@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/databricks.md ADDED
@@ -0,0 +1,96 @@
1
+ # ![Databricks logo](https://models.dev/logos/databricks.svg)Databricks
2
+
3
+ Access 25 Databricks models through Mastra's model router. Authentication is handled automatically using the `DATABRICKS_TOKEN` environment variable. Configure `DATABRICKS_HOST` as well.
4
+
5
+ Learn more in the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/).
6
+
7
+ ```bash
8
+ DATABRICKS_HOST=your-value
9
+ DATABRICKS_TOKEN=your-api-token
10
+ ```
11
+
12
+ ```typescript
13
+ import { Agent } from "@mastra/core/agent";
14
+
15
+ const agent = new Agent({
16
+ id: "my-agent",
17
+ name: "My Agent",
18
+ instructions: "You are a helpful assistant",
19
+ model: "databricks/databricks-claude-haiku-4-5"
20
+ });
21
+
22
+ // Generate a response
23
+ const response = await agent.generate("Hello!");
24
+
25
+ // Stream a response
26
+ const stream = await agent.stream("Tell me a story");
27
+ for await (const chunk of stream) {
28
+ console.log(chunk);
29
+ }
30
+ ```
31
+
32
+ > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/) for details.
33
+
34
+ ## Models
35
+
36
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
37
+ | --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
38
+ | `databricks/databricks-claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
39
+ | `databricks/databricks-claude-opus-4-1` | 200K | | | | | | $15 | $75 |
40
+ | `databricks/databricks-claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
+ | `databricks/databricks-claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
42
+ | `databricks/databricks-claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
43
+ | `databricks/databricks-claude-sonnet-4` | 200K | | | | | | $3 | $15 |
44
+ | `databricks/databricks-claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
45
+ | `databricks/databricks-claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
46
+ | `databricks/databricks-gemini-2-5-flash` | 1.0M | | | | | | $0.30 | $3 |
47
+ | `databricks/databricks-gemini-2-5-pro` | 1.0M | | | | | | $1 | $10 |
48
+ | `databricks/databricks-gemini-3-1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
49
+ | `databricks/databricks-gemini-3-1-pro` | 1.0M | | | | | | $2 | $12 |
50
+ | `databricks/databricks-gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
51
+ | `databricks/databricks-gemini-3-pro` | 1.0M | | | | | | $2 | $12 |
52
+ | `databricks/databricks-gpt-5` | 400K | | | | | | $1 | $10 |
53
+ | `databricks/databricks-gpt-5-1` | 400K | | | | | | $1 | $10 |
54
+ | `databricks/databricks-gpt-5-2` | 400K | | | | | | $2 | $14 |
55
+ | `databricks/databricks-gpt-5-4` | 1.1M | | | | | | $3 | $15 |
56
+ | `databricks/databricks-gpt-5-4-mini` | 400K | | | | | | $0.75 | $5 |
57
+ | `databricks/databricks-gpt-5-4-nano` | 400K | | | | | | $0.20 | $1 |
58
+ | `databricks/databricks-gpt-5-5` | 1.1M | | | | | | $5 | $30 |
59
+ | `databricks/databricks-gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
60
+ | `databricks/databricks-gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
61
+ | `databricks/databricks-gpt-oss-120b` | 131K | | | | | | $0.07 | $0.28 |
62
+ | `databricks/databricks-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
63
+
64
+ ## Advanced configuration
65
+
66
+ ### Custom headers
67
+
68
+ ```typescript
69
+ const agent = new Agent({
70
+ id: "custom-agent",
71
+ name: "custom-agent",
72
+ model: {
73
+ url: "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1",
74
+ id: "databricks/databricks-claude-haiku-4-5",
75
+ apiKey: process.env.DATABRICKS_TOKEN,
76
+ headers: {
77
+ "X-Custom-Header": "value"
78
+ }
79
+ }
80
+ });
81
+ ```
82
+
83
+ ### Dynamic model selection
84
+
85
+ ```typescript
86
+ const agent = new Agent({
87
+ id: "dynamic-agent",
88
+ name: "Dynamic Agent",
89
+ model: ({ requestContext }) => {
90
+ const useAdvanced = requestContext.task === "complex";
91
+ return useAdvanced
92
+ ? "databricks/databricks-gpt-oss-20b"
93
+ : "databricks/databricks-claude-haiku-4-5";
94
+ }
95
+ });
96
+ ```
package/.docs/models/providers/deepseek.md CHANGED
@@ -87,4 +87,6 @@ const response = await agent.generate("Hello!", {
87
87
 
88
88
  ### Available Options
89
89
 
90
- **thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
90
+ **thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
91
+
92
+ **reasoningEffort** (`"high" | "max" | undefined`)
package/.docs/models/providers/digitalocean.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![DigitalOcean logo](https://models.dev/logos/digitalocean.svg)DigitalOcean
2
2
 
3
- Access 64 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
3
+ Access 71 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
4
4
 
5
5
  Learn more in the [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/).
