAdvanced = requestContext.task === "complex";
87
+ return useAdvanced
88
+ ? "hyper/qwen3.7-plus"
89
+ : "hyper/deepseek-v4-flash";
90
+ }
91
+ });
92
+ ```
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway.svg)LLM Gateway
4
4
 
5
- Access 182 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
5
+ Access 185 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
 
@@ -56,7 +56,7 @@ for await (const chunk of stream) {
56
56
  | `llmgateway/cosmos3-super-reasoner` | 262K | | | | | | $0.10 | $0.30 |
57
57
  | `llmgateway/custom` | 128K | | | | | | — | — |
58
58
  | `llmgateway/deepseek-v3.2` | 164K | | | | | | $0.26 | $0.38 |
59
- | `llmgateway/deepseek-v4-flash` | 1.1M | | | | | | $0.14 | $0.28 |
59
+ | `llmgateway/deepseek-v4-flash` | 1.1M | | | | | | $0.08 | $0.15 |
60
60
  | `llmgateway/deepseek-v4-pro` | 1.1M | | | | | | $0.43 | $0.87 |
61
61
  | `llmgateway/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
62
62
  | `llmgateway/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
@@ -71,7 +71,7 @@ for await (const chunk of stream) {
71
71
  | `llmgateway/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
72
72
  | `llmgateway/gemma-3-27b` | 110K | | | | | | $0.10 | $0.30 |
73
73
  | `llmgateway/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
74
- | `llmgateway/gemma-4-31b-it` | 262K | | | | | | $0.13 | $0.38 |
74
+ | `llmgateway/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
75
75
  | `llmgateway/glm-4-32b-0414-128k` | 128K | | | | | | $0.10 | $0.10 |
76
76
  | `llmgateway/glm-4.5` | 131K | | | | | | $0.60 | $2 |
77
77
  | `llmgateway/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
@@ -86,7 +86,7 @@ for await (const chunk of stream) {
86
86
  | `llmgateway/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.40 |
87
87
  | `llmgateway/glm-5` | 203K | | | | | | $0.72 | $2 |
88
88
  | `llmgateway/glm-5.1` | 205K | | | | | | $0.93 | $3 |
89
- | `llmgateway/glm-5.2` | 1.0M | | | | | | $1 | $4 |
89
+ | `llmgateway/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
90
90
  | `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
91
91
  | `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
92
92
  | `llmgateway/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
@@ -96,7 +96,9 @@ for await (const chunk of stream) {
96
96
  | `llmgateway/gpt-4o` | 128K | | | | | | $3 | $10 |
97
97
  | `llmgateway/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
98
98
  | `llmgateway/gpt-4o-mini-search-preview` | 128K | | | | | | $0.15 | $0.60 |
99
+ | `llmgateway/gpt-4o-mini-transcribe` | 16K | | | | | | $1 | $5 |
99
100
  | `llmgateway/gpt-4o-search-preview` | 128K | | | | | | $3 | $10 |
101
+ | `llmgateway/gpt-4o-transcribe` | 16K | | | | | | $3 | $10 |
100
102
  | `llmgateway/gpt-5` | 400K | | | | | | $1 | $10 |
101
103
  | `llmgateway/gpt-5-chat-latest` | 400K | | | | | | $1 | $10 |
102
104
  | `llmgateway/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
@@ -120,7 +122,7 @@ for await (const chunk of stream) {
120
122
