@mastra/mcp-docs-server 1.2.23-alpha.5 → 1.2.23-alpha.6

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 (21) hide show
  1. package/.docs/models/gateways/merge-gateway.md +2 -1
  2. package/.docs/models/gateways/netlify.md +1 -1
  3. package/.docs/models/gateways/openrouter.md +1 -1
  4. package/.docs/models/gateways/vercel.md +2 -1
  5. package/.docs/models/index.md +1 -1
  6. package/.docs/models/providers/abliteration-ai.md +7 -6
  7. package/.docs/models/providers/coralbricks.md +4 -4
  8. package/.docs/models/providers/cortecs.md +2 -1
  9. package/.docs/models/providers/crossmodel.md +2 -2
  10. package/.docs/models/providers/edenai.md +6 -5
  11. package/.docs/models/providers/google.md +1 -2
  12. package/.docs/models/providers/groq.md +2 -1
  13. package/.docs/models/providers/hyper.md +8 -6
  14. package/.docs/models/providers/kilo.md +21 -22
  15. package/.docs/models/providers/llmgateway-providers.md +2 -26
  16. package/.docs/models/providers/llmgateway.md +3 -14
  17. package/.docs/models/providers/nano-gpt.md +5 -3
  18. package/.docs/models/providers/requesty.md +4 -4
  19. package/.docs/models/providers/vancine.md +18 -14
  20. package/.docs/reference/agents/durable-agent.md +76 -8
  21. package/package.json +4 -4
package/.docs/models/gateways/merge-gateway.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Merge Gateway logo](https://models.dev/logos/merge-gateway.svg)Merge Gateway
6
6
 
7
- Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 176 models through Mastra's model router.
7
+ Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 177 models through Mastra's model router.
8
8
 
9
9
  Learn more in the [Merge Gateway documentation](https://docs.merge.dev/merge-gateway).
10
10
 
@@ -67,6 +67,7 @@ ANTHROPIC_API_KEY=ant-...
67
67
  | `deepseek/deepseek-v3.2` |
68
68
  | `deepseek/deepseek-v4-flash` |
69
69
  | `deepseek/deepseek-v4-flash-0731` |
70
+ | `deepseek/deepseek-v4-flash-0731-fast` |
70
71
  | `deepseek/deepseek-v4-pro` |
71
72
  | `deepseek/deepseek-v4-pro-0423` |
72
73
  | `deepseek/deepseek-v4-pro-0813` |
package/.docs/models/gateways/netlify.md CHANGED
@@ -111,7 +111,6 @@ ANTHROPIC_API_KEY=ant-...
111
111
  | `openrouter/~x-ai/grok-latest` |
112
112
  | `openrouter/~z-ai/glm-latest` |
113
113
  | `openrouter/anthracite-org/magnum-v4-72b` |
114
- | `openrouter/arcee-ai/trinity-large-thinking` |
115
114
  | `openrouter/baidu/ernie-4.5-vl-424b-a47b` |
116
115
  | `openrouter/bytedance-seed/seed-1.6` |
117
116
  | `openrouter/bytedance-seed/seed-1.6-flash` |
@@ -143,6 +142,7 @@ ANTHROPIC_API_KEY=ant-...
143
142
  | `openrouter/google/gemma-4-31b-it` |
144
143
  | `openrouter/gryphe/mythomax-l2-13b` |
145
144
  | `openrouter/ibm-granite/granite-4.1-8b` |
145
+ | `openrouter/ibm-granite/granite-4.2-8b` |
146
146
  | `openrouter/inception/mercury-2` |
147
147
  | `openrouter/inclusionai/ling-3.0-flash` |
148
148
  | `openrouter/inclusionai/ling-3.0-flash-fin:free` |
package/.docs/models/gateways/openrouter.md CHANGED
@@ -140,10 +140,10 @@ ANTHROPIC_API_KEY=ant-...
140
140
  | `gryphe/mythomax-l2-13b` |
141
141
  | `ibm-granite/granite-4.0-h-micro` |
142
142
  | `ibm-granite/granite-4.1-8b` |
143
+ | `ibm-granite/granite-4.2-8b` |
143
144
  | `inception/mercury-2` |
144
145
  | `inclusionai/ling-3.0-flash` |
145
146
  | `inclusionai/ling-3.0-flash-fin:free` |
146
- | `kwaipilot/kat-coder-air-v2.5` |
147
147
  | `kwaipilot/kat-coder-pro-v2` |
148
148
  | `kwaipilot/kat-coder-pro-v2.5` |
149
149
  | `liquid/lfm-2.5-2.6b:free` |
package/.docs/models/gateways/vercel.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
6
6
 
7
- Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 361 models through Mastra's model router.
7
+ Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 362 models through Mastra's model router.
8
8
 
9
9
  Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
10
10
 
@@ -69,6 +69,7 @@ ANTHROPIC_API_KEY=ant-...
69
69
  | `alibaba/qwen3.8-2.4t-a95b` |
70
70
  | `alibaba/qwen3.8-27b` |
71
71
  | `alibaba/qwen3.8-flash` |
72
+ | `alibaba/qwen3.8-flash-next` |
72
73
  | `alibaba/qwen3.8-max` |
73
74
  | `alibaba/wan-v2.5-t2v-preview` |
74
75
  | `alibaba/wan-v2.6-i2v` |
package/.docs/models/index.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # Model Providers
6
6
 
