@mastra/mcp-docs-server 1.1.26-alpha.2 → 1.1.26-alpha.22

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 (60) hide show
  1. package/.docs/docs/agents/supervisor-agents.md +18 -0
  2. package/.docs/docs/editor/overview.md +69 -0
  3. package/.docs/docs/mastra-platform/overview.md +3 -1
  4. package/.docs/docs/memory/observational-memory.md +27 -7
  5. package/.docs/docs/observability/tracing/exporters/cloud.md +34 -41
  6. package/.docs/docs/observability/tracing/exporters/langfuse.md +31 -0
  7. package/.docs/guides/build-your-ui/ai-sdk-ui.md +19 -6
  8. package/.docs/guides/deployment/netlify.md +16 -1
  9. package/.docs/guides/getting-started/next-js.md +0 -4
  10. package/.docs/guides/migrations/mastra-cloud.md +128 -3
  11. package/.docs/models/gateways/netlify.md +2 -2
  12. package/.docs/models/gateways/openrouter.md +3 -1
  13. package/.docs/models/gateways/vercel.md +4 -1
  14. package/.docs/models/index.md +36 -1
  15. package/.docs/models/providers/302ai.md +32 -1
  16. package/.docs/models/providers/alibaba-cn.md +2 -1
  17. package/.docs/models/providers/anthropic.md +2 -1
  18. package/.docs/models/providers/berget.md +9 -12
  19. package/.docs/models/providers/cloudflare-workers-ai.md +2 -1
  20. package/.docs/models/providers/cortecs.md +4 -1
  21. package/.docs/models/providers/digitalocean.md +116 -0
  22. package/.docs/models/providers/firmware.md +2 -3
  23. package/.docs/models/providers/helicone.md +1 -2
  24. package/.docs/models/providers/hpc-ai.md +73 -0
  25. package/.docs/models/providers/huggingface.md +2 -1
  26. package/.docs/models/providers/kimi-for-coding.md +2 -1
  27. package/.docs/models/providers/llmgateway.md +59 -77
  28. package/.docs/models/providers/moonshotai.md +3 -2
  29. package/.docs/models/providers/nvidia.md +3 -2
  30. package/.docs/models/providers/ollama-cloud.md +2 -1
  31. package/.docs/models/providers/openai.md +1 -2
  32. package/.docs/models/providers/opencode-go.md +2 -1
  33. package/.docs/models/providers/opencode.md +4 -1
  34. package/.docs/models/providers/ovhcloud.md +4 -7
  35. package/.docs/models/providers/poe.md +2 -1
  36. package/.docs/models/providers/tencent-token-plan.md +71 -0
  37. package/.docs/models/providers/tencent-tokenhub.md +71 -0
  38. package/.docs/models/providers/wafer.ai.md +72 -0
  39. package/.docs/models/providers/zenmux.md +2 -1
  40. package/.docs/models/providers.md +5 -0
  41. package/.docs/reference/agents/generate.md +8 -0
  42. package/.docs/reference/client-js/mastra-client.md +23 -0
  43. package/.docs/reference/client-js/workflows.md +12 -0
  44. package/.docs/reference/core/mastra-class.md +9 -1
  45. package/.docs/reference/deployer/cloudflare.md +14 -1
  46. package/.docs/reference/deployer/netlify.md +50 -2
  47. package/.docs/reference/harness/harness-class.md +72 -49
  48. package/.docs/reference/index.md +1 -0
  49. package/.docs/reference/memory/observational-memory.md +2 -0
  50. package/.docs/reference/observability/tracing/exporters/cloud-exporter.md +4 -2
  51. package/.docs/reference/observability/tracing/exporters/langfuse.md +2 -0
  52. package/.docs/reference/processors/prefill-error-handler.md +5 -5
  53. package/.docs/reference/storage/cloudflare-d1.md +42 -42
  54. package/.docs/reference/streaming/agents/stream.md +8 -0
  55. package/.docs/reference/streaming/workflows/resumeStream.md +2 -0
  56. package/.docs/reference/workflows/run-methods/resume.md +24 -0
  57. package/.docs/reference/workflows/workflow-methods/foreach.md +14 -1
  58. package/.docs/reference/workspace/docker-sandbox.md +196 -0
  59. package/CHANGELOG.md +72 -0
  60. package/package.json +9 -9
package/.docs/models/gateways/vercel.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
2
2
 
3
- Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 231 models through Mastra's model router.
3
+ Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 234 models through Mastra's model router.
4
4
 