  | `llmgateway/gpt-5.6-luna` | 1.1M | | | | | | $1 | $6 |
121
123
  | `llmgateway/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
122
124
  | `llmgateway/gpt-5.6-terra` | 1.1M | | | | | | $3 | $15 |
123
- | `llmgateway/gpt-oss-120b` | 131K | | | | | | $0.05 | $0.25 |
125
+ | `llmgateway/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
124
126
  | `llmgateway/gpt-oss-20b` | 131K | | | | | | $0.04 | $0.15 |
125
127
  | `llmgateway/grok-4` | 256K | | | | | | $3 | $15 |
126
128
  | `llmgateway/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Mistral logo](https://models.dev/logos/mistral.svg)Mistral
4
4
 
5
- Access 22 Mistral models through Mastra's model router. Authentication is handled automatically using the `MISTRAL_API_KEY` environment variable.
5
+ Access 30 Mistral models through Mastra's model router. Authentication is handled automatically using the `MISTRAL_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Mistral documentation](https://docs.mistral.ai/getting-started/models/).
8
8
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Nebius Token Factory logo](https://models.dev/logos/nebius.svg)Nebius Token Factory
4
4
 
5
- Access 21 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
5
+ Access 33 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/).
8
8
 
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
42
42
  | `nebius/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.30 | $1 |
43
43
  | `nebius/MiniMaxAI/MiniMax-M3` | 1.0M | | | | | | $0.30 | $1 |
44
44
  | `nebius/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
45
+ | `nebius/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
45
46
  | `nebius/NousResearch/Hermes-4-405B` | 128K | | | | | | $1 | $3 |
46
47
  | `nebius/NousResearch/Hermes-4-70B` | 128K | | | | | | $0.13 | $0.40 |
47
48
  | `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1` | 128K | | | | | | $0.60 | $2 |
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Nvidia logo](https://models.dev/logos/nvidia.svg)Nvidia
4
4
 
5
- Access 82 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
5
+ Access 98 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
 
@@ -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: "nvidia/abacusai/dracarys-llama-3_1-70b-instruct"
20
+ model: "nvidia/abacusai/dracarys-llama-3.1-70b-instruct"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -36,7 +36,7 @@ for await (const chunk of stream) {
36
36
 
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
- | `nvidia/abacusai/dracarys-llama-3_1-70b-instruct` | 128K | | | | | | — | — |
39
+ | `nvidia/abacusai/dracarys-llama-3.1-70b-instruct` | 128K | | | | | | — | — |
40
40
  | `nvidia/baai/bge-m3` | 8K | | | | | | — | — |
41
41
  | `nvidia/black-forest-labs/flux_1-kontext-dev` | 41K | | | | | | — | — |
42
42
  | `nvidia/black-forest-labs/flux_1-schnell` | 77 | | | | | | — | — |
@@ -46,6 +46,8 @@ for await (const chunk of stream) {
46
46
  | `nvidia/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
47
47
  | `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