6
6
 
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
37
37
  | `digitalocean/alibaba-qwen3-32b` | 131K | | | | | | $0.25 | $0.55 |
38
38
  | `digitalocean/all-mini-lm-l6-v2` | 256 | | | | | | $0.01 | — |
39
39
  | `digitalocean/anthropic-claude-4.1-opus` | 200K | | | | | | $15 | $75 |
40
+ | `digitalocean/anthropic-claude-4.5-haiku` | 200K | | | | | | $1 | $5 |
40
41
  | `digitalocean/anthropic-claude-4.5-sonnet` | 1.0M | | | | | | $3 | $15 |
41
42
  | `digitalocean/anthropic-claude-4.6-sonnet` | 1.0M | | | | | | $3 | $15 |
42
43
  | `digitalocean/anthropic-claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
@@ -50,6 +51,7 @@ for await (const chunk of stream) {
50
51
  | `digitalocean/bge-reranker-v2-m3` | 8K | | | | | | $0.01 | — |
51
52
  | `digitalocean/deepseek-3.2` | 128K | | | | | | $0.50 | $2 |
52
53
  | `digitalocean/deepseek-r1-distill-llama-70b` | 131K | | | | | | $0.99 | $0.99 |
54
+ | `digitalocean/deepseek-v3` | 164K | | | | | | — | — |
53
55
  | `digitalocean/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
54
56
  | `digitalocean/e5-large-v2` | 512 | | | | | | $0.02 | — |
55
57
  | `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | — | | | | | | — | — |
@@ -62,11 +64,14 @@ for await (const chunk of stream) {
62
64
  | `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
63
65
  | `digitalocean/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
64
66
  | `digitalocean/llama-4-maverick` | 1.0M | | | | | | $0.25 | $0.87 |
65
- | `digitalocean/llama-guard-4-12b` | 128K | | | | | | — | — |
67
+ | `digitalocean/llama3-8b-instruct` | 131K | | | | | | $0.20 | $0.20 |
66
68
  | `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
67
69
  | `digitalocean/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
70
+ | `digitalocean/ministral-3-8b-instruct-2512` | 262K | | | | | | — | — |
68
71
  | `digitalocean/mistral-3-14B` | 262K | | | | | | $0.20 | $0.20 |
72
+ | `digitalocean/mistral-7b-instruct-v0.3` | 33K | | | | | | — | — |
69
73
  | `digitalocean/multi-qa-mpnet-base-dot-v1` | 512 | | | | | | $0.01 | — |
74
+ | `digitalocean/nemotron-3-nano-30b` | 262K | | | | | | — | — |
70
75
  | `digitalocean/nemotron-3-nano-omni` | 66K | | | | | | $0.50 | $0.90 |
71
76
  | `digitalocean/nemotron-nano-12b-v2-vl` | 128K | | | | | | $0.20 | $0.60 |
72
77
  | `digitalocean/nvidia-nemotron-3-super-120b` | 256K | | | | | | $0.30 | $0.65 |
@@ -87,11 +92,13 @@ for await (const chunk of stream) {
87
92
  | `digitalocean/openai-gpt-5.5` | 1.0M | | | | | | $5 | $30 |
88
93
  | `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
89
94
  | `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
95
+ | `digitalocean/openai-gpt-image-2` | — | | | | | | — | — |
90
96
  | `digitalocean/openai-gpt-oss-120b` | 131K | | | | | | $0.10 | $0.70 |
91
97
  | `digitalocean/openai-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.45 |
92
98
  | `digitalocean/openai-o1` | 200K | | | | | | $15 | $60 |
93
99
  | `digitalocean/openai-o3` | 200K | | | | | | $2 | $8 |
94
100
  | `digitalocean/openai-o3-mini` | 200K | | | | | | $1 | $4 |
101
+ | `digitalocean/qwen-2.5-14b-instruct` | 131K | | | | | | — | — |
95
102
  | `digitalocean/qwen3-coder-flash` | 262K | | | | | | $0.45 | $2 |
96
103
  | `digitalocean/qwen3-embedding-0.6b` | 8K | | | | | | $0.04 | — |
97
104