5
5
  Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
6
6
 
@@ -72,6 +72,7 @@ ANTHROPIC_API_KEY=ant-...
72
72
  | `anthropic/claude-opus-4.1` |
73
73
  | `anthropic/claude-opus-4.5` |
74
74
  | `anthropic/claude-opus-4.6` |
75
+ | `anthropic/claude-opus-4.7` |
75
76
  | `anthropic/claude-sonnet-4` |
76
77
  | `anthropic/claude-sonnet-4.5` |
77
78
  | `anthropic/claude-sonnet-4.6` |
@@ -119,6 +120,7 @@ ANTHROPIC_API_KEY=ant-...
119
120
  | `google/text-embedding-005` |
120
121
  | `google/text-multilingual-embedding-002` |
121
122
  | `inception/mercury-2` |
123
+ | `inception/mercury-coder-small` |
122
124
  | `inception/mercury-edit-2` |
123
125
  | `kwaipilot/kat-coder-pro-v1` |
124
126
  | `kwaipilot/kat-coder-pro-v2` |
@@ -264,4 +266,5 @@ ANTHROPIC_API_KEY=ant-...
264
266
  | `zai/glm-4.7-flashx` |
265
267
  | `zai/glm-5` |
266
268
  | `zai/glm-5-turbo` |
269
+ | `zai/glm-5.1` |
267
270
  | `zai/glm-5v-turbo` |
package/.docs/models/index.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Model Providers
2
2
 
3
- Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3596 models from 99 providers through a single API.
3
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3675 models from 104 providers through a single API.
4
4
 
5
5
  ## Features
6
6
 
@@ -228,6 +228,41 @@ Mastra tries your primary model first. If it encounters a 500 error, rate limit,
228
228
 
229
229
  Your users never experience the disruption - the response comes back with the same format, just from a different model. The error context is preserved as the system moves through your fallback chain, ensuring clean error propagation while maintaining streaming compatibility.
230
230
 
231
+ ### Per-model settings
232
+
233
+ Each fallback entry can carry its own `modelSettings`, `providerOptions`, and `headers` — useful when models in the chain need different temperatures or provider-specific knobs to produce comparable output.
234
+
235
+ ```typescript
236
+ import { Agent } from '@mastra/core/agent';
237
+
238
+ const agent = new Agent({
239
+ id: 'tuned-resilient',
240
+ name: 'Tuned Resilient Agent',
241
+ instructions: 'You are a helpful assistant.',
242
+ model: [
243
+ {
244
+ model: 'google/gemini-2.5-flash',
245
+ maxRetries: 2,
246
+ modelSettings: { temperature: 0.3 },
247
+ providerOptions: { google: { thinkingConfig: { thinkingBudget: 0 } } },
248
+ },
249
+ {
250
+ model: 'openai/gpt-5-mini',
251
+ maxRetries: 2,
252
+ modelSettings: { temperature: 0.7 },
253
+ providerOptions: { openai: { reasoningEffort: 'low' } },
254
+ },
255
+ ],
256
+ });
257
+ ```
258
+
259
+ **Precedence:**
260
+
261
+ - `modelSettings` and `providerOptions`: per-fallback entry overrides call-time options, which override agent `defaultOptions`. `modelSettings` shallow-merges by key. `providerOptions` deep-merges recursively, so nested provider config (e.g. `google.thinkingConfig`) preserves sibling keys across layers.
262
+ - `headers`: call-time `modelSettings.headers` overrides per-fallback `headers`, which overrides headers extracted from model-router models. Runtime headers (tracing, auth, tenancy) intentionally take precedence over model-level headers.
263
+
264
+ Each field also accepts a function of `requestContext`, matching how dynamic models are resolved.
265
+
231
266
  ## Use local models with Mastra
232
267
 
233
268
  Mastra also supports local models like `gpt-oss`, `Qwen3`, `DeepSeek` and many more that you run on your own hardware. The application running your local model needs to provide an OpenAI-compatible API server for Mastra to connect to. We recommend using [LMStudio](https://lmstudio.ai/) (see [Running the LMStudio server](https://lmstudio.ai/docs/developer/core/server)).
package/.docs/models/providers/302ai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![302.AI logo](https://models.dev/logos/302ai.svg)302.AI
2
2
 
3
- Access 64 302.AI models through Mastra's model router. Authentication is handled automatically using the `302AI_API_KEY` environment variable.
3
+ Access 95 302.AI models through Mastra's model router. Authentication is handled automatically using the `302AI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [302.AI documentation](https://doc.302.ai).
6
6
 