48
48
  | `nvidia/google/gemma-2-2b-it` | 128K | | | | | | — | — |
49
+ | `nvidia/google/gemma-3-12b-it` | 131K | | | | | | — | — |
50
+ | `nvidia/google/gemma-3-4b-it` | 131K | | | | | | — | — |
49
51
  | `nvidia/google/gemma-3n-e2b-it` | 128K | | | | | | — | — |
50
52
  | `nvidia/google/gemma-3n-e4b-it` | 128K | | | | | | — | — |
51
53
  | `nvidia/google/gemma-4-31b-it` | 256K | | | | | | — | — |
@@ -66,9 +68,11 @@ for await (const chunk of stream) {
66
68
  | `nvidia/minimaxai/minimax-m2.7` | 205K | | | | | | — | — |
67
69
  | `nvidia/minimaxai/minimax-m3` | 1.0M | | | | | | — | — |
68
70
  | `nvidia/mistralai/magistral-small-2506` | 33K | | | | | | — | — |
69
- | `nvidia/mistralai/mistral-7b-instruct-v03` | 66K | | | | | | — | — |
71
+ | `nvidia/mistralai/ministral-14b-instruct-2512` | 262K | | | | | | — | — |
72
+ | `nvidia/mistralai/mistral-7b-instruct-v0.3` | 66K | | | | | | — | — |
70
73
  | `nvidia/mistralai/mistral-large-3-675b-instruct-2512` | 262K | | | | | | — | — |
71
74
  | `nvidia/mistralai/mistral-medium-3-instruct` | 131K | | | | | | — | — |
75
+ | `nvidia/mistralai/mistral-medium-3.5-128b` | 262K | | | | | | — | — |
72
76
  | `nvidia/mistralai/mistral-nemotron` | 128K | | | | | | — | — |
73
77
  | `nvidia/mistralai/mistral-small-4-119b-2603` | 128K | | | | | | — | — |
74
78
  | `nvidia/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | — | — |
@@ -76,11 +80,18 @@ for await (const chunk of stream) {
76
80
  | `nvidia/nvidia/active-speaker-detection` | — | | | | | | — | — |
77
81
  | `nvidia/nvidia/bevformer` | 128K | | | | | | — | — |
78
82
  | `nvidia/nvidia/cosmos-predict1-5b` | — | | | | | | — | — |
83
+ | `nvidia/nvidia/cosmos-reason2-8b` | 131K | | | | | | — | — |
79
84
  | `nvidia/nvidia/cosmos-transfer1-7b` | — | | | | | | — | — |
80
85
  | `nvidia/nvidia/cosmos-transfer2_5-2b` | — | | | | | | — | — |
81
86
  | `nvidia/nvidia/gliner-pii` | 128K | | | | | | — | — |
82
- | `nvidia/nvidia/llama-3_1-nemotron-safety-guard-8b-v3` | 128K | | | | | | — | — |
83
87
  | `nvidia/nvidia/llama-3_2-nemoretriever-300m-embed-v1` | 33K | | | | | | — | — |
88
+ | `nvidia/nvidia/llama-3.1-nemotron-70b-instruct` | 128K | | | | | | — | — |
89
+ | `nvidia/nvidia/llama-3.1-nemotron-nano-8b-v1` | 131K | | | | | | — | — |
90
+ | `nvidia/nvidia/llama-3.1-nemotron-nano-vl-8b-v1` | 33K | | | | | | — | — |
91
+ | `nvidia/nvidia/llama-3.1-nemotron-safety-guard-8b-v3` | 128K | | | | | | — | — |
92
+ | `nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1` | 128K | | | | | | — | — |
93
+ | `nvidia/nvidia/llama-3.3-nemotron-super-49b-v1` | 131K | | | | | | — | — |
94
+ | `nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5` | 131K | | | | | | — | — |
84
95
  | `nvidia/nvidia/llama-nemotron-embed-vl-1b-v2` | 33K | | | | | | — | — |
85
96
  | `nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2` | 128K | | | | | | — | — |
86
97
  | `nvidia/nvidia/magpie-tts-zeroshot` | — | | | | | | — | — |
@@ -91,12 +102,13 @@ for await (const chunk of stream) {