7
- Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7046 models from 199 providers through a single API.
7
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7023 models from 199 providers through a single API.
8
8
 
9
9
  ## Features
10
10
 
package/.docs/models/providers/abliteration-ai.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![abliteration.ai logo](https://models.dev/logos/abliteration-ai.svg)abliteration.ai
6
6
 
7
- Access 2 abliteration.ai models through Mastra's model router. Authentication is handled automatically using the `ABLIT_KEY` environment variable.
7
+ Access 3 abliteration.ai models through Mastra's model router. Authentication is handled automatically using the `ABLIT_KEY` environment variable.
8
8
 
9
9
  Learn more in the [abliteration.ai documentation](https://docs.abliteration.ai/models).
10
10
 
@@ -36,10 +36,11 @@ for await (const chunk of stream) {
36
36
 
37
37
  ## Models
38
38
 
39
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
- | ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
- | `abliteration-ai/abliterated-model` | 150K | | | | | | $3 | $3 |
42
- | `abliteration-ai/abliterated-model-large` | 1.0M | | | | | | $5 | $5 |
39
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
+ | -------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
+ | `abliteration-ai/abliterated-model` | 150K | | | | | | $3 | $3 |
42
+ | `abliteration-ai/abliterated-model-large` | 1.0M | | | | | | $5 | $5 |
43
+ | `abliteration-ai/abliterated-model-large-v2` | 1.0M | | | | | | $5 | $5 |
43
44
 
44
45
  ## Advanced configuration
45
46
 
@@ -69,7 +70,7 @@ const agent = new Agent({
69
70
  model: ({ requestContext }) => {
70
71
  const useAdvanced = requestContext.task === "complex";
71
72
  return useAdvanced
72
- ? "abliteration-ai/abliterated-model-large"
73
+ ? "abliteration-ai/abliterated-model-large-v2"
73
74
  : "abliteration-ai/abliterated-model";
74
75
  }
75
76
  });
package/.docs/models/providers/coralbricks.md CHANGED
@@ -19,7 +19,7 @@ const agent = new Agent({
19
19
  id: "my-agent",
20
20
  name: "My Agent",
21
21
  instructions: "You are a helpful assistant",
22
- model: "coralbricks/glm-5.2-fp4"
22
+ model: "coralbricks/glm-5.3-fp4"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -38,7 +38,7 @@ for await (const chunk of stream) {
38
38
 
39
39
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
40
  | -------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
- | `coralbricks/glm-5.2-fp4` | 1.0M | | | | | | $1 | $4 |
41
+ | `coralbricks/glm-5.3-fp4` | 1.0M | | | | | | $1 | $4 |
42
42
  | `coralbricks/gpt-oss-120b` | 131K | | | | | | $0.12 | $0.60 |
43
43
  | `coralbricks/kimi-k3` | 1.0M | | | | | | $3 | $15 |
44
44
 