@@ -35,13 +35,25 @@ for await (const chunk of stream) {
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
37
  | `302ai/chatgpt-4o-latest` | 128K | | | | | | $5 | $15 |
38
+ | `302ai/claude-3-5-haiku-20241022` | 200K | | | | | | $0.80 | $4 |
39
+ | `302ai/claude-3-5-haiku-latest` | 200K | | | | | | $0.80 | $4 |
40
+ | `302ai/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
38
41
  | `302ai/claude-haiku-4-5-20251001` | 200K | | | | | | $1 | $5 |
39
42
  | `302ai/claude-opus-4-1-20250805` | 200K | | | | | | $15 | $75 |
40
43
  | `302ai/claude-opus-4-1-20250805-thinking` | 200K | | | | | | $15 | $75 |
44
+ | `302ai/claude-opus-4-20250514` | 200K | | | | | | $15 | $75 |
45
+ | `302ai/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
46
  | `302ai/claude-opus-4-5-20251101` | 200K | | | | | | $5 | $25 |
42
47
  | `302ai/claude-opus-4-5-20251101-thinking` | 200K | | | | | | $5 | $25 |
48
+ | `302ai/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
49
+ | `302ai/claude-opus-4-6-thinking` | 1.0M | | | | | | $5 | $25 |
50
+ | `302ai/claude-opus-4-7` | 200K | | | | | | $5 | $25 |
51
+ | `302ai/claude-sonnet-4-20250514` | 200K | | | | | | $3 | $15 |
52
+ | `302ai/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
43
53
  | `302ai/claude-sonnet-4-5-20250929` | 200K | | | | | | $3 | $15 |
44
54
  | `302ai/claude-sonnet-4-5-20250929-thinking` | 200K | | | | | | $3 | $15 |
55
+ | `302ai/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
56
+ | `302ai/claude-sonnet-4-6-thinking` | 1.0M | | | | | | $3 | $15 |
45
57
  | `302ai/deepseek-chat` | 128K | | | | | | $0.29 | $0.43 |
46
58
  | `302ai/deepseek-reasoner` | 128K | | | | | | $0.29 | $0.43 |
47
59
  | `302ai/deepseek-v3.2` | 128K | | | | | | $0.29 | $0.43 |
@@ -60,11 +72,21 @@ for await (const chunk of stream) {
60
72
  | `302ai/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
61
73
  | `302ai/gemini-3-pro-image-preview` | 33K | | | | | | $2 | $120 |
62
74
  | `302ai/gemini-3-pro-preview` | 1.0M | | | | | | $2 | $12 |
75
+ | `302ai/gemini-3.1-flash-image-preview` | 131K | | | | | | $0.50 | $60 |
63
76
  | `302ai/glm-4.5` | 128K | | | | | | $0.29 | $1 |
77
+ | `302ai/glm-4.5-air` | 128K | | | | | | $0.11 | $0.29 |
78
+ | `302ai/glm-4.5-airx` | 128K | | | | | | $0.57 | $2 |
79
+ | `302ai/glm-4.5-x` | 128K | | | | | | $1 | $2 |
64
80
  | `302ai/glm-4.5v` | 64K | | | | | | $0.29 | $0.86 |
65
81
  | `302ai/glm-4.6` | 200K | | | | | | $0.29 | $1 |
66
82
  | `302ai/glm-4.6v` | 128K | | | | | | $0.14 | $0.43 |
67
83
  | `302ai/glm-4.7` | 200K | | | | | | $0.29 | $1 |
84
+ | `302ai/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.43 |
85
+ | `302ai/glm-5` | 200K | | | | | | $0.60 | $3 |
86
+ | `302ai/glm-5-turbo` | 200K | | | | | | $0.72 | $3 |
87
+ | `302ai/glm-5.1` | 200K | | | | | | $0.86 | $4 |
88
+ | `302ai/glm-5v-turbo` | 200K | | | | | | $0.72 | $3 |
89
+ | `302ai/glm-for-coding` | 200K | | | | | | $0.09 | $0.34 |
68
90
  | `302ai/gpt-4.1` | 1.0M | | | | | | $2 | $8 |
69
91
  | `302ai/gpt-4.1-mini` | 1.0M | | | | | | $0.40 | $2 |
70
92
  | `302ai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
@@ -77,17 +99,26 @@ for await (const chunk of stream) {
77
99
  | `302ai/gpt-5.1-chat-latest` | 128K | | | | | | $1 | $10 |
78
100
  | `302ai/gpt-5.2` | 400K | | | | | | $2 | $14 |
79
101
  | `302ai/gpt-5.2-chat-latest` | 128K | | | | | | $2 | $14 |
102
+ | `302ai/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
103
+ | `302ai/gpt-5.4-mini-2026-03-17` | 400K | | | | | | $0.75 | $5 |
104
+ | `302ai/gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
105
+ | `302ai/gpt-5.4-nano-2026-03-17` | 400K | | | | | | $0.20 | $1 |
80
106
  | `302ai/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
81
107
  | `302ai/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
82
108
  | `302ai/grok-4-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
83
109
  | `302ai/grok-4-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
84
110
  | `302ai/grok-4.1` | 200K | | | | | | $2 | $10 |
111
+ | `302ai/grok-4.20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
112
+ | `302ai/grok-4.20-beta-0309-reasoning` | 2.0M | | | | | | $2 | $6 |
113
+ | `302ai/grok-4.20-multi-agent-beta-0309` | 2.0M | | | | | | $2 | $6 |
85
114
  | `302ai/kimi-k2-0905-preview` | 262K | | | | | | $0.63 | $3 |
86
115
  | `302ai/kimi-k2-thinking` | 262K | | | | | | $0.57 | $2 |
87
116
  | `302ai/kimi-k2-thinking-turbo` | 262K | | | | | | $1 | $9 |
88
117
  | `302ai/MiniMax-M1` | 1.0M | | | | | | $0.13 | $1 |
89
118
  | `302ai/MiniMax-M2` | 1.0M | | | | | | $0.33 | $1 |
90
119
  | `302ai/MiniMax-M2.1` | 1.0M | | | | | | $0.30 | $1 |
120
+ | `302ai/MiniMax-M2.7` | 205K | | | | | | $0.30 | $1 |
121
+ | `302ai/MiniMax-M2.7-highspeed` | 205K | | | | | | $0.60 | $5 |
91
122
  | `302ai/ministral-14b-2512` | 128K | | | | | | $0.33 | $0.33 |
92
123
  | `302ai/mistral-large-2512` | 128K | | | | | | $1 | $3 |
93
124
  | `302ai/qwen-flash` | 1.0M | | | | | | $0.02 | $0.22 |
package/.docs/models/providers/alibaba-cn.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Alibaba (China) logo](https://models.dev/logos/alibaba-cn.svg)Alibaba (China)
2
2
 