  | `digitalocean/qwen3-tts-voicedesign` | 33K | | | | | | — | — |
package/.docs/models/providers/firepass.md ADDED
@@ -0,0 +1,71 @@
1
+ # ![Fireworks (Firepass) logo](https://models.dev/logos/firepass.svg)Fireworks (Firepass)
2
+
3
+ Access 1 Fireworks (Firepass) model through Mastra's model router. Authentication is handled automatically using the `FIREPASS_API_KEY` environment variable.
4
+
5
+ Learn more in the [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass).
6
+
7
+ ```bash
8
+ FIREPASS_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: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
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 [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass) for details.
32
+
33
+ ## Models
34
+
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | ----------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `firepass/accounts/fireworks/routers/kimi-k2p6-turbo` | 262K | | | | | | — | — |
38
+
39
+ ## Advanced configuration
40
+
41
+ ### Custom headers
42
+
43
+ ```typescript
44
+ const agent = new Agent({
45
+ id: "custom-agent",
46
+ name: "custom-agent",
47
+ model: {
48
+ url: "https://api.fireworks.ai/inference/v1/",
49
+ id: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo",
50
+ apiKey: process.env.FIREPASS_API_KEY,
51
+ headers: {
52
+ "X-Custom-Header": "value"
53
+ }
54
+ }
55
+ });
56
+ ```
57
+
58
+ ### Dynamic model selection
59
+
60
+ ```typescript
61
+ const agent = new Agent({
62
+ id: "dynamic-agent",
63
+ name: "Dynamic Agent",
64
+ model: ({ requestContext }) => {
65
+ const useAdvanced = requestContext.task === "complex";
66
+ return useAdvanced
67
+ ? "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
68
+ : "firepass/accounts/fireworks/routers/kimi-k2p6-turbo";
69
+ }
70
+ });
71
+ ```
package/.docs/models/providers/google.md CHANGED
@@ -1,8 +1,8 @@
1
1
  # ![Google logo](https://models.dev/logos/google.svg)Google
2
2
 
3
- Access 37 Google models through Mastra's model router. Authentication is handled automatically using the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable.
3
+ Access 38 Google models through Mastra's model router. Authentication is handled automatically using the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable.
4
4
 
5
- Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/pricing).
5
+ Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
6
6
 
7
7
  ```bash
8
8
  GOOGLE_GENERATIVE_AI_API_KEY=your-api-key
@@ -54,6 +54,7 @@ for await (const chunk of stream) {
54
54
  | `google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
55
55
  | `google/gemini-3-pro-preview` | 1.0M | | | | | | $2 | $12 |
56
56
  | `google/gemini-3.1-flash-image-preview` | 131K | | | | | | $0.25 | $60 |
57
+ | `google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
57
58
  | `google/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
58
59
  | `google/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
59
60
  | `google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
package/.docs/models/providers/kilo.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
2
2
 
3
- Access 355 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
3
+ Access 357 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Kilo Gateway documentation](https://kilo.ai).