91
102
  | `nvidia/nvidia/nemotron-3-ultra-550b-a55b` | 1.0M | | | | | | $0.50 | $3 |
92
103
  | `nvidia/nvidia/nemotron-content-safety-reasoning-4b` | 128K | | | | | | — | — |
93
104
  | `nvidia/nvidia/nemotron-mini-4b-instruct` | 128K | | | | | | — | — |
105
+ | `nvidia/nvidia/nemotron-nano-12b-v2-vl` | 128K | | | | | | — | — |
94
106
  | `nvidia/nvidia/nemotron-voicechat` | 128K | | | | | | — | — |
95
107
  | `nvidia/nvidia/nv-embed-v1` | 33K | | | | | | — | — |
96
108
  | `nvidia/nvidia/nv-embedcode-7b-v1` | 33K | | | | | | — | — |
97
109
  | `nvidia/nvidia/nvidia-nemotron-nano-9b-v2` | 131K | | | | | | — | — |
98
110
  | `nvidia/nvidia/rerank-qa-mistral-4b` | 128K | | | | | | — | — |
99
- | `nvidia/nvidia/riva-translate-4b-instruct-v1_1` | 128K | | | | | | — | — |
111
+ | `nvidia/nvidia/riva-translate-4b-instruct-v1.1` | 128K | | | | | | — | — |
100
112
  | `nvidia/nvidia/sparsedrive` | 128K | | | | | | — | — |
101
113
  | `nvidia/nvidia/streampetr` | 128K | | | | | | — | — |
102
114
  | `nvidia/nvidia/studiovoice` | 128K | | | | | | — | — |
@@ -106,6 +118,7 @@ for await (const chunk of stream) {
106
118
  | `nvidia/openai/gpt-oss-120b` | 128K | | | | | | — | — |
107
119
  | `nvidia/openai/gpt-oss-20b` | 131K | | | | | | — | — |
108
120
  | `nvidia/openai/whisper-large-v3` | — | | | | | | — | — |
121
+ | `nvidia/poolside/laguna-xs-2.1` | 262K | | | | | | — | — |
109
122
  | `nvidia/qwen/qwen-image` | — | | | | | | — | — |
110
123
  | `nvidia/qwen/qwen-image-edit` | — | | | | | | — | — |
111
124
  | `nvidia/qwen/qwen2.5-coder-32b-instruct` | 128K | | | | | | — | — |
@@ -116,7 +129,8 @@ for await (const chunk of stream) {
116
129
  | `nvidia/sarvamai/sarvam-m` | 128K | | | | | | — | — |
117
130
  | `nvidia/stepfun-ai/step-3.5-flash` | 256K | | | | | | — | — |
118
131
  | `nvidia/stepfun-ai/step-3.7-flash` | 256K | | | | | | — | — |
119
- | `nvidia/upstage/solar-10_7b-instruct` | 128K | | | | | | — | — |
132
+ | `nvidia/thinkingmachines/inkling` | 1.0M | | | | | | — | — |
133
+ | `nvidia/upstage/solar-10.7b-instruct` | 128K | | | | | | — | — |
120
134
  | `nvidia/z-ai/glm-5.2` | 1.0M | | | | | | — | — |
121
135
 
122
136
  ## Advanced configuration
@@ -129,7 +143,7 @@ const agent = new Agent({
129
143
  name: "custom-agent",
130
144
  model: {
131
145
  url: "https://integrate.api.nvidia.com/v1",
132
- id: "nvidia/abacusai/dracarys-llama-3_1-70b-instruct",
146
+ id: "nvidia/abacusai/dracarys-llama-3.1-70b-instruct",
133
147
  apiKey: process.env.NVIDIA_API_KEY,
134
148
  headers: {
135
149
  "X-Custom-Header": "value"
@@ -148,7 +162,7 @@ const agent = new Agent({
148
162
  const useAdvanced = requestContext.task === "complex";
149
163
  return useAdvanced
150
164
  ? "nvidia/z-ai/glm-5.2"
151
- : "nvidia/abacusai/dracarys-llama-3_1-70b-instruct";
165
+ : "nvidia/abacusai/dracarys-llama-3.1-70b-instruct";
152
166
  }
153
167
  });
154
168
  ```
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Ollama Cloud logo](https://models.dev/logos/ollama-cloud.svg)Ollama Cloud
4
4
 