3
- Access 75 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
3
+ Access 76 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Alibaba (China) documentation](https://www.alibabacloud.com/help/en/model-studio/models).
6
6
 
@@ -46,6 +46,7 @@ for await (const chunk of stream) {
46
46
  | `alibaba-cn/deepseek-v3-1` | 131K | | | | | | $0.57 | $2 |
47
47
  | `alibaba-cn/deepseek-v3-2-exp` | 131K | | | | | | $0.29 | $0.43 |
48
48
  | `alibaba-cn/glm-5` | 203K | | | | | | $0.86 | $3 |
49
+ | `alibaba-cn/glm-5.1` | 203K | | | | | | $0.87 | $3 |
49
50
  | `alibaba-cn/kimi-k2-thinking` | 262K | | | | | | $0.57 | $2 |
50
51
  | `alibaba-cn/kimi-k2.5` | 262K | | | | | | $0.57 | $2 |
51
52
  | `alibaba-cn/kimi/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
package/.docs/models/providers/anthropic.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Anthropic logo](https://models.dev/logos/anthropic.svg)Anthropic
2
2
 
3
- Access 22 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
3
+ Access 23 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
6
6
 
@@ -49,6 +49,7 @@ for await (const chunk of stream) {
49
49
  | `anthropic/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
50
50
  | `anthropic/claude-opus-4-5-20251101` | 200K | | | | | | $5 | $25 |
51
51
  | `anthropic/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
52
+ | `anthropic/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
52
53
  | `anthropic/claude-sonnet-4-0` | 200K | | | | | | $3 | $15 |
53
54
  | `anthropic/claude-sonnet-4-20250514` | 200K | | | | | | $3 | $15 |
54
55
  | `anthropic/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
package/.docs/models/providers/berget.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Berget.AI logo](https://models.dev/logos/berget.svg)Berget.AI
2
2
 
