@mastra/mcp-docs-server 1.1.35-alpha.8 → 1.1.35

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 (108) hide show
  1. package/.docs/course/03-agent-memory/18-advanced-configuration-semantic-recall.md +48 -4
  2. package/.docs/docs/agents/background-tasks.md +62 -2
  3. package/.docs/docs/agents/processors.md +9 -1
  4. package/.docs/docs/agents/response-caching.md +148 -0
  5. package/.docs/docs/agents/signals.md +151 -0
  6. package/.docs/docs/agents/using-tools.md +8 -0
  7. package/.docs/docs/browser/agent-browser.md +15 -0
  8. package/.docs/docs/browser/stagehand.md +25 -1
  9. package/.docs/docs/editor/tools.md +1 -1
  10. package/.docs/docs/index.md +2 -2
  11. package/.docs/docs/mastra-platform/configuration.md +1 -1
  12. package/.docs/docs/mastra-platform/overview.md +1 -1
  13. package/.docs/docs/memory/observational-memory.md +61 -13
  14. package/.docs/docs/memory/semantic-recall.md +68 -6
  15. package/.docs/docs/observability/logging.md +2 -2
  16. package/.docs/docs/observability/metrics/overview.md +4 -4
  17. package/.docs/docs/observability/overview.md +6 -6
  18. package/.docs/docs/observability/tracing/bridges/otel.md +25 -0
  19. package/.docs/docs/observability/tracing/exporters/arize.md +5 -5
  20. package/.docs/docs/observability/tracing/exporters/braintrust.md +37 -0
  21. package/.docs/docs/observability/tracing/exporters/langfuse.md +21 -0
  22. package/.docs/docs/observability/tracing/exporters/{cloud.md → mastra-platform.md} +28 -26
  23. package/.docs/docs/observability/tracing/exporters/{default.md → mastra-storage.md} +56 -19
  24. package/.docs/docs/observability/tracing/exporters/otel.md +79 -2
  25. package/.docs/docs/observability/tracing/overview.md +30 -29
  26. package/.docs/docs/observability/tracing/processors/sensitive-data-filter.md +6 -6
  27. package/.docs/docs/server/mastra-server.md +30 -19
  28. package/.docs/docs/studio/observability.md +4 -4
  29. package/.docs/docs/studio/overview.md +6 -0
  30. package/.docs/docs/voice/overview.md +84 -0
  31. package/.docs/docs/workflows/suspend-and-resume.md +28 -1
  32. package/.docs/guides/deployment/inngest.md +23 -0
  33. package/.docs/guides/migrations/mastra-cloud.md +6 -6
  34. package/.docs/guides/migrations/upgrade-to-v1/tracing.md +19 -17
  35. package/.docs/models/gateways/netlify.md +2 -1
  36. package/.docs/models/gateways/openrouter.md +4 -1
  37. package/.docs/models/gateways/vercel.md +2 -1
  38. package/.docs/models/index.md +1 -1
  39. package/.docs/models/providers/chutes.md +23 -54
  40. package/.docs/models/providers/databricks.md +96 -0
  41. package/.docs/models/providers/deepseek.md +3 -1
  42. package/.docs/models/providers/digitalocean.md +9 -2
  43. package/.docs/models/providers/firepass.md +71 -0
  44. package/.docs/models/providers/google.md +3 -2
  45. package/.docs/models/providers/kilo.md +5 -3
  46. package/.docs/models/providers/llmgateway.md +7 -1
  47. package/.docs/models/providers/nebius.md +37 -55
  48. package/.docs/models/providers/novita-ai.md +5 -5
  49. package/.docs/models/providers/nvidia.md +59 -49
  50. package/.docs/models/providers/ollama-cloud.md +1 -1
  51. package/.docs/models/providers/openai.md +2 -0
  52. package/.docs/models/providers/opencode.md +44 -43
  53. package/.docs/models/providers/poe.md +4 -1
  54. package/.docs/models/providers/sarvam.md +72 -0
  55. package/.docs/models/providers/wafer.ai.md +2 -1
  56. package/.docs/models/providers/xiaomi-token-plan-ams.md +6 -5
  57. package/.docs/models/providers/xiaomi-token-plan-cn.md +6 -5
  58. package/.docs/models/providers/xiaomi-token-plan-sgp.md +6 -5
  59. package/.docs/models/providers.md +3 -1
  60. package/.docs/reference/agents/agent.md +85 -0
  61. package/.docs/reference/browser/agent-browser.md +37 -11
  62. package/.docs/reference/browser/stagehand-browser.md +35 -9
  63. package/.docs/reference/cli/mastra.md +33 -1
  64. package/.docs/reference/client-js/agents.md +115 -1
  65. package/.docs/reference/client-js/responses.md +4 -0
  66. package/.docs/reference/configuration.md +6 -6
  67. package/.docs/reference/editor/tool-provider.md +3 -3
  68. package/.docs/reference/harness/harness-class.md +21 -8
  69. package/.docs/reference/index.md +5 -0
  70. package/.docs/reference/memory/observational-memory.md +11 -1
  71. package/.docs/reference/observability/metrics/automatic-metrics.md +2 -4
  72. package/.docs/reference/observability/tracing/bridges/datadog.md +2 -2
  73. package/.docs/reference/observability/tracing/bridges/otel.md +26 -4
  74. package/.docs/reference/observability/tracing/configuration.md +6 -3
  75. package/.docs/reference/observability/tracing/exporters/arize.md +1 -1
  76. package/.docs/reference/observability/tracing/exporters/braintrust.md +2 -0
  77. package/.docs/reference/observability/tracing/exporters/cloud-exporter.md +3 -1