5
- Access 18 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
5
+ Access 19 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
8
8
 
@@ -46,6 +46,7 @@ for await (const chunk of stream) {
46
46
  | `ollama-cloud/kimi-k2.5` | 262K | | | | | | — | — |
47
47
  | `ollama-cloud/kimi-k2.6` | 262K | | | | | | — | — |
48
48
  | `ollama-cloud/kimi-k2.7-code` | 262K | | | | | | — | — |
49
+ | `ollama-cloud/kimi-k3` | 1.0M | | | | | | — | — |
49
50
  | `ollama-cloud/minimax-m2.5` | 205K | | | | | | — | — |
50
51
  | `ollama-cloud/minimax-m2.7` | 197K | | | | | | — | — |
51
52
  | `ollama-cloud/minimax-m3` | 512K | | | | | | — | — |
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![OpenAI logo](https://models.dev/logos/openai.svg)OpenAI
4
4
 
5
- Access 37 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
5
+ Access 47 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
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![OpenCode Go logo](https://models.dev/logos/opencode-go.svg)OpenCode Go
4
4
 
5
- Access 16 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
5
+ Access 22 OpenCode Go 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 Go documentation](https://opencode.ai/docs/zen).
8
8
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
4
4
 
5
- Access 59 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
5
+ Access 85 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
 
@@ -85,6 +85,7 @@ for await (const chunk of stream) {
85
85
  | `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
86
86
  | `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
87
87
  | `opencode/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
88
+ | `opencode/kimi-k3` | 1.0M | | | | | | $3 | $15 |
88
89
  | `opencode/laguna-s-2.1-free` | 256K | | | | | | — | — |
89
90
  | `opencode/ling-3.0-flash-free` | 262K | | | | | | — | — |
90
91
  | `opencode/mimo-v2.5-free` | 200K | | | | | | — | — |
@@ -124,7 +125,7 @@ const agent = new Agent({
124
125
  model: ({ requestContext }) => {
125
126
  const useAdvanced = requestContext.task === "complex";
126
127
  return useAdvanced
127
- ? "opencode/qwen3.6-plus"
128
+ ? "opencode/trinity-large-preview-free"
128
129
  : "opencode/big-pickle";
129
130
  }
130
131
  });
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Poe logo](https://models.dev/logos/poe.svg)Poe
4
4
 
5
- Access 126 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
5
+ Access 137 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Poe documentation](https://creator.poe.com/docs/external-applications/openai-compatible-api).
8
8
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Scaleway logo](https://models.dev/logos/scaleway.svg)Scaleway
4
4
 
5
- Access 16 Scaleway models through Mastra's model router. Authentication is handled automatically using the `SCALEWAY_API_KEY` environment variable.
5
+ Access 17 Scaleway models through Mastra's model router. Authentication is handled automatically using the `SCALEWAY_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Scaleway documentation](https://www.scaleway.com/en/docs/generative-apis/).
8
8
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Synthetic logo](https://models.dev/logos/synthetic.svg)Synthetic
4
4
 
5
- Access 7 Synthetic models through Mastra's model router. Authentication is handled automatically using the `SYNTHETIC_API_KEY` environment variable.
5
+ Access 8 Synthetic models through Mastra's model router. Authentication is handled automatically using the `SYNTHETIC_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Synthetic documentation](https://synthetic.new/pricing).
8
8
 
@@ -38,6 +38,7 @@ for await (const chunk of stream) {
38
38
  | ------------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
39
  | `synthetic/hf:MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.60 | $1 |
40
40
  | `synthetic/hf:moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
41
+ | `synthetic/hf:moonshotai/Kimi-K3` | 524K | | | | | | $3 | $15 |
41
42
  | `synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4` | 262K | | | | | | $0.30 | $1 |
42
43
  | `synthetic/hf:openai/gpt-oss-120b` | 131K | | | | | | $0.10 | $0.10 |
43
44
  | `synthetic/hf:Qwen/Qwen3.6-27B` | 262K | | | | | | $0.45 | $4 |
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Together AI logo](https://models.dev/logos/togetherai.svg)Together AI
4
4
 
5
- Access 21 Together AI models through Mastra's model router. Authentication is handled automatically using the `TOGETHER_API_KEY` environment variable.
5
+ Access 34 Together AI models through Mastra's model router. Authentication is handled automatically using the `TOGETHER_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Together AI documentation](https://docs.together.ai/docs/serverless-models).
8
8
 