6
6
 
@@ -50,7 +50,6 @@ for await (const chunk of stream) {
50
50
  | `kilo/alfredpros/codellama-7b-instruct-solidity` | 4K | | | | | | $0.80 | $1 |
51
51
  | `kilo/alibaba/tongyi-deepresearch-30b-a3b` | 131K | | | | | | $0.09 | $0.45 |
52
52
  | `kilo/allenai/olmo-3-32b-think` | 66K | | | | | | $0.15 | $0.50 |
53
- | `kilo/allenai/olmo-3.1-32b-instruct` | 66K | | | | | | $0.20 | $0.60 |
54
53
  | `kilo/alpindale/goliath-120b` | 6K | | | | | | $4 | $8 |
55
54
  | `kilo/amazon/nova-2-lite-v1` | 1.0M | | | | | | $0.30 | $3 |
56
55
  | `kilo/amazon/nova-lite-v1` | 300K | | | | | | $0.06 | $0.24 |
@@ -79,6 +78,7 @@ for await (const chunk of stream) {
79
78
  | `kilo/arcee-ai/trinity-large-thinking` | 262K | | | | | | $0.22 | $0.85 |
80
79
  | `kilo/arcee-ai/trinity-mini` | 131K | | | | | | $0.04 | $0.15 |
81
80
  | `kilo/arcee-ai/virtuoso-large` | 131K | | | | | | $0.75 | $1 |
81
+ | `kilo/baidu/cobuddy:free` | 131K | | | | | | — | — |
82
82
  | `kilo/baidu/ernie-4.5-21b-a3b` | 120K | | | | | | $0.07 | $0.28 |
83
83
  | `kilo/baidu/ernie-4.5-21b-a3b-thinking` | 131K | | | | | | $0.07 | $0.28 |
84
84
  | `kilo/baidu/ernie-4.5-300b-a47b` | 123K | | | | | | $0.28 | $1 |
@@ -161,6 +161,7 @@ for await (const chunk of stream) {
161
161
  | `kilo/meta-llama/llama-guard-3-8b` | 131K | | | | | | $0.02 | $0.06 |
162
162
  | `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
163
163
  | `kilo/microsoft/phi-4` | 16K | | | | | | $0.06 | $0.14 |
164
+ | `kilo/microsoft/phi-4-mini-instruct` | 128K | | | | | | $0.08 | $0.35 |
164
165
  | `kilo/microsoft/wizardlm-2-8x22b` | 66K | | | | | | $0.62 | $0.62 |
165
166
  | `kilo/minimax/minimax-01` | 1.0M | | | | | | $0.20 | $1 |
166
167
  | `kilo/minimax/minimax-m1` | 1.0M | | | | | | $0.40 | $2 |
@@ -182,6 +183,7 @@ for await (const chunk of stream) {
182
183
  | `kilo/mistralai/mistral-large-2411` | 131K | | | | | | $2 | $6 |
183
184
  | `kilo/mistralai/mistral-large-2512` | 262K | | | | | | $0.50 | $2 |
184
185
  | `kilo/mistralai/mistral-medium-3` | 131K | | | | | | $0.40 | $2 |
186
+ | `kilo/mistralai/mistral-medium-3-5` | 262K | | | | | | $2 | $8 |
185
187
  | `kilo/mistralai/mistral-medium-3.1` | 131K | | | | | | $0.40 | $2 |
186
188
  | `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.02 | $0.04 |
187
189
  | `kilo/mistralai/mistral-saba` | 33K | | | | | | $0.20 | $0.60 |
@@ -212,7 +214,6 @@ for await (const chunk of stream) {
212
214
  | `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
213
215
  | `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.10 | $0.50 |
214
216
  | `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
215
- | `kilo/nvidia/nemotron-nano-12b-v2-vl` | 131K | | | | | | $0.20 | $0.60 |
216
217
  | `kilo/nvidia/nemotron-nano-9b-v2` | 131K | | | | | | $0.04 | $0.16 |
217
218
  | `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
218
219
  | `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
@@ -263,6 +264,7 @@ for await (const chunk of stream) {
263
264
  | `kilo/openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