@@ -52,7 +52,7 @@ const agent = new Agent({
52
52
  name: "custom-agent",
53
53
  model: {
54
54
  url: "https://inference.coralbricks.ai/v1",
55
- id: "coralbricks/glm-5.2-fp4",
55
+ id: "coralbricks/glm-5.3-fp4",
56
56
  apiKey: process.env.CORAL_API_KEY,
57
57
  headers: {
58
58
  "X-Custom-Header": "value"
@@ -71,7 +71,7 @@ const agent = new Agent({
71
71
  const useAdvanced = requestContext.task === "complex";
72
72
  return useAdvanced
73
73
  ? "coralbricks/kimi-k3"
74
- : "coralbricks/glm-5.2-fp4";
74
+ : "coralbricks/glm-5.3-fp4";
75
75
  }
76
76
  });
77
77
  ```
package/.docs/models/providers/cortecs.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Cortecs logo](https://models.dev/logos/cortecs.svg)Cortecs
6
6
 
7
- Access 111 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
7
+ Access 112 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Cortecs documentation](https://cortecs.ai).
10
10
 
@@ -55,6 +55,7 @@ for await (const chunk of stream) {
55
55
  | `cortecs/deepseek-v3.2` | 164K | | | | | | $0.30 | $0.49 |
56
56
  | `cortecs/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.13 | $0.28 |
57
57
  | `cortecs/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
58
+ | `cortecs/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
58
59
  | `cortecs/devstral-2512` | 262K | | | | | | $0.45 | $2 |
59
60
  | `cortecs/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $2 |
60
61
  | `cortecs/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
package/.docs/models/providers/crossmodel.md CHANGED
@@ -75,8 +75,8 @@ for await (const chunk of stream) {
75
75
  | `crossmodel/qwen/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
76
76
  | `crossmodel/qwen/qwen3.6-plus` | 1.0M | | | | | | $0.32 | $2 |
77
77
  | `crossmodel/qwen/qwen3.7-flash` | 1.0M | | | | | | $0.04 | $0.13 |
78
- | `crossmodel/qwen/qwen3.7-max` | 1.0M | | | | | | $2 | $5 |
79
- | `crossmodel/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.29 | $1 |
78
+ | `crossmodel/qwen/qwen3.7-max` | 1.0M | | | | | | $2 | $6 |
79
+ | `crossmodel/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
80
80
  | `crossmodel/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.13 | $0.43 |
81
81
  | `crossmodel/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
82
82
  | `crossmodel/tencent/hy3` | 262K | | | | | | $0.16 | $0.64 |
package/.docs/models/providers/edenai.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Eden AI logo](https://models.dev/logos/edenai.svg)Eden AI
6
6
 
7
- Access 238 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
7
+ Access 239 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Eden AI documentation](https://docs.edenai.co).
10
10
 
@@ -107,7 +107,7 @@ for await (const chunk of stream) {
107
107
  | `edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
108
108
  | `edenai/fireworks_ai/accounts/fireworks/models/muse-glimmer-30b` | 131K | | | | | | $0.35 | $2 |
109
109
  | `edenai/fireworks_ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
110
- | `edenai/flexai/deepseek-v4-flash-0731` | 786K | | | | | | $0.08 | $0.18 |
110
+ | `edenai/flexai/deepseek-v4-flash-0731` | 786K | | | | | | $0.03 | $0.10 |
111
111
  | `edenai/flexai/gpt-oss-120b` | 131K | | | | | | $0.04 | $0.10 |
112
112
  | `edenai/flexai/gpt-oss-20b` | 131K | | | | | | $0.02 | $0.10 |
113
113
  | `edenai/flexai/Muse-Glimmer-30B` | 131K | | | | | | $0.30 | $1 |
@@ -131,8 +131,8 @@ for await (const chunk of stream) {
131
131
  | `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
132
132
  | `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
133
133
  | `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
134
- | `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.76 | $0.76 |
135
- | `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.76 |
134
+ | `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
135
+ | `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
136
136
  | `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
137
137
  | `edenai/minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
138
138
  | `edenai/minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
@@ -152,6 +152,7 @@ for await (const chunk of stream) {
152
152
  | `edenai/mistral/voxtral-small-latest` | 33K | | | | | | $0.10 | $0.40 |
153
153
  | `edenai/moonshot/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
154
154
  | `edenai/moonshot/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
155
+ | `edenai/moonshot/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
155
156
  | `edenai/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
156
157
  | `edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
157
158
  | `edenai/nebius/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.13 | $0.40 |
@@ -223,7 +224,7 @@ for await (const chunk of stream) {
223
224
  | `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.16 | $0.47 |
224
225
  | `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
225
226
  | `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
226
- | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.47 | $0.93 |
227
+ | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
227
228
  | `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
228
229
  | `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
229
230
  | `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