@@ -45,6 +45,7 @@ for await (const chunk of stream) {
45
45
  | `togetherai/MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.30 | $1 |
46
46
  | `togetherai/moonshotai/Kimi-K2.6` | 262K | | | | | | $1 | $5 |
47
47
  | `togetherai/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
48
+ | `togetherai/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
48
49
  | `togetherai/nvidia/nemotron-3-ultra-550b-a55b` | 512K | | | | | | $0.60 | $4 |
49
50
  | `togetherai/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
50
51
  | `togetherai/openai/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Weights & Biases logo](https://models.dev/logos/wandb.svg)Weights & Biases
4
4
 
5
- Access 26 Weights & Biases models through Mastra's model router. Authentication is handled automatically using the `WANDB_API_KEY` environment variable.
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
 
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Xiaomi Token Plan (Europe) logo](https://models.dev/logos/xiaomi-token-plan-ams.svg)Xiaomi Token Plan (Europe)
4
4
 
5
- Access 6 Xiaomi Token Plan (Europe) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
5
+ Access 7 Xiaomi Token Plan (Europe) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Xiaomi Token Plan (Europe) documentation](https://platform.xiaomimimo.com/#/docs).
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: "xiaomi-token-plan-ams/mimo-v2-tts"
20
+ model: "xiaomi-token-plan-ams/mimo-v2-pro"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -53,7 +53,7 @@ const agent = new Agent({
53
53
  name: "custom-agent",
54
54
  model: {
55
55
  url: "https://token-plan-ams.xiaomimimo.com/v1",
56
- id: "xiaomi-token-plan-ams/mimo-v2-tts",
56
+ id: "xiaomi-token-plan-ams/mimo-v2-pro",
57
57
  apiKey: process.env.XIAOMI_API_KEY,
58
58
  headers: {
59
59
  "X-Custom-Header": "value"
@@ -72,7 +72,7 @@ const agent = new Agent({
72
72
  const useAdvanced = requestContext.task === "complex";
73
73
  return useAdvanced
74
74
  ? "xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign"
75
- : "xiaomi-token-plan-ams/mimo-v2-tts";
75
+ : "xiaomi-token-plan-ams/mimo-v2-pro";
76
76
  }
77
77
  });
78
78
  ```
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Xiaomi Token Plan (China) logo](https://models.dev/logos/xiaomi-token-plan-cn.svg)Xiaomi Token Plan (China)
4
4
 
5
- Access 6 Xiaomi Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
5
+ Access 7 Xiaomi Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Xiaomi Token Plan (China) documentation](https://platform.xiaomimimo.com/#/docs).
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: "xiaomi-token-plan-cn/mimo-v2-tts"
20
+ model: "xiaomi-token-plan-cn/mimo-v2-pro"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -53,7 +53,7 @@ const agent = new Agent({
53
53
  name: "custom-agent",
54
54
  model: {
55
55
  url: "https://token-plan-cn.xiaomimimo.com/v1",
56
- id: "xiaomi-token-plan-cn/mimo-v2-tts",
56
+ id: "xiaomi-token-plan-cn/mimo-v2-pro",
57
57
  apiKey: process.env.XIAOMI_API_KEY,
58
58
  headers: {
59
59
  "X-Custom-Header": "value"
@@ -72,7 +72,7 @@ const agent = new Agent({
72
72
  const useAdvanced = requestContext.task === "complex";
73
73
  return useAdvanced
74
74
  ? "xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign"
75
- : "xiaomi-token-plan-cn/mimo-v2-tts";
75
+ : "xiaomi-token-plan-cn/mimo-v2-pro";
76
76
  }
77
77
  });
78
78
  ```
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Xiaomi Token Plan (Singapore) logo](https://models.dev/logos/xiaomi-token-plan-sgp.svg)Xiaomi Token Plan (Singapore)
4
4
 