264
265
  | `kilo/openai/gpt-audio` | 128K | | | | | | $3 | $10 |
265
266
  | `kilo/openai/gpt-audio-mini` | 128K | | | | | | $0.60 | $2 |
267
+ | `kilo/openai/gpt-chat-latest` | 400K | | | | | | $5 | $30 |
266
268
  | `kilo/openai/gpt-oss-120b` | 131K | | | | | | $0.04 | $0.19 |
267
269
  | `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.03 | $0.14 |
268
270
  | `kilo/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
package/.docs/models/providers/llmgateway.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway.svg)LLM Gateway
2
2
 
3
- Access 189 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
3
+ Access 195 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
6
6
 
@@ -66,6 +66,7 @@ for await (const chunk of stream) {
66
66
  | `llmgateway/gemini-2.5-flash-lite-preview-09-2025` | 1.0M | | | | | | $0.10 | $0.40 |
67
67
  | `llmgateway/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
68
68
  | `llmgateway/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
69
+ | `llmgateway/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
69
70
  | `llmgateway/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
70
71
  | `llmgateway/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
71
72
  | `llmgateway/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
@@ -132,6 +133,7 @@ for await (const chunk of stream) {
132
133
  | `llmgateway/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
133
134
  | `llmgateway/grok-4-20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
134
135
  | `llmgateway/grok-4-20-beta-0309-reasoning` | 2.0M | | | | | | $2 | $6 |
136
+ | `llmgateway/grok-4-3` | 1.0M | | | | | | $1 | $3 |
135
137
  | `llmgateway/grok-4-fast` | 2.0M | | | | | | $0.20 | $0.50 |
136
138
  | `llmgateway/grok-4-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
137
139
  | `llmgateway/grok-4-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
@@ -154,6 +156,10 @@ for await (const chunk of stream) {
154
156
  | `llmgateway/llama-4-scout` | 33K | | | | | | $0.18 | $0.59 |
155
157
  | `llmgateway/llama-4-scout-17b-instruct` | 8K | | | | | | $0.17 | $0.66 |
156
158
  | `llmgateway/mimo-v2-flash` | 262K | | | | | | $0.10 | $0.30 |
159
+ | `llmgateway/mimo-v2-omni` | 262K | | | | | | $0.40 | $2 |
160
+ | `llmgateway/mimo-v2-pro` | 1.0M | | | | | | $1 | $3 |
161
+ | `llmgateway/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
162
+ | `llmgateway/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
157
163
  | `llmgateway/minimax-m2` | 197K | | | | | | $0.30 | $1 |
158
164
  | `llmgateway/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
159
165
  | `llmgateway/minimax-m2.1-lightning` | 197K | | | | | | $0.12 | $0.48 |
package/.docs/models/providers/nebius.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Nebius Token Factory logo](https://models.dev/logos/nebius.svg)Nebius Token Factory
2
2
 
3
- Access 49 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
3
+ Access 31 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/).