package/.docs/models/providers/google.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Google logo](https://models.dev/logos/google.svg)Google
6
6
 
7
- Access 39 Google models through Mastra's model router. Authentication is handled automatically using one of the following environment variables: `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`.
7
+ Access 38 Google models through Mastra's model router. Authentication is handled automatically using one of the following environment variables: `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`.
8
8
 
9
9
  Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
10
10
 
@@ -67,7 +67,6 @@ for await (const chunk of stream) {
67
67
  | `google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
68
68
  | `google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.30 | $3 |
69
69
  | `google/gemini-omni-flash-preview` | 131K | | | | | | $2 | $18 |
70
- | `google/gemini-robotics-er-1.6-preview` | 131K | | | | | | $1 | $5 |
71
70
  | `google/gemma-4-26b-a4b-it` | 262K | | | | | | — | — |
72
71
  | `google/gemma-4-31b-it` | 262K | | | | | | — | — |
73
72
  | `google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
package/.docs/models/providers/groq.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Groq logo](https://models.dev/logos/groq.svg)Groq
6
6
 
7
- Access 15 Groq models through Mastra's model router. Authentication is handled automatically using the `GROQ_API_KEY` environment variable.
7
+ Access 16 Groq models through Mastra's model router. Authentication is handled automatically using the `GROQ_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Groq documentation](https://console.groq.com/docs/models).
10
10
 
@@ -49,6 +49,7 @@ for await (const chunk of stream) {
49
49
  | `groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
50
50
  | `groq/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
51
51
  | `groq/qwen/qwen3.6-27b` | 131K | | | | | | $0.60 | $3 |
52
+ | `groq/qwen/qwen3.8-27b` | 131K | | | | | | $0.80 | $4 |
52
53
  | `groq/whisper-large-v3` | — | | | | | | — | — |
53
54
  | `groq/whisper-large-v3-turbo` | — | | | | | | — | — |
54
55
 
package/.docs/models/providers/hyper.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Charm Hyper logo](https://models.dev/logos/hyper.svg)Charm Hyper
6
6
 
7
- Access 29 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
7
+ Access 31 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
10
10
 
@@ -42,18 +42,20 @@ for await (const chunk of stream) {
42
42
  | `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
43
43
  | `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
44
44
  | `hyper/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
45
- | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.41 |
46
- | `hyper/glm-5` | 203K | | | | | | $0.90 | $3 |
45
+ | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.12 | $0.42 |
46
+ | `hyper/glm-5` | 203K | | | | | | $0.91 | $3 |
47
47
  | `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
48
48
  | `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
49
- | `hyper/gpt-oss-120b` | 128K | | | | | | $0.18 | $0.68 |
49
+ | `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
50
+ | `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
51
+ | `hyper/gpt-oss-120b` | 128K | | | | | | $0.19 | $0.70 |
50
52
  | `hyper/kimi-k2.5` | 262K | | | | | | $0.54 | $3 |
51
53
  | `hyper/kimi-k2.6` | 262K | | | | | | $1 | $4 |
52
54
  | `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
53
55
  | `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
54
56
  | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
55
- | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.28 | $0.93 |
56
- | `hyper/minimax-m2.7` | 262K | | | | | | $0.40 | $1 |
57
+ | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.90 |
58
+ | `hyper/minimax-m2.7` | 262K | | | | | | $0.42 | $2 |
57
59
  | `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
58
60
  | `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
59
61
  | `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
package/.docs/models/providers/kilo.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
6
6
 
7
- Access 364 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
7
+ Access 363 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Kilo Gateway documentation](https://kilo.ai).
10
10
 
@@ -42,14 +42,14 @@ for await (const chunk of stream) {
42
42
  | `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
43
43
  | `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
44
44
  | `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
45
- | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.03 | $0.16 |
45
+ | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.16 |
46
46
  | `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
47
47
  | `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
48
48
  | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $3 | $13 |
49
49
  | `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
50
50
  | `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
51
51
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
52
- | `kilo/~z-ai/glm-latest` | 262K | | | | | | $1 | $4 |
52
+ | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $1 | $4 |
53
53
  | `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
54
54
  | `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
55
55
  | `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -77,7 +77,7 @@ for await (const chunk of stream) {