  78. package/.docs/reference/observability/tracing/exporters/console-exporter.md +2 -2
  79. package/.docs/reference/observability/tracing/exporters/default-exporter.md +7 -1
  80. package/.docs/reference/observability/tracing/exporters/mastra-platform-exporter.md +263 -0
  81. package/.docs/reference/observability/tracing/exporters/mastra-storage-exporter.md +194 -0
  82. package/.docs/reference/observability/tracing/exporters/otel.md +12 -8
  83. package/.docs/reference/observability/tracing/instances.md +2 -2
  84. package/.docs/reference/observability/tracing/interfaces.md +37 -2
  85. package/.docs/reference/observability/tracing/processors/sensitive-data-filter.md +22 -0
  86. package/.docs/reference/observability/tracing/span-filtering.md +2 -2
  87. package/.docs/reference/processors/prefill-error-handler.md +3 -3
  88. package/.docs/reference/processors/response-cache.md +114 -0
  89. package/.docs/reference/processors/tool-call-filter.md +28 -0
  90. package/.docs/reference/storage/clickhouse.md +8 -8
  91. package/.docs/reference/storage/cloudflare-d1.md +1 -1
  92. package/.docs/reference/storage/cloudflare.md +1 -1
  93. package/.docs/reference/storage/composite.md +1 -1
  94. package/.docs/reference/storage/convex.md +1 -1
  95. package/.docs/reference/storage/dsql.md +428 -0
  96. package/.docs/reference/storage/duckdb.md +3 -3
  97. package/.docs/reference/storage/dynamodb.md +1 -1
  98. package/.docs/reference/storage/lance.md +1 -1
  99. package/.docs/reference/storage/libsql.md +1 -1
  100. package/.docs/reference/storage/postgresql.md +1 -1
  101. package/.docs/reference/storage/upstash.md +1 -1
  102. package/.docs/reference/streaming/ChunkType.md +44 -0
  103. package/.docs/reference/tools/brightdata.md +167 -0
  104. package/.docs/reference/tools/create-tool.md +46 -0
  105. package/.docs/reference/voice/inworld.md +133 -0
  106. package/.docs/reference/workflows/workflow-state-reader.md +113 -0
  107. package/CHANGELOG.md +106 -0
  108. package/package.json +5 -5
package/.docs/models/providers/nvidia.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Nvidia logo](https://models.dev/logos/nvidia.svg)Nvidia
2
2
 
3
- Access 82 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
3
+ Access 92 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
6
6
 
@@ -15,7 +15,7 @@ const agent = new Agent({
15
15
  id: "my-agent",
16
16
  name: "My Agent",
17
17
  instructions: "You are a helpful assistant",
18
- model: "nvidia/black-forest-labs/flux.1-dev"
18
+ model: "nvidia/abacusai/dracarys-llama-3_1-70b-instruct"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,88 +34,98 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `nvidia/abacusai/dracarys-llama-3_1-70b-instruct` | 128K | | | | | | — | — |
38
+ | `nvidia/baai/bge-m3` | 8K | | | | | | — | — |
39
+ | `nvidia/black-forest-labs/flux_1-kontext-dev` | 41K | | | | | | — | — |
40
+ | `nvidia/black-forest-labs/flux_1-schnell` | 77 | | | | | | — | — |
41
+ | `nvidia/black-forest-labs/flux_2-klein-4b` | 41K | | | | | | — | — |
37
42
  | `nvidia/black-forest-labs/flux.1-dev` | 4K | | | | | | — | — |
38
- | `nvidia/deepseek-ai/deepseek-coder-6.7b-instruct` | 128K | | | | | | — | — |
39
- | `nvidia/deepseek-ai/deepseek-r1` | 128K | | | | | | — | — |
40
- | `nvidia/deepseek-ai/deepseek-r1-0528` | 128K | | | | | | — | — |
41
- | `nvidia/deepseek-ai/deepseek-v3.1` | 128K | | | | | | — | — |
43
+ | `nvidia/bytedance/seed-oss-36b-instruct` | 262K | | | | | | — | — |
42
44
  | `nvidia/deepseek-ai/deepseek-v3.1-terminus` | 128K | | | | | | — | — |
43
45
  | `nvidia/deepseek-ai/deepseek-v3.2` | 164K | | | | | | — | — |
44
46
  | `nvidia/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
45
47
  | `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
46
- | `nvidia/google/codegemma-1.1-7b` | 128K | | | | | | — | — |
47
- | `nvidia/google/codegemma-7b` | 128K | | | | | | — | — |
48
- | `nvidia/google/gemma-2-27b-it` | 128K | | | | | | — | — |
49
48
  | `nvidia/google/gemma-2-2b-it` | 128K | | | | | | — | — |
50
- | `nvidia/google/gemma-3-12b-it` | 128K | | | | | | — | — |
51
- | `nvidia/google/gemma-3-1b-it` | 128K | | | | | | — | — |
52
49
  | `nvidia/google/gemma-3-27b-it` | 131K | | | | | | — | — |
53
50
  | `nvidia/google/gemma-3n-e2b-it` | 128K | | | | | | — | — |
54
51
  | `nvidia/google/gemma-3n-e4b-it` | 128K | | | | | | — | — |
55
52
  | `nvidia/google/gemma-4-31b-it` | 256K | | | | | | — | — |
56
- | `nvidia/meta/codellama-70b` | 128K | | | | | | — | — |
57
- | `nvidia/meta/llama-3.1-405b-instruct` | 128K | | | | | | — | — |
53
+ | `nvidia/google/google-paligemma` | 128K | | | | | | — | — |
54
+ | `nvidia/meta/esm2-650m` | 128K | | | | | | — | — |
55
+ | `nvidia/meta/esmfold` | 128K | | | | | | — | — |
58
56
  | `nvidia/meta/llama-3.1-70b-instruct` | 128K | | | | | | — | — |
57