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: "nebius/BAAI/bge-en-icl"
18
+ model: "nebius/MiniMaxAI/MiniMax-M2.5"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -32,57 +32,39 @@ 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
- | `nebius/BAAI/bge-en-icl` | 33K | | | | | | $0.01 | — |
38
- | `nebius/BAAI/bge-multilingual-gemma2` | 8K | | | | | | $0.01 | — |
39
- | `nebius/black-forest-labs/flux-dev` | 77 | | | | | | — | — |
40
- | `nebius/black-forest-labs/flux-schnell` | 77 | | | | | | — | — |
41
- | `nebius/deepseek-ai/DeepSeek-R1-0528` | 128K | | | | | | $0.80 | $2 |
42
- | `nebius/deepseek-ai/DeepSeek-R1-0528-fast` | 131K | | | | | | $2 | $6 |
43
- | `nebius/deepseek-ai/DeepSeek-V3-0324` | 128K | | | | | | $0.50 | $2 |
44
- | `nebius/deepseek-ai/DeepSeek-V3-0324-fast` | 128K | | | | | | $0.75 | $2 |
45
- | `nebius/deepseek-ai/DeepSeek-V3.2` | 163K | | | | | | $0.30 | $0.45 |
46
- | `nebius/google/gemma-2-2b-it` | 8K | | | | | | $0.02 | $0.06 |
47
- | `nebius/google/gemma-2-9b-it-fast` | 8K | | | | | | $0.03 | $0.09 |
48
- | `nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
49
- | `nebius/google/gemma-3-27b-it-fast` | 110K | | | | | | $0.20 | $0.60 |
50
- | `nebius/intfloat/e5-mistral-7b-instruct` | 33K | | | | | | $0.01 | — |
51
- | `nebius/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.13 | $0.40 |
52
- | `nebius/meta-llama/Llama-3.3-70B-Instruct-fast` | 128K | | | | | | $0.25 | $0.75 |
53
- | `nebius/meta-llama/Llama-Guard-3-8B` | 8K | | | | | | $0.02 | $0.06 |
54
- | `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct` | 128K | | | | | | $0.02 | $0.06 |
55
- | `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct-fast` | 128K | | | | | | $0.03 | $0.09 |
56
- | `nebius/MiniMaxAI/MiniMax-M2.1` | 128K | | | | | | $0.30 | $1 |
57
- | `nebius/moonshotai/Kimi-K2-Instruct` | 200K | | | | | | $0.50 | $2 |
58
- | `nebius/moonshotai/Kimi-K2-Thinking` | 128K | | | | | | $0.60 | $3 |
59
- | `nebius/moonshotai/Kimi-K2.5` | 256K | | | | | | $0.50 | $3 |
60
- | `nebius/moonshotai/Kimi-K2.5-fast` | 256K | | | | | | $0.50 | $3 |
61
- | `nebius/NousResearch/Hermes-4-405B` | 128K | | | | | | $1 | $3 |
62
- | `nebius/NousResearch/Hermes-4-70B` | 128K | | | | | | $0.13 | $0.40 |
63
- | `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1` | 128K | | | | | | $0.60 | $2 |
64
- | `nebius/nvidia/nemotron-3-super-120b-a12b` | 256K | | | | | | $0.30 | $0.90 |
65
- | `nebius/nvidia/Nemotron-Nano-V2-12b` | 32K | | | | | | $0.07 | $0.20 |
66
- | `nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B` | 32K | | | | | | $0.06 | $0.24 |
67
- | `nebius/openai/gpt-oss-120b` | 128K | | | | | | $0.15 | $0.60 |
68
- | `nebius/openai/gpt-oss-20b` | 128K | | | | | | $0.05 | $0.20 |
69
- | `nebius/PrimeIntellect/INTELLECT-3` | 128K | | | | | | $0.20 | $1 |
70
- | `nebius/Qwen/Qwen2.5-Coder-7B-fast` | 128K | | | | | | $0.03 | $0.09 |
71
- | `nebius/Qwen/Qwen2.5-VL-72B-Instruct` | 128K | | | | | | $0.25 | $0.75 |
72
- | `nebius/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.20 | $0.60 |
73
- | `nebius/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.20 | $0.80 |
74
- | `nebius/Qwen/Qwen3-30B-A3B-Instruct-2507` | 128K | | | | | | $0.10 | $0.30 |
75