77
77
  | `kilo/anthropic/claude-sonnet-4.5` | 1.0M | | | | | | $3 | $15 |
78
78
  | `kilo/anthropic/claude-sonnet-4.6` | 1.0M | | | | | | $3 | $15 |
79
79
  | `kilo/anthropic/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
80
- | `kilo/arcee-ai/trinity-large-thinking` | 262K | | | | | | $0.22 | $0.85 |
80
+ | `kilo/arcee-ai/trinity-large-thinking` | 262K | | | | | | $0.25 | $0.80 |
81
81
  | `kilo/baidu/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
82
82
  | `kilo/bytedance-seed/seed-1.6` | 262K | | | | | | $0.25 | $2 |
83
83
  | `kilo/bytedance-seed/seed-1.6-flash` | 262K | | | | | | $0.07 | $0.30 |
@@ -92,8 +92,8 @@ for await (const chunk of stream) {
92
92
  | `kilo/cohere/command-r-plus-08-2024` | 128K | | | | | | $3 | $10 |
93
93
  | `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
94
94
  | `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
95
- | `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.40 | $1 |
96
- | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.27 | $1 |
95
+ | `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.26 | $1 |
96
+ | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.25 | $1 |
97
97
  | `kilo/deepseek/deepseek-chat-v3.1` | 161K | | | | | | $0.27 | $1 |
98
98
  | `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
99
99
  | `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
@@ -103,30 +103,30 @@ for await (const chunk of stream) {
103
103
  | `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
104
104
  | `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
105
105
  | `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
106
- | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
106
+ | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.44 | $1 |
107
107
  | `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
108
108
  | `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
109
109
  | `kilo/dots-studio/dots-3-note-preview:free` | 512K | | | | | | — | — |
110
110
  | `kilo/google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
111
- | `kilo/google/gemini-2.5-flash-image` | 33K | | | | | | $0.30 | $3 |
111
+ | `kilo/google/gemini-2.5-flash-image` | 33K | | | | | | $0.15 | $1 |
112
112
  | `kilo/google/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
113
113
  | `kilo/google/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
114
114
  | `kilo/google/gemini-2.5-pro-preview` | 1.0M | | | | | | $1 | $10 |
115
115
  | `kilo/google/gemini-2.5-pro-preview-05-06` | 1.0M | | | | | | $1 | $10 |
116
- | `kilo/google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
116
+ | `kilo/google/gemini-3-flash-preview` | 1.0M | | | | | | $0.25 | $2 |
117
117
  | `kilo/google/gemini-3-pro-image` | 131K | | | | | | $2 | $12 |
118
- | `kilo/google/gemini-3-pro-image-preview` | 66K | | | | | | $2 | $12 |
118
+ | `kilo/google/gemini-3-pro-image-preview` | 66K | | | | | | $1 | $6 |
119
119
  | `kilo/google/gemini-3.1-flash-image` | 131K | | | | | | $0.50 | $3 |
120
120
  | `kilo/google/gemini-3.1-flash-image-preview` | 66K | | | | | | $0.50 | $3 |
121
- | `kilo/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
121
+ | `kilo/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.13 | $0.75 |
122
122
  | `kilo/google/gemini-3.1-flash-lite-image` | 66K | | | | | | $0.25 | $2 |
123
- | `kilo/google/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
124
- | `kilo/google/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
123
+ | `kilo/google/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.13 | $0.75 |
124
+ | `kilo/google/gemini-3.1-pro-preview` | 1.0M | | | | | | $1 | $6 |
125
125
  | `kilo/google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
126
- | `kilo/google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
127
- | `kilo/google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
128
- | `kilo/google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
129
- | `kilo/google/gemini-3.7-flash` | 1.0M | | | | | | $2 | $8 |
126
+ | `kilo/google/gemini-3.5-flash` | 1.0M | | | | | | $0.75 | $5 |
127
+ | `kilo/google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.15 | $1 |
128
+ | `kilo/google/gemini-3.6-flash` | 1.0M | | | | | | $0.38 | $2 |
129
+ | `kilo/google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
130
130
  | `kilo/google/gemma-2-27b-it` | 8K | | | | | | $0.65 | $0.65 |
131
131
  | `kilo/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
132
132
  | `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
@@ -138,6 +138,7 @@ for await (const chunk of stream) {
138
138
  | `kilo/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.06 | $0.06 |
139
139
  | `kilo/ibm-granite/granite-4.0-h-micro` | 131K | | | | | | $0.02 | $0.11 |
140
140
  | `kilo/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
141
+ | `kilo/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
141
142
  | `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
142
143
  | `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
143
144
  | `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
@@ -146,9 +147,8 @@ for await (const chunk of stream) {
146
147
  | `kilo/kilo-auto/free` | 256K | | | | | | — | — |
147
148
  | `kilo/kilo-auto/frontier` | 1.0M | | | | | | $5 | $25 |
148
149
  | `kilo/kilo-auto/small` | 262K | | | | | | $0.05 | $0.40 |
149
- | `kilo/kwaipilot/kat-coder-air-v2.5` | 256K | | | | | | $0.15 | $0.60 |