+ | `nvidia/meta/llama-3.1-8b-instruct` | 16K | | | | | | — | — |
59
58
  | `nvidia/meta/llama-3.2-11b-vision-instruct` | 128K | | | | | | — | — |
60
59
  | `nvidia/meta/llama-3.2-1b-instruct` | 128K | | | | | | — | — |
60
+ | `nvidia/meta/llama-3.2-3b-instruct` | 33K | | | | | | — | — |
61
+ | `nvidia/meta/llama-3.2-90b-vision-instruct` | 128K | | | | | | — | — |
61
62
  | `nvidia/meta/llama-3.3-70b-instruct` | 128K | | | | | | — | — |
62
63
  | `nvidia/meta/llama-4-maverick-17b-128e-instruct` | 128K | | | | | | — | — |
63
- | `nvidia/meta/llama-4-scout-17b-16e-instruct` | 128K | | | | | | — | — |
64
- | `nvidia/meta/llama3-70b-instruct` | 128K | | | | | | — | — |
65
- | `nvidia/meta/llama3-8b-instruct` | 128K | | | | | | — | — |
66
- | `nvidia/microsoft/phi-3-medium-128k-instruct` | 128K | | | | | | — | — |
67
- | `nvidia/microsoft/phi-3-medium-4k-instruct` | 4K | | | | | | — | — |
68
- | `nvidia/microsoft/phi-3-small-128k-instruct` | 128K | | | | | | — | — |
69
- | `nvidia/microsoft/phi-3-small-8k-instruct` | 8K | | | | | | — | — |
70
- | `nvidia/microsoft/phi-3-vision-128k-instruct` | 128K | | | | | | — | — |
71
- | `nvidia/microsoft/phi-3.5-moe-instruct` | 128K | | | | | | — | — |
72
- | `nvidia/microsoft/phi-3.5-vision-instruct` | 128K | | | | | | — | — |
64
+ | `nvidia/meta/llama-guard-4-12b` | 128K | | | | | | — | — |
73
65
  | `nvidia/microsoft/phi-4-mini-instruct` | 131K | | | | | | — | — |
74
- | `nvidia/minimaxai/minimax-m2.1` | 205K | | | | | | — | — |
66
+ | `nvidia/microsoft/phi-4-multimodal-instruct` | 128K | | | | | | — | — |
75
67
  | `nvidia/minimaxai/minimax-m2.5` | 205K | | | | | | — | — |
76
68
  | `nvidia/minimaxai/minimax-m2.7` | 205K | | | | | | — | — |
77
- | `nvidia/mistralai/codestral-22b-instruct-v0.1` | 128K | | | | | | — | — |
78
69
  | `nvidia/mistralai/devstral-2-123b-instruct-2512` | 262K | | | | | | — | — |
79
- | `nvidia/mistralai/mamba-codestral-7b-v0.1` | 128K | | | | | | — | — |
80
- | `nvidia/mistralai/ministral-14b-instruct-2512` | 262K | | | | | | — | — |
81
- | `nvidia/mistralai/mistral-large-2-instruct` | 128K | | | | | | — | — |
70
+ | `nvidia/mistralai/magistral-small-2506` | 33K | | | | | | — | — |
71
+ | `nvidia/mistralai/mistral-7b-instruct-v03` | 66K | | | | | | — | — |
82
72
  | `nvidia/mistralai/mistral-large-3-675b-instruct-2512` | 262K | | | | | | — | — |
83
- | `nvidia/mistralai/mistral-medium-3.5-128b` | 262K | | | | | | — | — |
84
- | `nvidia/mistralai/mistral-small-3.1-24b-instruct-2503` | 128K | | | | | | — | — |
73
+ | `nvidia/mistralai/mistral-medium-3-instruct` | 131K | | | | | | — | — |
74
+ | `nvidia/mistralai/mistral-nemotron` | 128K | | | | | | — | — |
75
+ | `nvidia/mistralai/mistral-small-4-119b-2603` | 128K | | | | | | — | — |
76
+ | `nvidia/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | — | — |
77
+ | `nvidia/mistralai/mixtral-8x7b-instruct` | 33K | | | | | | — | — |
85
78
  | `nvidia/moonshotai/kimi-k2-instruct` | 128K | | | | | | — | — |
86
79
  | `nvidia/moonshotai/kimi-k2-instruct-0905` | 262K | | | | | | — | — |
87
80
  | `nvidia/moonshotai/kimi-k2-thinking` | 262K | | | | | | — | — |
88
- | `nvidia/moonshotai/kimi-k2.5` | 262K | | | | | | — | — |
89
81
  | `nvidia/moonshotai/kimi-k2.6` | 262K | | | | | | — | — |
90
- | `nvidia/nvidia/cosmos-nemotron-34b` | 131K | | | | | | — | — |
91
- | `nvidia/nvidia/llama-3.1-nemotron-51b-instruct` | 128K | | | | | | — | — |
92
- | `nvidia/nvidia/llama-3.1-nemotron-70b-instruct` | 128K | | | | | | — | — |
93
- | `nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1` | 131K | | | | | | — | — |
94
- | `nvidia/nvidia/llama-3.3-nemotron-super-49b-v1` | 128K | | | | | | — | — |
95
- | `nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5` | 128K | | | | | | — | — |
96
- | `nvidia/nvidia/llama-embed-nemotron-8b` | 33K | | | | | | — | — |
97
- | `nvidia/nvidia/llama3-chatqa-1.5-70b` | 128K | | | | | | — | — |
98
- | `nvidia/nvidia/nemoretriever-ocr-v1` | — | | | | | | — | — |
82
+ | `nvidia/nvidia/active-speaker-detection` | — | | | | | | — | — |
83
+ | `nvidia/nvidia/bevformer` | 128K | | | | | | — | — |
84
+ | `nvidia/nvidia/cosmos-predict1-5b` | — | | | | | | — | — |
85
+ | `nvidia/nvidia/cosmos-transfer1-7b` | — | | | | | | — | — |
86
+ | `nvidia/nvidia/cosmos-transfer2_5-2b` | — | | | | | | — | — |
87
+ | `nvidia/nvidia/gliner-pii` | 128K | | | | | | — | — |
88
+ | `nvidia/nvidia/llama-3_1-nemotron-safety-guard-8b-v3` | 128K | | | | | | — | — |
89
+ | `nvidia/nvidia/llama-3_2-nemoretriever-300m-embed-v1` | 33K | | | | | | — | — |
90
+ | `nvidia/nvidia/llama-3_3-nemotron-super-49b-v1` | 131K | | | | | | — | — |
91
+ | `nvidia/nvidia/llama-3_3-nemotron-super-49b-v1_5` | 131K | | | | | | — | — |
92
+ | `nvidia/nvidia/llama-nemotron-embed-vl-1b-v2` | 33K | | | | | | — | — |
93
+ | `nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2` | 128K | | | | | | — | — |
94