5
- Access 6 Xiaomi Token Plan (Singapore) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
5
+ Access 7 Xiaomi Token Plan (Singapore) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Xiaomi Token Plan (Singapore) documentation](https://platform.xiaomimimo.com/#/docs).
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: "xiaomi-token-plan-sgp/mimo-v2-tts"
20
+ model: "xiaomi-token-plan-sgp/mimo-v2-pro"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -53,7 +53,7 @@ const agent = new Agent({
53
53
  name: "custom-agent",
54
54
  model: {
55
55
  url: "https://token-plan-sgp.xiaomimimo.com/v1",
56
- id: "xiaomi-token-plan-sgp/mimo-v2-tts",
56
+ id: "xiaomi-token-plan-sgp/mimo-v2-pro",
57
57
  apiKey: process.env.XIAOMI_API_KEY,
58
58
  headers: {
59
59
  "X-Custom-Header": "value"
@@ -72,7 +72,7 @@ const agent = new Agent({
72
72
  const useAdvanced = requestContext.task === "complex";
73
73
  return useAdvanced
74
74
  ? "xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign"
75
- : "xiaomi-token-plan-sgp/mimo-v2-tts";
75
+ : "xiaomi-token-plan-sgp/mimo-v2-pro";
76
76
  }
77
77
  });
78
78
  ```
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Xiaomi logo](https://models.dev/logos/xiaomi.svg)Xiaomi
4
4
 
5
- Access 3 Xiaomi models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
5
+ Access 6 Xiaomi models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Xiaomi documentation](https://platform.xiaomimimo.com/#/docs).
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: "xiaomi/mimo-v2.5"
20
+ model: "xiaomi/mimo-v2-flash"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -50,7 +50,7 @@ const agent = new Agent({
50
50
  name: "custom-agent",
51
51
  model: {
52
52
  url: "https://api.xiaomimimo.com/v1",
53
- id: "xiaomi/mimo-v2.5",
53
+ id: "xiaomi/mimo-v2-flash",
54
54
  apiKey: process.env.XIAOMI_API_KEY,
55
55
  headers: {
56
56
  "X-Custom-Header": "value"
@@ -69,7 +69,7 @@ const agent = new Agent({
69
69
  const useAdvanced = requestContext.task === "complex";
70
70
  return useAdvanced
71
71
  ? "xiaomi/mimo-v2.5-pro-ultraspeed"
72
- : "xiaomi/mimo-v2.5";
72
+ : "xiaomi/mimo-v2-flash";
73
73
  }
74
74
  });
75
75
  ```
@@ -32,6 +32,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
32
32
  - [Berget.AI](https://mastra.ai/models/providers/berget)
33
33
  - [Blue Claw](https://mastra.ai/models/providers/blueclaw)
34
34
  - [Cerebras](https://mastra.ai/models/providers/cerebras)
35
+ - [Charm Hyper](https://mastra.ai/models/providers/hyper)
35
36
  - [Chutes](https://mastra.ai/models/providers/chutes)
36
37
  - [Clarifai](https://mastra.ai/models/providers/clarifai)
37
38
  - [Claudinio](https://mastra.ai/models/providers/claudinio)
@@ -216,9 +216,19 @@ type ChannelHandler = (
216
216
  thread: Thread,
217
217
  message: Message,
218
218
  defaultHandler: (thread: Thread, message: Message) => Promise<void>,
219
+ ctx?: ChannelHandlerContext,
219
220
  ) => Promise<void>
220
221
  ```
221
222
 
223
+ `ctx` carries the resolved `mastra` instance, so a handler can reach storage or other registered primitives without being passed an external accessor:
224
+
225
+ ```typescript
226
+ onDirectMessage: async (thread, message, defaultHandler, ctx) => {
227
+ const store = await ctx?.mastra?.getStorage()?.getStore('memory')
228
+ await defaultHandler(thread, message)
229
+ }
230
+ ```
231
+
222
232
  ## Resource ID resolution
223
233
 
224
234
  By default a channel thread's memory `resourceId` is `${platform}:${message.author.userId}`. The sender owns the memory, scoped per platform. For apps with a shared identity, such as single sign-on (SSO), this splits memory: the same user gets `feishu:user_123` in a Feishu DM but `user_123` on the web.