150
- | `kilo/kwaipilot/kat-coder-pro-v2` | 256K | | | | | | $0.30 | $1 |
151
- | `kilo/kwaipilot/kat-coder-pro-v2.5` | 256K | | | | | | $0.74 | $3 |
150
+ | `kilo/kwaipilot/kat-coder-pro-v2` | 262K | | | | | | $0.30 | $1 |
151
+ | `kilo/kwaipilot/kat-coder-pro-v2.5` | 262K | | | | | | $0.74 | $3 |
152
152
  | `kilo/liquid/lfm-2.5-2.6b:free` | 66K | | | | | | — | — |
153
153
  | `kilo/mancer/weaver` | 8K | | | | | | $0.50 | $0.75 |
154
154
  | `kilo/meituan/longcat-2.0` | 1.0M | | | | | | $0.75 | $3 |
@@ -365,9 +365,8 @@ for await (const chunk of stream) {
365
365
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
366
366
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
367
367
  | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
368
- | `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
368
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
369
369
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
370
- | `kilo/tencent/hy3:free` | 262K | | | | | | — | — |
371
370
  | `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
372
371
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
373
372
  | `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
package/.docs/models/providers/llmgateway-providers.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
6
6
 
7
- Access 384 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 360 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
10
10
 
@@ -246,31 +246,6 @@ for await (const chunk of stream) {
246
246
  | `llmgateway-providers/moonshot/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
247
247
  | `llmgateway-providers/moonshot/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
248
248
  | `llmgateway-providers/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
249
- | `llmgateway-providers/nebius/cosmos3-super-reasoner` | 262K | | | | | | $0.10 | $0.30 |
250
- | `llmgateway-providers/nebius/deepseek-v4-pro` | 1.0M | | | | | | $2 | $4 |
251
- | `llmgateway-providers/nebius/gemma-3-27b` | 110K | | | | | | $0.10 | $0.30 |
252
- | `llmgateway-providers/nebius/glm-5.1` | 203K | | | | | | $1 | $4 |
253
- | `llmgateway-providers/nebius/glm-5.2` | 1.0M | | | | | | $1 | $4 |
254
- | `llmgateway-providers/nebius/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
255
- | `llmgateway-providers/nebius/hermes-4-405b` | 131K | | | | | | $1 | $3 |
256
- | `llmgateway-providers/nebius/hermes-4-70b` | 131K | | | | | | $0.13 | $0.40 |
257
- | `llmgateway-providers/nebius/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
258
- | `llmgateway-providers/nebius/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
259
- | `llmgateway-providers/nebius/kimi-k3` | 1.0M | | | | | | $3 | $15 |
260
- | `llmgateway-providers/nebius/llama-3.1-nemotron-ultra-253b` | 128K | | | | | | $0.60 | $2 |
261
- | `llmgateway-providers/nebius/llama-3.3-70b-instruct` | 128K | | | | | | $0.13 | $0.40 |
262
- | `llmgateway-providers/nebius/minicpm-v-4.5` | 32K | | | | | | $0.66 | $1 |
263
- | `llmgateway-providers/nebius/minimax-m2.5` | 197K | | | | | | $0.30 | $1 |
264
- | `llmgateway-providers/nebius/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
265
- | `llmgateway-providers/nebius/nemotron-3-nano-30b` | 262K | | | | | | $0.06 | $0.24 |
266
- | `llmgateway-providers/nebius/nemotron-3-nano-omni` | 262K | | | | | | $0.06 | $0.24 |
267
- | `llmgateway-providers/nebius/nemotron-3-super-120b` | 262K | | | | | | $0.30 | $0.90 |
268
- | `llmgateway-providers/nebius/nemotron-3-ultra-550b` | 1.0M | | | | | | $1 | $3 |
269
- | `llmgateway-providers/nebius/qwen2-5-vl-72b-instruct` | 32K | | | | | | $0.25 | $0.75 |
270
- | `llmgateway-providers/nebius/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.20 | $0.60 |
271
- | `llmgateway-providers/nebius/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.10 | $0.30 |
272
- | `llmgateway-providers/nebius/qwen3-32b` | 41K | | | | | | $0.10 | $0.30 |
273
- | `llmgateway-providers/nebius/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
274
249
  | `llmgateway-providers/novita/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
275
250
  | `llmgateway-providers/novita/deepseek-v4-flash` | 1.1M | | | | | | $0.14 | $0.28 |
276
251
  | `llmgateway-providers/novita/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
@@ -356,6 +331,7 @@ for await (const chunk of stream) {
356
331
  | `llmgateway-providers/runware/deepseek-v4-pro` | 1.0M | | | | | | $0.96 | $2 |
357
332
  | `llmgateway-providers/runware/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
358
333
  | `llmgateway-providers/runware/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
334
+ | `llmgateway-providers/runware/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
359
335
  | `llmgateway-providers/runware/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
360
336
  | `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
361
337
  | `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
package/.docs/models/providers/llmgateway.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![DevPass (LLM Gateway) logo](https://models.dev/logos/llmgateway.svg)DevPass (LLM Gateway)
6
6
 
7
- Access 191 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 180 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
10
10
 
@@ -53,7 +53,6 @@ for await (const chunk of stream) {
53
53
  | `llmgateway/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
54
54
  | `llmgateway/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