+ | `nvidia/nvidia/magpie-tts-zeroshot` | — | | | | | | — | — |
95
+ | `nvidia/nvidia/nemotron-3-content-safety` | 128K | | | | | | — | — |
99
96
  | `nvidia/nvidia/nemotron-3-nano-30b-a3b` | 131K | | | | | | — | — |
100
97
  | `nvidia/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` | 256K | | | | | | — | — |
101
98
  | `nvidia/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.20 | $0.80 |
102
- | `nvidia/nvidia/nemotron-4-340b-instruct` | 128K | | | | | | — | — |
99
+ | `nvidia/nvidia/nemotron-content-safety-reasoning-4b` | 128K | | | | | | — | — |
100
+ | `nvidia/nvidia/nemotron-mini-4b-instruct` | 128K | | | | | | — | — |
101
+ | `nvidia/nvidia/nemotron-voicechat` | 128K | | | | | | — | — |
102
+ | `nvidia/nvidia/nv-embed-v1` | 33K | | | | | | — | — |
103
+ | `nvidia/nvidia/nv-embedcode-7b-v1` | 33K | | | | | | — | — |
103
104
  | `nvidia/nvidia/nvidia-nemotron-nano-9b-v2` | 131K | | | | | | — | — |
104
- | `nvidia/nvidia/parakeet-tdt-0.6b-v2` | — | | | | | | — | — |
105
+ | `nvidia/nvidia/rerank-qa-mistral-4b` | 128K | | | | | | — | — |
106
+ | `nvidia/nvidia/riva-translate-4b-instruct-v1_1` | 128K | | | | | | — | — |
107
+ | `nvidia/nvidia/sparsedrive` | 128K | | | | | | — | — |
108
+ | `nvidia/nvidia/streampetr` | 128K | | | | | | — | — |
109
+ | `nvidia/nvidia/studiovoice` | 128K | | | | | | — | — |
110
+ | `nvidia/nvidia/synthetic-video-detector` | — | | | | | | — | — |
111
+ | `nvidia/nvidia/usdcode` | 128K | | | | | | — | — |
112
+ | `nvidia/nvidia/usdvalidate` | — | | | | | | — | — |
105
113
  | `nvidia/openai/gpt-oss-120b` | 128K | | | | | | — | — |
114
+ | `nvidia/openai/gpt-oss-20b` | 131K | | | | | | — | — |
106
115
  | `nvidia/openai/whisper-large-v3` | — | | | | | | — | — |
116
+ | `nvidia/qwen/qwen-image` | — | | | | | | — | — |
117
+ | `nvidia/qwen/qwen-image-edit` | — | | | | | | — | — |
107
118
  | `nvidia/qwen/qwen2.5-coder-32b-instruct` | 128K | | | | | | — | — |
108
- | `nvidia/qwen/qwen2.5-coder-7b-instruct` | 128K | | | | | | — | — |
109
- | `nvidia/qwen/qwen3-235b-a22b` | 131K | | | | | | — | — |
110
119
  | `nvidia/qwen/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | — | — |
111
120
  | `nvidia/qwen/qwen3-next-80b-a3b-instruct` | 262K | | | | | | — | — |
112
121
  | `nvidia/qwen/qwen3-next-80b-a3b-thinking` | 262K | | | | | | — | — |
122
+ | `nvidia/qwen/qwen3.5-122b-a10b` | 262K | | | | | | — | — |
113
123
  | `nvidia/qwen/qwen3.5-397b-a17b` | 262K | | | | | | — | — |
114
- | `nvidia/qwen/qwq-32b` | 128K | | | | | | — | — |
124
+ | `nvidia/sarvamai/sarvam-m` | 128K | | | | | | — | — |
115
125
  | `nvidia/stepfun-ai/step-3.5-flash` | 256K | | | | | | — | — |
126
+ | `nvidia/upstage/solar-10_7b-instruct` | 128K | | | | | | — | — |
116
127
  | `nvidia/z-ai/glm-5.1` | 131K | | | | | | — | — |
117
128
  | `nvidia/z-ai/glm4.7` | 205K | | | | | | — | — |
118
- | `nvidia/z-ai/glm5` | 203K | | | | | | — | — |
119
129
 
120
130
  ## Advanced configuration
121
131
 
@@ -127,7 +137,7 @@ const agent = new Agent({
127
137
  name: "custom-agent",
128
138
  model: {
129
139
  url: "https://integrate.api.nvidia.com/v1",
130
- id: "nvidia/black-forest-labs/flux.1-dev",
140
+ id: "nvidia/abacusai/dracarys-llama-3_1-70b-instruct",
131
141
  apiKey: process.env.NVIDIA_API_KEY,
132
142
  headers: {
133
143
  "X-Custom-Header": "value"
@@ -145,8 +155,8 @@ const agent = new Agent({
145
155
  model: ({ requestContext }) => {
146
156
  const useAdvanced = requestContext.task === "complex";
147
157
  return useAdvanced
148
- ? "nvidia/z-ai/glm5"
149
- : "nvidia/black-forest-labs/flux.1-dev";
158
+ ? "nvidia/z-ai/glm4.7"
159
+ : "nvidia/abacusai/dracarys-llama-3_1-70b-instruct";
150
160
  }
151
161
  });
152
162
  ```
package/.docs/models/providers/ollama-cloud.md CHANGED
@@ -55,7 +55,7 @@ for await (const chunk of stream) {
55
55
  | `ollama-cloud/kimi-k2-thinking` | 262K | | | | | | — | — |
56
56
  | `ollama-cloud/kimi-k2:1t` | 262K | | | | | | — | — |
57
57
  | `ollama-cloud/kimi-k2.5` | 262K | | | | | | — | — |
58
- | `ollama-cloud/kimi-k2.6:cloud` | 262K | | | | | | — | — |
58
+ | `ollama-cloud/kimi-k2.6` | 262K | | | | | | — | — |
59
59
  | `ollama-cloud/minimax-m2` | 205K | | | | | | — | — |
60
60
  | `ollama-cloud/minimax-m2.1` | 205K | | | | | | — | — |
61
61
  | `ollama-cloud/minimax-m2.5` | 205K | | | | | | — | — |
package/.docs/models/providers/openai.md CHANGED
@@ -176,6 +176,8 @@ const response = await agent.generate("Hello!", {
176
176
 
177
177
  **forceReasoning** (`boolean | undefined`)
178
178
 
179
+ **allowedTools** (`{ toolNames: string[]; mode?: "auto" | "required" | undefined; } | undefined`)
180
+
179
181
  ## Direct provider installation
180
182
 
181
183
  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.
package/.docs/models/providers/opencode.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
2
2
 
3