3
- Access 8 Berget.AI models through Mastra's model router. Authentication is handled automatically using the `BERGET_API_KEY` environment variable.
3
+ Access 5 Berget.AI models through Mastra's model router. Authentication is handled automatically using the `BERGET_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Berget.AI documentation](https://api.berget.ai).
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: "berget/BAAI/bge-reranker-v2-m3"
18
+ model: "berget/google/gemma-4-31B-it"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,14 +34,11 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `berget/BAAI/bge-reranker-v2-m3` | 512 | | | | | | $0.10 | $0.10 |
38
- | `berget/intfloat/multilingual-e5-large` | 512 | | | | | | $0.02 | — |
39
- | `berget/intfloat/multilingual-e5-large-instruct` | 512 | | | | | | $0.02 | — |
40
- | `berget/KBLab/kb-whisper-large` | 480K | | | | | | $3 | $3 |
41
- | `berget/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.90 | $0.90 |
42
- | `berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506` | 32K | | | | | | $0.30 | $0.30 |
43
- | `berget/openai/gpt-oss-120b` | 128K | | | | | | $0.30 | $0.90 |
44
- | `berget/zai-org/GLM-4.7` | 128K | | | | | | $0.70 | $2 |
37
+ | `berget/google/gemma-4-31B-it` | 128K | | | | | | $0.28 | $0.55 |
38
+ | `berget/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.99 | $0.99 |
39
+ | `berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506` | 32K | | | | | | $0.33 | $0.33 |
40
+ | `berget/openai/gpt-oss-120b` | 128K | | | | | | $0.44 | $0.99 |
41
+ | `berget/zai-org/GLM-4.7` | 128K | | | | | | $0.77 | $3 |
45
42
 