- | `nebius/Qwen/Qwen3-30B-A3B-Thinking-2507` | 128K | | | | | | $0.10 | $0.30 |
76
- | `nebius/Qwen/Qwen3-32B` | 128K | | | | | | $0.10 | $0.30 |
77
- | `nebius/Qwen/Qwen3-32B-fast` | 128K | | | | | | $0.20 | $0.60 |
78
- | `nebius/Qwen/Qwen3-Coder-30B-A3B-Instruct` | 128K | | | | | | $0.10 | $0.30 |
79
- | `nebius/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $0.40 | $2 |
80
- | `nebius/Qwen/Qwen3-Embedding-8B` | 33K | | | | | | $0.01 | — |
81
- | `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking` | 128K | | | | | | $0.15 | $1 |
82
- | `nebius/zai-org/GLM-4.5` | 128K | | | | | | $0.60 | $2 |
83
- | `nebius/zai-org/GLM-4.5-Air` | 128K | | | | | | $0.20 | $1 |
84
- | `nebius/zai-org/GLM-4.7-FP8` | 128K | | | | | | $0.40 | $2 |
85
- | `nebius/zai-org/GLM-5` | 200K | | | | | | $1 | $3 |
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | ------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `nebius/deepseek-ai/DeepSeek-V3.2` | 163K | | | | | | $0.30 | $0.45 |
38
+ | `nebius/deepseek-ai/DeepSeek-V3.2-fast` | 8K | | | | | | $0.40 | $2 |
39
+ | `nebius/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $4 |
40
+ | `nebius/google/gemma-2-2b-it` | 8K | | | | | | $0.02 | $0.06 |
41
+ | `nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
42
+ | `nebius/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.13 | $0.40 |
43
+ | `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct` | 128K | | | | | | $0.02 | $0.06 |
44
+ | `nebius/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.30 | $1 |
45
+ | `nebius/MiniMaxAI/MiniMax-M2.5-fast` | 8K | | | | | | $0.30 | $1 |
46
+ | `nebius/moonshotai/Kimi-K2.5` | 256K | | | | | | $0.50 | $3 |
47
+ | `nebius/moonshotai/Kimi-K2.5-fast` | 256K | | | | | | $0.50 | $3 |
48
+ | `nebius/NousResearch/Hermes-4-405B` | 128K | | | | | | $1 | $3 |
49
+ | `nebius/NousResearch/Hermes-4-70B` | 128K | | | | | | $0.13 | $0.40 |
50
+ | `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1` | 128K | | | | | | $0.60 | $2 |
51
+ | `nebius/nvidia/Nemotron-3-Nano-Omni` | 66K | | | | | | $0.06 | $0.24 |
52
+ | `nebius/nvidia/nemotron-3-super-120b-a12b` | 256K | | | | | | $0.30 | $0.90 |
53
+ | `nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B` | 32K | | | | | | $0.06 | $0.24 |
54
+ | `nebius/openai/gpt-oss-120b` | 128K | | | | | | $0.15 | $0.60 |
55
+ | `nebius/openai/gpt-oss-120b-fast` | 8K | | | | | | $0.10 | $0.50 |
56
+ | `nebius/PrimeIntellect/INTELLECT-3` | 128K | | | | | | $0.20 | $1 |
57
+ | `nebius/Qwen/Qwen2.5-VL-72B-Instruct` | 128K | | | | | | $0.25 | $0.75 |
58
+ | `nebius/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.20 | $0.60 |
59
+ | `nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast` | 8K | | | | | | $0.50 | $2 |
60
+ | `nebius/Qwen/Qwen3-30B-A3B-Instruct-2507` | 128K | | | | | | $0.10 | $0.30 |
61
+ | `nebius/Qwen/Qwen3-32B` | 128K | | | | | | $0.10 | $0.30 |
62
+ | `nebius/Qwen/Qwen3-Embedding-8B` | 33K | | | | | | $0.01 | — |
63
+ | `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking` | 128K | | | | | | $0.15 | $1 |
64
+ | `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast` | 8K | | | | | | $0.15 | $1 |
65
+ | `nebius/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
66