- Access 39 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
3
+ Access 40 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
6
6
 
@@ -32,47 +32,48 @@ for await (const chunk of stream) {
32
32
 
33
33
  ## Models
34
34
 
35
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
- | -------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `opencode/big-pickle` | 200K | | | | | | — | — |
38
- | `opencode/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
39
- | `opencode/claude-opus-4-1` | 200K | | | | | | $15 | $75 |
40
- | `opencode/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
- | `opencode/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
42
- | `opencode/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
43
- | `opencode/claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
44
- | `opencode/claude-sonnet-4-5` | 1.0M | | | | | | $3 | $15 |
45
- | `opencode/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
46
- | `opencode/gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
47
- | `opencode/gemini-3.1-pro` | 1.0M | | | | | | $2 | $12 |
48
- | `opencode/glm-5` | 205K | | | | | | $1 | $3 |
49
- | `opencode/glm-5.1` | 205K | | | | | | $1 | $4 |
50
- | `opencode/gpt-5` | 400K | | | | | | $1 | $9 |
51
- | `opencode/gpt-5-codex` | 400K | | | | | | $1 | $9 |
52
- | `opencode/gpt-5-nano` | 400K | | | | | | — | — |
53
- | `opencode/gpt-5.1` | 400K | | | | | | $1 | $9 |
54
- | `opencode/gpt-5.1-codex` | 400K | | | | | | $1 | $9 |
55
- | `opencode/gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
56
- | `opencode/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
57
- | `opencode/gpt-5.2` | 400K | | | | | | $2 | $14 |
58
- | `opencode/gpt-5.2-codex` | 400K | | | | | | $2 | $14 |
59
- | `opencode/gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
60
- | `opencode/gpt-5.3-codex-spark` | 128K | | | | | | $2 | $14 |
61
- | `opencode/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
62
- | `opencode/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
63
- | `opencode/gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
64
- | `opencode/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
65
- | `opencode/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
66
- | `opencode/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
67
- | `opencode/hy3-preview-free` | 256K | | | | | | — | — |
68
- | `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
69
- | `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
70
- | `opencode/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
71
- | `opencode/minimax-m2.5-free` | 205K | | | | | | — | — |
72
- | `opencode/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
73
- | `opencode/nemotron-3-super-free` | 205K | | | | | | — | — |
74
- | `opencode/qwen3.5-plus` | 262K | | | | | | $0.20 | $1 |
75
- | `opencode/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `opencode/big-pickle` | 200K | | | | | | — | — |
38
+ | `opencode/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
39
+ | `opencode/claude-opus-4-1` | 200K | | | | | | $15 | $75 |
40
+ | `opencode/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
+ | `opencode/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
42
+ | `opencode/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
43
+ | `opencode/claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
44
+ | `opencode/claude-sonnet-4-5` | 1.0M | | | | | | $3 | $15 |
45
+ | `opencode/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
46
+ | `opencode/deepseek-v4-flash-free` | 1.0M | | | | | | — | — |
47
+ | `opencode/gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
48
+ | `opencode/gemini-3.1-pro` | 1.0M | | | | | | $2 | $12 |
49
+ | `opencode/glm-5` | 205K | | | | | | $1 | $3 |
50
+ | `opencode/glm-5.1` | 205K | | | | | | $1 | $4 |
51
+ | `opencode/gpt-5` | 400K | | | | | | $1 | $9 |
52
+ | `opencode/gpt-5-codex` | 400K | | | | | | $1 | $9 |
53
+ | `opencode/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
54
+ | `opencode/gpt-5.1` | 400K | | | | | | $1 | $9 |
55
+ | `opencode/gpt-5.1-codex` | 400K | | | | | | $1 | $9 |
56
+ | `opencode/gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
57
+ | `opencode/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
58
+ | `opencode/gpt-5.2` | 400K | | | | | | $2 | $14 |
59
+ | `opencode/gpt-5.2-codex` | 400K | | | | | | $2 | $14 |
60
+ | `opencode/gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
61
+ | `opencode/gpt-5.3-codex-spark` | 128K | | | | | | $2 | $14 |
62
+ | `opencode/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
63
+ | `opencode/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
64
+ | `opencode/gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
65
+ | `opencode/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
66
+ | `opencode/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