46
43
  ## Advanced configuration
47
44
 
@@ -53,7 +50,7 @@ const agent = new Agent({
53
50
  name: "custom-agent",
54
51
  model: {
55
52
  url: "https://api.berget.ai/v1",
56
- id: "berget/BAAI/bge-reranker-v2-m3",
53
+ id: "berget/google/gemma-4-31B-it",
57
54
  apiKey: process.env.BERGET_API_KEY,
58
55
  headers: {
59
56
  "X-Custom-Header": "value"
@@ -72,7 +69,7 @@ const agent = new Agent({
72
69
  const useAdvanced = requestContext.task === "complex";
73
70
  return useAdvanced
74
71
  ? "berget/zai-org/GLM-4.7"
75
- : "berget/BAAI/bge-reranker-v2-m3";
72
+ : "berget/google/gemma-4-31B-it";
76
73
  }
77
74
  });
78
75
  ```
package/.docs/models/providers/cloudflare-workers-ai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Cloudflare Workers AI logo](https://models.dev/logos/cloudflare-workers-ai.svg)Cloudflare Workers AI
2
2
 
3
- Access 7 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
3
+ Access 8 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
4
4
 
5
5
  Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
6
6
 
@@ -38,6 +38,7 @@ for await (const chunk of stream) {
38
38
  | `cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it` | 256K | | | | | | $0.10 | $0.30 |
39
39
  | `cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct` | 128K | | | | | | $0.27 | $0.85 |
40
40
  | `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.5` | 256K | | | | | | $0.60 | $3 |
41
+ | `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6` | 256K | | | | | | $0.95 | $4 |
41
42
  | `cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b` | 256K | | | | | | $0.50 | $2 |
42
43
  | `cloudflare-workers-ai/@cf/openai/gpt-oss-120b` | 128K | | | | | | $0.35 | $0.75 |
43
44
  | `cloudflare-workers-ai/@cf/openai/gpt-oss-20b` | 128K | | | | | | $0.20 | $0.30 |
package/.docs/models/providers/cortecs.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Cortecs logo](https://models.dev/logos/cortecs.svg)Cortecs
2
2
 
3
- Access 30 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
3
+ Access 33 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Cortecs documentation](https://cortecs.ai).
6
6
 
@@ -39,6 +39,7 @@ for await (const chunk of stream) {
39
39
  | `cortecs/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
40
40
  | `cortecs/claude-opus4-5` | 200K | | | | | | $6 | $30 |
41
41
  | `cortecs/claude-opus4-6` | 1.0M | | | | | | $6 | $30 |
42
+ | `cortecs/claude-opus4-7` | 1.0M | | | | | | $6 | $28 |
42
43
  | `cortecs/claude-sonnet-4` | 200K | | | | | | $3 | $17 |
43
44
  | `cortecs/deepseek-v3-0324` | 128K | | | | | | $0.55 | $2 |
44
45
  | `cortecs/devstral-2512` | 262K | | | | | | — | — |
@@ -49,6 +50,7 @@ for await (const chunk of stream) {
49
50
  | `cortecs/glm-4.7` | 198K | | | | | | $0.45 | $2 |
50
51
  | `cortecs/glm-4.7-flash` | 203K | | | | | | $0.09 | $0.53 |
51
52
  | `cortecs/glm-5` | 203K | | | | | | $1 | $3 |
53
+ | `cortecs/glm-5.1` | 205K | | | | | | $1 | $4 |
52
54
  | `cortecs/gpt-4.1` | 1.0M | | | | | | $2 | $9 |
53
55
  | `cortecs/gpt-oss-120b` | 128K | | | | | | — | — |
54
56
  | `cortecs/intellect-3` | 128K | | | | | | $0.22 | $1 |
@@ -59,6 +61,7 @@ for await (const chunk of stream) {
59
61
  | `cortecs/minimax-m2` | 400K | | | | | | $0.39 | $2 |
60
62
  | `cortecs/minimax-m2.1` | 196K | | | | | | $0.34 | $1 |
61
63
  | `cortecs/minimax-m2.5` | 197K | | | | | | $0.32 | $1 |
64
+ | `cortecs/minimax-M2.7` | 203K | | | | | | $0.47 | $1 |
62
65
  | `cortecs/nova-pro-v1` | 300K | | | | | | $1 | $4 |
63
66
  | `cortecs/qwen3-32b` | 16K | | | | | | $0.10 | $0.33 |
64
67
  | `cortecs/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.44 | $2 |
package/.docs/models/providers/digitalocean.md ADDED
@@ -0,0 +1,116 @@
1
+ # ![DigitalOcean logo](https://models.dev/logos/digitalocean.svg)DigitalOcean
2
+
3
+ Access 46 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
4
+
5
+ Learn more in the [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/).
6
+
7
+ ```bash
8
+ DIGITALOCEAN_ACCESS_TOKEN=your-api-token
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: "digitalocean/alibaba-qwen3-32b"
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 [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) for details.
32
+
33
+ ## Models
34
+
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `digitalocean/alibaba-qwen3-32b` | 131K | | | | | | $0.25 | $0.55 |
38
+ | `digitalocean/all-mini-lm-l6-v2` | 256 | | | | | | $0.01 | — |
39
+ | `digitalocean/anthropic-claude-4.1-opus` | 200K | | | | | | $15 | $75 |
40
+ | `digitalocean/anthropic-claude-4.5-sonnet` | 1.0M | | | | | | $3 | $15 |
41
+ | `digitalocean/anthropic-claude-4.6-sonnet` | 1.0M | | | | | | $3 | $15 |
42
+ | `digitalocean/anthropic-claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
43
+ | `digitalocean/anthropic-claude-opus-4` | 200K | | | | | | $15 | $75 |
44
+ | `digitalocean/anthropic-claude-opus-4.5` | 200K | | | | | | $5 | $25 |
45
+ | `digitalocean/anthropic-claude-opus-4.6` | 1.0M | | | | | | $5 | $25 |
46
+ | `digitalocean/anthropic-claude-opus-4.7` | 1.0M | | | | | | $5 | $25 |
47
+ | `digitalocean/anthropic-claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
48
+ | `digitalocean/arcee-trinity-large-thinking` | 256K | | | | | | $0.25 | $0.90 |
49
+ | `digitalocean/deepseek-r1-distill-llama-70b` | 131K | | | | | | $0.99 | $0.99 |
50
+ | `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | — | | | | | | — | — |
51
+ | `digitalocean/fal-ai/fast-sdxl` | — | | | | | | — | — |
52
+ | `digitalocean/fal-ai/flux/schnell` | — | | | | | | — | — |
53
+ | `digitalocean/fal-ai/stable-audio-25/text-to-audio` | — | | | | | | — | — |
54
+ | `digitalocean/glm-5` | 203K | | | | | | $1 | $3 |
55
+ | `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
56
+ | `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
57
+ | `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
58
+ | `digitalocean/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
59
+ | `digitalocean/multi-qa-mpnet-base-dot-v1` | 512 | | | | | | $0.01 | — |
60
+ | `digitalocean/nvidia-nemotron-3-super-120b` | 256K | | | | | | $0.30 | $0.65 |
61
+ | `digitalocean/openai-gpt-4.1` | 1.0M | | | | | | $2 | $8 |
62
+ | `digitalocean/openai-gpt-4o` | 128K | | | | | | $3 | $10 |
63
+ | `digitalocean/openai-gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
64
+ | `digitalocean/openai-gpt-5` | 400K | | | | | | $1 | $10 |
65
+ | `digitalocean/openai-gpt-5-2-pro` | 400K | | | | | | $21 | $168 |
66
+ | `digitalocean/openai-gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
67
+ | `digitalocean/openai-gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
68
+ | `digitalocean/openai-gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
69
+ | `digitalocean/openai-gpt-5.2` | 400K | | | | | | $2 | $14 |
70
+ | `digitalocean/openai-gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
71
+ | `digitalocean/openai-gpt-5.4` | 1.0M | | | | | | $3 | $15 |
72
+ | `digitalocean/openai-gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
73
+ | `digitalocean/openai-gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
74
+ | `digitalocean/openai-gpt-5.4-pro` | 400K | | | | | | $30 | $180 |
75
+ | `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
76
+ | `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
77
+ | `digitalocean/openai-gpt-oss-120b` | 131K | | | | | | $0.10 | $0.70 |
78
+ | `digitalocean/openai-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.45 |
79
+ | `digitalocean/openai-o1` | 200K | | | | | | $15 | $60 |
80
+ | `digitalocean/openai-o3` | 200K | | | | | | $2 | $8 |
81
+ | `digitalocean/openai-o3-mini` | 200K | | | | | | $1 | $4 |
82
+ | `digitalocean/qwen3-embedding-0.6b` | 8K | | | | | | $0.04 | — |
83
+
84
+ ## Advanced configuration
85
+
86
+ ### Custom headers
87
+
88
+ ```typescript
89
+ const agent = new Agent({
90
+ id: "custom-agent",
91
+ name: "custom-agent",
92
+ model: {
93
+ url: "https://inference.do-ai.run/v1",
94
+ id: "digitalocean/alibaba-qwen3-32b",
95
+ apiKey: process.env.DIGITALOCEAN_ACCESS_TOKEN,
96
+ headers: {
97
+ "X-Custom-Header": "value"
98
+ }
99
+ }
100
+ });
101
+ ```
102
+
103
+ ### Dynamic model selection
104
+
105
+ ```typescript
106
+ const agent = new Agent({
107
+ id: "dynamic-agent",
108
+ name: "Dynamic Agent",
109
+ model: ({ requestContext }) => {
110
+ const useAdvanced = requestContext.task === "complex";
111
+ return useAdvanced
112
+ ? "digitalocean/qwen3-embedding-0.6b"
113
+ : "digitalocean/alibaba-qwen3-32b";
114
+ }
115
+ });
116
+ ```
package/.docs/models/providers/firmware.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Firmware logo](https://models.dev/logos/firmware.svg)Firmware
2
2
 