55
55
  | `llmgateway/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
56
- | `llmgateway/cosmos3-super-reasoner` | 262K | | | | | | $0.10 | $0.30 |
57
56
  | `llmgateway/custom` | 128K | | | | | | — | — |
58
57
  | `llmgateway/deepseek-v3.2` | 164K | | | | | | $0.26 | $0.38 |
59
58
  | `llmgateway/deepseek-v4-flash` | 1.1M | | | | | | $0.05 | $0.10 |
@@ -72,7 +71,6 @@ for await (const chunk of stream) {
72
71
  | `llmgateway/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
73
72
  | `llmgateway/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
74
73
  | `llmgateway/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
75
- | `llmgateway/gemma-3-27b` | 110K | | | | | | $0.10 | $0.30 |
76
74
  | `llmgateway/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
77
75
  | `llmgateway/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
78
76
  | `llmgateway/glm-4-32b-0414-128k` | 128K | | | | | | $0.10 | $0.10 |
@@ -136,8 +134,6 @@ for await (const chunk of stream) {
136
134
  | `llmgateway/grok-4-5` | 500K | | | | | | $2 | $6 |
137
135
  | `llmgateway/grok-4-6` | 500K | | | | | | $2 | $6 |
138
136
  | `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
139
- | `llmgateway/hermes-4-405b` | 131K | | | | | | $1 | $3 |
140
- | `llmgateway/hermes-4-70b` | 131K | | | | | | $0.13 | $0.40 |
141
137
  | `llmgateway/hy3` | 262K | | | | | | $0.14 | $0.58 |
142
138
  | `llmgateway/kimi-k2` | 256K | | | | | | $0.57 | $2 |
143
139
  | `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
@@ -150,15 +146,13 @@ for await (const chunk of stream) {
150
146
  | `llmgateway/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
151
147
  | `llmgateway/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
152
148
  | `llmgateway/llama-3.1-70b-instruct` | 128K | | | | | | $0.72 | $0.72 |
153
- | `llmgateway/llama-3.1-nemotron-ultra-253b` | 128K | | | | | | $0.60 | $2 |
154
149
  | `llmgateway/llama-3.2-11b-instruct` | 128K | | | | | | $0.07 | $0.33 |
155
150
  | `llmgateway/llama-3.2-3b-instruct` | 33K | | | | | | $0.03 | $0.05 |
156
- | `llmgateway/llama-3.3-70b-instruct` | 131K | | | | | | $0.13 | $0.40 |
151
+ | `llmgateway/llama-3.3-70b-instruct` | 131K | | | | | | $0.14 | $0.40 |
157
152
  | `llmgateway/llama-4-maverick-17b-instruct` | 1.0M | | | | | | $0.27 | $0.85 |
158
153
  | `llmgateway/llama-4-scout-17b-instruct` | 131K | | | | | | $0.18 | $0.59 |
159
154
  | `llmgateway/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
160
155
  | `llmgateway/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
161
- | `llmgateway/minicpm-v-4.5` | 32K | | | | | | $0.66 | $1 |
162
156
  | `llmgateway/minimax-m2` | 197K | | | | | | $0.20 | $1 |
163
157
  | `llmgateway/minimax-m2.1` | 205K | | | | | | $0.27 | $1 |
164
158
  | `llmgateway/minimax-m2.1-lightning` | 197K | | | | | | $0.12 | $0.48 |
@@ -176,9 +170,6 @@ for await (const chunk of stream) {
176
170
  | `llmgateway/mistral-small-2506` | 128K | | | | | | $0.10 | $0.30 |
177
171
  | `llmgateway/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
178
172
  | `llmgateway/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
179
- | `llmgateway/nemotron-3-nano-30b` | 262K | | | | | | $0.06 | $0.24 |
180
- | `llmgateway/nemotron-3-nano-omni` | 262K | | | | | | $0.06 | $0.24 |
181
- | `llmgateway/nemotron-3-super-120b` | 262K | | | | | | $0.30 | $0.90 |
182
173
  | `llmgateway/nemotron-3-ultra-550b` | 1.0M | | | | | | $0.50 | $2 |
183
174
  | `llmgateway/o1` | 200K | | | | | | $15 | $60 |
184
175
  | `llmgateway/o3` | 200K | | | | | | $2 | $8 |
@@ -190,12 +181,10 @@ for await (const chunk of stream) {
190
181
  | `llmgateway/qwen-omni-turbo` | 33K | | | | | | $0.20 | $0.80 |
191
182
  | `llmgateway/qwen-plus` | 131K | | | | | | $0.40 | $1 |
192
183
  | `llmgateway/qwen-plus-latest` | 1.0M | | | | | | $0.40 | $1 |
193
- | `llmgateway/qwen2-5-vl-72b-instruct` | 32K | | | | | | $0.25 | $0.75 |
194
184
  | `llmgateway/qwen3-235b-a22b-fp8` | 41K | | | | | | $0.20 | $0.80 |
195
185
  | `llmgateway/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.09 | $0.58 |
196
186
  | `llmgateway/qwen3-235b-a22b-thinking-2507` | 262K | | | | | | $0.30 | $3 |
197
- | `llmgateway/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.10 | $0.30 |
198
- | `llmgateway/qwen3-32b` | 41K | | | | | | $0.10 | $0.30 |
187
+ | `llmgateway/qwen3-32b` | 41K | | | | | | $0.36 | $0.87 |
199
188
  | `llmgateway/qwen3-coder-30b-a3b-instruct` | 262K | | | | | | $0.07 | $0.27 |
200
189
  | `llmgateway/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.38 | $2 |
201
190
  | `llmgateway/qwen3-coder-flash` | 1.0M | | | | | | $0.30 | $2 |
package/.docs/models/providers/nano-gpt.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 606 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 608 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
10
10
 
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
41
41
  | `nano-gpt/abacusai/Dracarys-72B-Instruct` | 33K | | | | | | $0.49 | $0.49 |
42
42
  | `nano-gpt/abliteration-ai/abliterated-model` | 262K | | | | | | $3 | $3 |
43
43
  | `nano-gpt/abliteration-ai/abliterated-model-large` | 1.0M | | | | | | $5 | $5 |
44
+ | `nano-gpt/abliteration-ai/abliterated-model-large-v2` | 1.0M | | | | | | $5 | $5 |
44
45
  | `nano-gpt/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
45
46
  | `nano-gpt/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
46
47