67
+ | `opencode/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
68
+ | `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
69
+ | `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
70
+ | `opencode/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
71
+ | `opencode/minimax-m2.5-free` | 205K | | | | | | — | — |
72
+ | `opencode/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
73
+ | `opencode/nemotron-3-super-free` | 205K | | | | | | — | — |
74
+ | `opencode/qwen3.5-plus` | 262K | | | | | | $0.20 | $1 |
75
+ | `opencode/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
76
+ | `opencode/ring-2.6-1t-free` | 262K | | | | | | — | — |
76
77
 
77
78
  ## Advanced configuration
78
79
 
@@ -102,7 +103,7 @@ const agent = new Agent({
102
103
  model: ({ requestContext }) => {
103
104
  const useAdvanced = requestContext.task === "complex";
104
105
  return useAdvanced
105
- ? "opencode/qwen3.6-plus"
106
+ ? "opencode/ring-2.6-1t-free"
106
107
  : "opencode/big-pickle";
107
108
  }
108
109
  });
package/.docs/models/providers/poe.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Poe logo](https://models.dev/logos/poe.svg)Poe
2
2
 
3
- Access 121 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
3
+ Access 124 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Poe documentation](https://creator.poe.com/docs/external-applications/openai-compatible-api).
6
6
 
@@ -51,6 +51,8 @@ for await (const chunk of stream) {
51
51
  | `poe/elevenlabs/elevenlabs-music` | 2K | | | | | | — | — |
52
52
  | `poe/elevenlabs/elevenlabs-v2.5-turbo` | 128K | | | | | | — | — |
53
53
  | `poe/elevenlabs/elevenlabs-v3` | 128K | | | | | | — | — |
54
+ | `poe/empiriolabs/deepseek-v4-flash-el` | 1.0M | | | | | | $0.14 | $0.28 |
55
+ | `poe/empiriolabs/deepseek-v4-pro-el` | 1.0M | | | | | | $2 | $3 |
54
56
  | `poe/fireworks-ai/kimi-k2.5-fw` | 262K | | | | | | — | — |
55
57
  | `poe/google/gemini-2.0-flash` | 990K | | | | | | $0.10 | $0.42 |
56
58
  | `poe/google/gemini-2.0-flash-lite` | 990K | | | | | | $0.05 | $0.21 |
@@ -87,6 +89,7 @@ for await (const chunk of stream) {
87
89
  | `poe/novita/glm-5` | 205K | | | | | | $1 | $3 |
88
90
  | `poe/novita/kimi-k2-thinking` | 256K | | | | | | — | — |
89
91
  | `poe/novita/kimi-k2.5` | 128K | | | | | | $0.60 | $3 |
92
+ | `poe/novita/kimi-k2.6` | 262K | | | | | | $0.96 | $4 |
90
93
  | `poe/novita/minimax-m2.1` | 205K | | | | | | — | — |
91
94
  | `poe/openai/dall-e-3` | 800 | | | | | | — | — |
92
95
  | `poe/openai/gpt-3.5-turbo` | 16K | | | | | | $0.45 | $1 |
package/.docs/models/providers/sarvam.md ADDED
@@ -0,0 +1,72 @@
1
+ # ![Sarvam AI logo](https://models.dev/logos/sarvam.svg)Sarvam AI
2
+
3
+ Access 2 Sarvam AI models through Mastra's model router. Authentication is handled automatically using the `SARVAM_API_KEY` environment variable.
4
+
5
+ Learn more in the [Sarvam AI documentation](https://docs.sarvam.ai).
6
+
7
+ ```bash
8
+ SARVAM_API_KEY=your-api-key
9
+ ```
10
+
11
+ ```typescript
12
+ import { Agent } from "@mastra/core/agent";
13
+
14
+ const agent = new Agent({
15
+ id: "my-agent",
16
+ name: "My Agent",
17
+ instructions: "You are a helpful assistant",
18
+ model: "sarvam/sarvam-105b"
19
+ });
20
+
21
+ // Generate a response
22
+ const response = await agent.generate("Hello!");
23
+
24
+ // Stream a response
25
+ const stream = await agent.stream("Tell me a story");
26
+ for await (const chunk of stream) {
27
+ console.log(chunk);
28
+ }
29
+ ```
30
+
31
+ > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Sarvam AI documentation](https://docs.sarvam.ai) for details.
32
+
33
+ ## Models
34
+
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | -------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `sarvam/sarvam-105b` | 131K | | | | | | — | — |
38
+ | `sarvam/sarvam-30b` | 66K | | | | | | — | — |
39
+
40
+ ## Advanced configuration
41
+
42
+ ### Custom headers
43
+
44
+ ```typescript
45
+ const agent = new Agent({
46
+ id: "custom-agent",
47
+ name: "custom-agent",
48
+ model: {
49
+ url: "https://api.sarvam.ai/v1",
50
+ id: "sarvam/sarvam-105b",
51
+ apiKey: process.env.SARVAM_API_KEY,
52
+ headers: {
53
+ "X-Custom-Header": "value"
54
+ }
55
+ }
56
+ });
57
+ ```
58
+
59
+ ### Dynamic model selection
60
+
61
+ ```typescript
62
+ const agent = new Agent({
63
+ id: "dynamic-agent",
64
+ name: "Dynamic Agent",
65
+ model: ({ requestContext }) => {
66
+ const useAdvanced = requestContext.task === "complex";
67
+ return useAdvanced
68
+ ? "sarvam/sarvam-30b"
69
+ : "sarvam/sarvam-105b";
70
+ }
71
+ });
72
+ ```
package/.docs/models/providers/wafer.ai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Wafer logo](https://models.dev/logos/wafer.ai.svg)Wafer
2
2
 
3
- Access 3 Wafer models through Mastra's model router. Authentication is handled automatically using the `WAFER_API_KEY` environment variable.