3
- Access 25 Firmware models through Mastra's model router. Authentication is handled automatically using the `FIRMWARE_API_KEY` environment variable.
3
+ Access 24 Firmware models through Mastra's model router. Authentication is handled automatically using the `FIRMWARE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Firmware documentation](https://docs.frogbot.ai).
6
6
 
@@ -35,9 +35,8 @@ for await (const chunk of stream) {
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
37
  | `firmware/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
38
- | `firmware/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
39
38
  | `firmware/claude-opus-4-6` | 200K | | | | | | $5 | $25 |
40
- | `firmware/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
39
+ | `firmware/claude-opus-4-7` | 200K | | | | | | $5 | $25 |
41
40
  | `firmware/claude-sonnet-4-6` | 200K | | | | | | $3 | $15 |
42
41
  | `firmware/deepseek-v3-2` | 128K | | | | | | $0.58 | $2 |
43
42
  | `firmware/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
package/.docs/models/providers/helicone.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Helicone logo](https://models.dev/logos/helicone.svg)Helicone
2
2
 
3
- Access 91 Helicone models through Mastra's model router. Authentication is handled automatically using the `HELICONE_API_KEY` environment variable.
3
+ Access 90 Helicone models through Mastra's model router. Authentication is handled automatically using the `HELICONE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Helicone documentation](https://helicone.ai/models).
6
6
 