+ | `nebius/Qwen/Qwen3.5-397B-A17B-fast` | 8K | | | | | | $0.60 | $4 |
67
+ | `nebius/zai-org/GLM-5` | 200K | | | | | | $1 | $3 |
86
68
 
87
69
  ## Advanced configuration
88
70
 
@@ -94,7 +76,7 @@ const agent = new Agent({
94
76
  name: "custom-agent",
95
77
  model: {
96
78
  url: "https://api.tokenfactory.nebius.com/v1",
97
- id: "nebius/BAAI/bge-en-icl",
79
+ id: "nebius/MiniMaxAI/MiniMax-M2.5",
98
80
  apiKey: process.env.NEBIUS_API_KEY,
99
81
  headers: {
100
82
  "X-Custom-Header": "value"
@@ -113,7 +95,7 @@ const agent = new Agent({
113
95
  const useAdvanced = requestContext.task === "complex";
114
96
  return useAdvanced
115
97
  ? "nebius/zai-org/GLM-5"
116
- : "nebius/BAAI/bge-en-icl";
98
+ : "nebius/MiniMaxAI/MiniMax-M2.5";
117
99
  }
118
100
  });
119
101
  ```
package/.docs/models/providers/novita-ai.md CHANGED
@@ -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: "novita-ai/baichuan/baichuan-m2-32b"
18
+ model: "novita-ai/Sao10K/L3-8B-Stheno-v3.2"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -64,6 +64,7 @@ for await (const chunk of stream) {
64
64
  | `novita-ai/google/gemma-4-31b-it` | 262K | | | | | | $0.14 | $0.40 |
65
65
  | `novita-ai/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.09 | $0.09 |
66
66
  | `novita-ai/inclusionai/ling-2.6-1t` | 262K | | | | | | — | — |
67
+ | `novita-ai/inclusionai/ling-2.6-flash` | 262K | | | | | | $0.10 | $0.30 |
67
68
  | `novita-ai/kwaipilot/kat-coder-pro` | 256K | | | | | | $0.30 | $1 |
68
69
  | `novita-ai/meta-llama/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
69
70
  | `novita-ai/meta-llama/llama-3-8b-instruct` | 8K | | | | | | $0.04 | $0.04 |
@@ -117,10 +118,9 @@ for await (const chunk of stream) {
117
118
  | `novita-ai/qwen/qwen3.5-27b` | 262K | | | | | | $0.30 | $2 |
118
119
  | `novita-ai/qwen/qwen3.5-35b-a3b` | 262K | | | | | | $0.25 | $2 |
119
120
  | `novita-ai/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.60 | $4 |
120
- | `novita-ai/qwen/qwen3.6-27b` | 262K | | | | | | $0.60 | $4 |
121
121
  | `novita-ai/sao10k/l3-70b-euryale-v2.1` | 8K | | | | | | $1 | $1 |
122
122
  | `novita-ai/sao10k/l3-8b-lunaris` | 8K | | | | | | $0.05 | $0.05 |
123
- | `novita-ai/sao10k/L3-8B-Stheno-v3.2` | 8K | | | | | | $0.05 | $0.05 |
123
+ | `novita-ai/Sao10K/L3-8B-Stheno-v3.2` | 8K | | | | | | $0.05 | $0.05 |
124
124
  | `novita-ai/sao10k/l31-70b-euryale-v2.2` | 8K | | | | | | $1 | $1 |
125
125
  | `novita-ai/xiaomimimo/mimo-v2-flash` | 262K | | | | | | $0.10 | $0.30 |
126
126
  | `novita-ai/zai-org/autoglm-phone-9b-multilingual` | 66K | | | | | | $0.04 | $0.14 |
@@ -144,7 +144,7 @@ const agent = new Agent({
144
144
  name: "custom-agent",
145
145
  model: {
146
146
  url: "https://api.novita.ai/openai",
147
- id: "novita-ai/baichuan/baichuan-m2-32b",
147
+ id: "novita-ai/Sao10K/L3-8B-Stheno-v3.2",
148
148
  apiKey: process.env.NOVITA_API_KEY,
149
149
  headers: {
150
150
  "X-Custom-Header": "value"
@@ -163,7 +163,7 @@ const agent = new Agent({
163
163
  const useAdvanced = requestContext.task === "complex";
164
164
  return useAdvanced
165
165
  ? "novita-ai/zai-org/glm-5.1"
166
- : "novita-ai/baichuan/baichuan-m2-32b";
166
+ : "novita-ai/Sao10K/L3-8B-Stheno-v3.2";
167
167
  }
168
168
  });
169
169
  ```