3
+ Access 4 Wafer models through Mastra's model router. Authentication is handled automatically using the `WAFER_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Wafer documentation](https://docs.wafer.ai/wafer-pass).
6
6
 
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
36
36
  | ---------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
37
  | `wafer.ai/DeepSeek-V4-Pro` | 1.0M | | | | | | — | — |
38
38
  | `wafer.ai/GLM-5.1` | 203K | | | | | | — | — |
39
+ | `wafer.ai/MiniMax-M2.7` | 205K | | | | | | — | — |
39
40
  | `wafer.ai/Qwen3.5-397B-A17B` | 262K | | | | | | — | — |
40
41
 
41
42
  ## Advanced configuration
package/.docs/models/providers/xiaomi-token-plan-ams.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Xiaomi Token Plan (Europe) logo](https://models.dev/logos/xiaomi-token-plan-ams.svg)Xiaomi Token Plan (Europe)
2
2
 
3
- Access 5 Xiaomi Token Plan (Europe) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
3
+ Access 6 Xiaomi Token Plan (Europe) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Xiaomi Token Plan (Europe) documentation](https://platform.xiaomimimo.com/#/docs).
6
6
 
@@ -15,7 +15,7 @@ const agent = new Agent({
15
15
  id: "my-agent",
16
16
  name: "My Agent",
17
17
  instructions: "You are a helpful assistant",
18
- model: "xiaomi-token-plan-ams/mimo-v2-omni"
18
+ model: "xiaomi-token-plan-ams/mimo-v2-flash"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,7 +34,8 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `xiaomi-token-plan-ams/mimo-v2-omni` | 256K | | | | | | — | — |
37
+ | `xiaomi-token-plan-ams/mimo-v2-flash` | 262K | | | | | | — | — |
38
+ | `xiaomi-token-plan-ams/mimo-v2-omni` | 262K | | | | | | — | — |
38
39
  | `xiaomi-token-plan-ams/mimo-v2-pro` | 1.0M | | | | | | — | — |
39
40
  | `xiaomi-token-plan-ams/mimo-v2-tts` | 8K | | | | | | — | — |
40
41
  | `xiaomi-token-plan-ams/mimo-v2.5` | 1.0M | | | | | | — | — |
@@ -50,7 +51,7 @@ const agent = new Agent({
50
51
  name: "custom-agent",
51
52
  model: {
52
53
  url: "https://token-plan-ams.xiaomimimo.com/v1",
53
- id: "xiaomi-token-plan-ams/mimo-v2-omni",
54
+ id: "xiaomi-token-plan-ams/mimo-v2-flash",
54
55
  apiKey: process.env.XIAOMI_API_KEY,
55
56
  headers: {
56
57
  "X-Custom-Header": "value"
@@ -69,7 +70,7 @@ const agent = new Agent({
69
70
  const useAdvanced = requestContext.task === "complex";
70
71
  return useAdvanced
71
72
  ? "xiaomi-token-plan-ams/mimo-v2.5-pro"
72
- : "xiaomi-token-plan-ams/mimo-v2-omni";
73
+ : "xiaomi-token-plan-ams/mimo-v2-flash";
73
74
  }
74
75
  });
75
76
  ```
package/.docs/models/providers/xiaomi-token-plan-cn.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Xiaomi Token Plan (China) logo](https://models.dev/logos/xiaomi-token-plan-cn.svg)Xiaomi Token Plan (China)
2
2
 
3
- Access 5 Xiaomi Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
3
+ Access 6 Xiaomi Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Xiaomi Token Plan (China) documentation](https://platform.xiaomimimo.com/#/docs).
6
6
 
@@ -15,7 +15,7 @@ const agent = new Agent({
15
15
  id: "my-agent",
16
16
  name: "My Agent",
17
17
  instructions: "You are a helpful assistant",
18
- model: "xiaomi-token-plan-cn/mimo-v2-omni"
18
+ model: "xiaomi-token-plan-cn/mimo-v2-flash"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,7 +34,8 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `xiaomi-token-plan-cn/mimo-v2-omni` | 256K | | | | | | — | — |
37
+ | `xiaomi-token-plan-cn/mimo-v2-flash` | 262K | | | | | | — | — |
38
+ | `xiaomi-token-plan-cn/mimo-v2-omni` | 262K | | | | | | — | — |
38
39
  | `xiaomi-token-plan-cn/mimo-v2-pro` | 1.0M | | | | | | — | — |
39
40
  | `xiaomi-token-plan-cn/mimo-v2-tts` | 8K | | | | | | — | — |
40
41
  | `xiaomi-token-plan-cn/mimo-v2.5` | 1.0M | | | | | | — | — |
@@ -50,7 +51,7 @@ const agent = new Agent({
50
51
  name: "custom-agent",
51
52
  model: {
52
53
  url: "https://token-plan-cn.xiaomimimo.com/v1",
53
- id: "xiaomi-token-plan-cn/mimo-v2-omni",
54
+ id: "xiaomi-token-plan-cn/mimo-v2-flash",
54
55
  apiKey: process.env.XIAOMI_API_KEY,
55
56
  headers: {
56
57
  "X-Custom-Header": "value"
@@ -69,7 +70,7 @@ const agent = new Agent({
69
70
  const useAdvanced = requestContext.task === "complex";
70
71
  return useAdvanced
71
72
  ? "xiaomi-token-plan-cn/mimo-v2.5-pro"
72
- : "xiaomi-token-plan-cn/mimo-v2-omni";
73
+ : "xiaomi-token-plan-cn/mimo-v2-flash";
73
74
  }
74
75
  });
75
76
  ```
package/.docs/models/providers/xiaomi-token-plan-sgp.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Xiaomi Token Plan (Singapore) logo](https://models.dev/logos/xiaomi-token-plan-sgp.svg)Xiaomi Token Plan (Singapore)
2
2
 
3
- Access 5 Xiaomi Token Plan (Singapore) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
3
+ Access 6 Xiaomi Token Plan (Singapore) models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Xiaomi Token Plan (Singapore) documentation](https://platform.xiaomimimo.com/#/docs).