@@ -48,7 +48,6 @@ for await (const chunk of stream) {
48
48
  | `helicone/claude-opus-4-1-20250805` | 200K | | | | | | $15 | $75 |
49
49
  | `helicone/claude-sonnet-4` | 200K | | | | | | $3 | $15 |
50
50
  | `helicone/claude-sonnet-4-5-20250929` | 200K | | | | | | $3 | $15 |
51
- | `helicone/codex-mini-latest` | 200K | | | | | | $2 | $6 |
52
51
  | `helicone/deepseek-r1-distill-llama-70b` | 128K | | | | | | $0.03 | $0.13 |
53
52
  | `helicone/deepseek-reasoner` | 128K | | | | | | $0.56 | $2 |
54
53
  | `helicone/deepseek-tng-r1t2-chimera` | 130K | | | | | | $0.30 | $1 |
package/.docs/models/providers/hpc-ai.md ADDED
@@ -0,0 +1,73 @@
1
+ # ![HPC-AI logo](https://models.dev/logos/hpc-ai.svg)HPC-AI
2
+
3
+ Access 3 HPC-AI models through Mastra's model router. Authentication is handled automatically using the `HPC_AI_API_KEY` environment variable.
4
+
5
+ Learn more in the [HPC-AI documentation](https://www.hpc-ai.com/doc/docs/quickstart/).
6
+
7
+ ```bash
8
+ HPC_AI_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: "hpc-ai/minimax/minimax-m2.5"
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 [HPC-AI documentation](https://www.hpc-ai.com/doc/docs/quickstart/) for details.
32
+
33
+ ## Models
34
+
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | ----------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `hpc-ai/minimax/minimax-m2.5` | 1.0M | | | | | | $0.14 | $0.56 |
38
+ | `hpc-ai/moonshotai/kimi-k2.5` | 262K | | | | | | $0.21 | $1 |
39
+ | `hpc-ai/zai-org/glm-5.1` | 202K | | | | | | $0.66 | $2 |
40
+
41
+ ## Advanced configuration
42
+
43
+ ### Custom headers
44
+
45
+ ```typescript
46
+ const agent = new Agent({
47
+ id: "custom-agent",
48
+ name: "custom-agent",
49
+ model: {
50
+ url: "https://api.hpc-ai.com/inference/v1",
51
+ id: "hpc-ai/minimax/minimax-m2.5",
52
+ apiKey: process.env.HPC_AI_API_KEY,
53
+ headers: {
54
+ "X-Custom-Header": "value"
55
+ }
56
+ }
57
+ });
58
+ ```
59
+
60
+ ### Dynamic model selection
61
+
62
+ ```typescript
63
+ const agent = new Agent({
64
+ id: "dynamic-agent",
65
+ name: "Dynamic Agent",
66
+ model: ({ requestContext }) => {
67
+ const useAdvanced = requestContext.task === "complex";
68
+ return useAdvanced
69
+ ? "hpc-ai/zai-org/glm-5.1"
70
+ : "hpc-ai/minimax/minimax-m2.5";
71
+ }
72
+ });
73
+ ```
package/.docs/models/providers/huggingface.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
2
2
 
3
- Access 22 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
3
+ Access 23 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
4
4
 
5
5
  Learn more in the [Hugging Face documentation](https://huggingface.co).
6
6
 
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
43
43
  | `huggingface/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $1 | $3 |
44
44
  | `huggingface/moonshotai/Kimi-K2-Thinking` | 262K | | | | | | $0.60 | $3 |
45
45
  | `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
46
+ | `huggingface/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
46
47
  | `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.30 | $3 |
47
48
  | `huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $2 | $2 |
48
49
  | `huggingface/Qwen/Qwen3-Coder-Next` | 262K | | | | | | $0.20 | $2 |
package/.docs/models/providers/kimi-for-coding.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Kimi For Coding logo](https://models.dev/logos/kimi-for-coding.svg)Kimi For Coding
2
2
 
3
- Access 2 Kimi For Coding models through Mastra's model router. Authentication is handled automatically using the `KIMI_API_KEY` environment variable.
3
+ Access 3 Kimi For Coding models through Mastra's model router. Authentication is handled automatically using the `KIMI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Kimi For Coding documentation](https://www.kimi.com/coding/docs/en/third-party-agents.html).
6
6
 
@@ -35,6 +35,7 @@ for await (const chunk of stream) {
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
37
  | `kimi-for-coding/k2p5` | 262K | | | | | | — | — |
38
+ | `kimi-for-coding/k2p6` | 262K | | | | | | — | — |
38
39
  | `kimi-for-coding/kimi-k2-thinking` | 262K | | | | | | — | — |
39
40
 
40
41
  ## Advanced configuration