6
6
 
@@ -15,7 +15,7 @@ const agent = new Agent({
15
15
  id: "my-agent",
16
16
  name: "My Agent",
17
17
  instructions: "You are a helpful assistant",
18
- model: "xiaomi-token-plan-sgp/mimo-v2-omni"
18
+ model: "xiaomi-token-plan-sgp/mimo-v2-flash"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,7 +34,8 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `xiaomi-token-plan-sgp/mimo-v2-omni` | 256K | | | | | | — | — |
37
+ | `xiaomi-token-plan-sgp/mimo-v2-flash` | 262K | | | | | | — | — |
38
+ | `xiaomi-token-plan-sgp/mimo-v2-omni` | 262K | | | | | | — | — |
38
39
  | `xiaomi-token-plan-sgp/mimo-v2-pro` | 1.0M | | | | | | — | — |
39
40
  | `xiaomi-token-plan-sgp/mimo-v2-tts` | 8K | | | | | | — | — |
40
41
  | `xiaomi-token-plan-sgp/mimo-v2.5` | 1.0M | | | | | | — | — |
@@ -50,7 +51,7 @@ const agent = new Agent({
50
51
  name: "custom-agent",
51
52
  model: {
52
53
  url: "https://token-plan-sgp.xiaomimimo.com/v1",
53
- id: "xiaomi-token-plan-sgp/mimo-v2-omni",
54
+ id: "xiaomi-token-plan-sgp/mimo-v2-flash",
54
55
  apiKey: process.env.XIAOMI_API_KEY,
55
56
  headers: {
56
57
  "X-Custom-Header": "value"
@@ -69,7 +70,7 @@ const agent = new Agent({
69
70
  const useAdvanced = requestContext.task === "complex";
70
71
  return useAdvanced
71
72
  ? "xiaomi-token-plan-sgp/mimo-v2.5-pro"
72
- : "xiaomi-token-plan-sgp/mimo-v2-omni";
73
+ : "xiaomi-token-plan-sgp/mimo-v2-flash";
73
74
  }
74
75
  });
75
76
  ```
package/.docs/models/providers.md CHANGED
@@ -26,11 +26,13 @@ Direct access to individual AI model providers. Each provider offers unique mode
26
26
  - [Cloudflare Workers AI](https://mastra.ai/models/providers/cloudflare-workers-ai)
27
27
  - [Cortecs](https://mastra.ai/models/providers/cortecs)
28
28
  - [D.Run (China)](https://mastra.ai/models/providers/drun)
29
+ - [Databricks](https://mastra.ai/models/providers/databricks)
29
30
  - [Deep Infra](https://mastra.ai/models/providers/deepinfra)
30
31
  - [DigitalOcean](https://mastra.ai/models/providers/digitalocean)
31
32
  - [DInference](https://mastra.ai/models/providers/dinference)
32
33
  - [evroc](https://mastra.ai/models/providers/evroc)
33
34
  - [FastRouter](https://mastra.ai/models/providers/fastrouter)
35
+ - [Fireworks (Firepass)](https://mastra.ai/models/providers/firepass)
34
36
  - [Fireworks AI](https://mastra.ai/models/providers/fireworks-ai)
35
37
  - [Friendli](https://mastra.ai/models/providers/friendli)
36
38
  - [FrogBot](https://mastra.ai/models/providers/frogbot)
@@ -45,7 +47,6 @@ Direct access to individual AI model providers. Each provider offers unique mode
45
47
  - [Jiekou.AI](https://mastra.ai/models/providers/jiekou)
46
48
  - [Kilo Gateway](https://mastra.ai/models/providers/kilo)
47
49
  - [Kimi For Coding](https://mastra.ai/models/providers/kimi-for-coding)
48
- - [Kiro](https://mastra.ai/models/providers/kiro)
49
50
  - [KUAE Cloud Coding Plan](https://mastra.ai/models/providers/kuae-cloud-coding-plan)
50
51
  - [Llama](https://mastra.ai/models/providers/llama)
51
52
  - [LLM Gateway](https://mastra.ai/models/providers/llmgateway)
@@ -80,6 +81,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
80
81
  - [Qiniu](https://mastra.ai/models/providers/qiniu-ai)
81
82
  - [Regolo AI](https://mastra.ai/models/providers/regolo-ai)
82
83
  - [Requesty](https://mastra.ai/models/providers/requesty)
84
+ - [Sarvam AI](https://mastra.ai/models/providers/sarvam)
83
85
  - [Scaleway](https://mastra.ai/models/providers/scaleway)
84
86
  - [SiliconFlow](https://mastra.ai/models/providers/siliconflow)
85
87
  - [SiliconFlow (China)](https://mastra.ai/models/providers/siliconflow-cn)