  | `nano-gpt/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -206,7 +207,7 @@ for await (const chunk of stream) {
206
207
  | `nano-gpt/gemini-2.5-pro-preview-06-05` | 1.0M | | | | | | $3 | $10 |
207
208
  | `nano-gpt/gemini-3-pro-image-preview` | 1.0M | | | | | | $2 | $12 |
208
209
  | `nano-gpt/gemini-exp-1206` | 2.1M | | | | | | $1 | $5 |
209
- | `nano-gpt/gemma-4-12b-it` | 262K | | | | | | $0.06 | $0.30 |
210
+ | `nano-gpt/gemma-4-12b-it` | 262K | | | | | | $0.05 | $0.25 |
210
211
  | `nano-gpt/gemma-4-26b-a4b-it-chimerax` | 262K | | | | | | $0.12 | $0.38 |
211
212
  | `nano-gpt/gemma-4-26b-a4b-it-darksoul` | 262K | | | | | | $0.12 | $0.38 |
212
213
  | `nano-gpt/gemma-4-26b-a4b-it-luminous` | 262K | | | | | | $0.12 | $0.38 |
@@ -272,6 +273,7 @@ for await (const chunk of stream) {
272
273
  | `nano-gpt/huihui-ai/Llama-3.3-70B-Instruct-abliterated` | 16K | | | | | | $0.70 | $0.70 |
273
274
  | `nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated` | 33K | | | | | | $0.70 | $0.70 |
274
275
  | `nano-gpt/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
276
+ | `nano-gpt/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
275
277
  | `nano-gpt/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.07 | $0.22 |
276
278
  | `nano-gpt/inclusionai/ling-3.0-flash:thinking` | 262K | | | | | | $0.07 | $0.22 |
277
279
  | `nano-gpt/inflatebot/MN-12B-Mag-Mell-R1` | 16K | | | | | | $0.49 | $0.49 |
@@ -643,7 +645,7 @@ for await (const chunk of stream) {
643
645
  | `nano-gpt/z-ai/glm-5.3:thinking` | 1.0M | | | | | | $1 | $3 |
644
646
  | `nano-gpt/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
645
647
  | `nano-gpt/z-ai/glm-5v-turbo:thinking` | 203K | | | | | | $1 | $4 |
646
- | `nano-gpt/z-ai/glm-latest` | 1.0M | | | | | | $0.42 | $1 |
648
+ | `nano-gpt/z-ai/glm-latest` | 1.0M | | | | | | $1 | $3 |
647
649
 
648
650
  ## Advanced configuration
649
651
 
package/.docs/models/providers/requesty.md CHANGED
@@ -61,7 +61,7 @@ for await (const chunk of stream) {
61
61
  | `requesty/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
62
62
  | `requesty/claude-sonnet-5@eu` | 1.0M | | | | | | $2 | $11 |
63
63
  | `requesty/deepseek-v4-flash` | 1.0M | | | | | | $0.44 | $1 |
64
- | `requesty/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
64
+ | `requesty/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.08 | $0.15 |
65
65
  | `requesty/deepseek-v4-flash-0731@eu` | 1.0M | | | | | | $0.14 | $0.28 |
66
66
  | `requesty/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
67
67
  | `requesty/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
@@ -86,12 +86,12 @@ for await (const chunk of stream) {
86
86
  | `requesty/gemma-4-31b-it` | 262K | | | | | | — | — |
87
87
  | `requesty/glm-5.1` | 200K | | | | | | $1 | $4 |
88
88
  | `requesty/glm-5.1@eu` | 200K | | | | | | $1 | $4 |
89
- | `requesty/glm-5.2` | 1.0M | | | | | | $1 | $4 |
89
+ | `requesty/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
90
90
  | `requesty/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
91
91
  | `requesty/glm-5.2@eu` | 1.0M | | | | | | $1 | $4 |
92
92
  | `requesty/glm-5.3` | 1.0M | | | | | | $1 | $4 |
93
- | `requesty/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
94
- | `requesty/glm-5.3@eu` | 1.0M | | | | | | $2 | $5 |
93
+ | `requesty/glm-5.3-flash` | 131K | | | | | | $0.07 | $0.25 |
94
+ | `requesty/glm-5.3@eu` | 1.0M | | | | | | $1 | $4 |
95
95
  | `requesty/gpt-4.1-mini@eu` | 1.0M | | | | | | $0.44 | $2 |
96
96
  | `requesty/gpt-4.1-nano@eu` | 1.0M | | | | | | $0.11 | $0.44 |
97
97
  | `requesty/gpt-4.1@eu` | 1.0M | | | | | | $2 | $9 |
package/.docs/models/providers/vancine.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Vancine logo](https://models.dev/logos/vancine.svg)Vancine
6
6
 
7
- Access 8 Vancine models through Mastra's model router. Authentication is handled automatically using the `VANCINE_API_KEY` environment variable.
7
+ Access 12 Vancine models through Mastra's model router. Authentication is handled automatically using the `VANCINE_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Vancine documentation](https://vancine.com/docs).
10
10
 
@@ -19,7 +19,7 @@ const agent = new Agent({
19
19
  id: "my-agent",
20
20
  name: "My Agent",
21
21
  instructions: "You are a helpful assistant",
22
- model: "vancine/MiniMax-M3"
22
+ model: "vancine/LongCat-2.0"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -36,16 +36,20 @@ for await (const chunk of stream) {
36
36
 
37
37
  ## Models
38
38
 
39
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
- | --------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
- | `vancine/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
42
- | `vancine/deepseek-v4-pro` | 1.0M | | | | | | $0.66 | $2 |
43
- | `vancine/glm-5.3` | 1.0M | | | | | | $1 | $4 |
44
- | `vancine/glm-5.3-flash` | 1.0M | | | | | | $0.06 | $0.20 |
45
- | `vancine/kimi-k3` | 1.0M | | | | | | $2 | $12 |
46
- | `vancine/MiniMax-M3` | 1.0M | | | | | | $0.24 | $0.96 |
47
- | `vancine/qwen3.8-flash` | 1.0M | | | | | | $0.12 | $0.38 |
48
- | `vancine/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
39
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
+ | -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
+ | `vancine/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
42
+ | `vancine/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
43
+ | `vancine/deepseek-v4-pro` | 1.0M | | | | | | $0.66 | $2 |
44
+ | `vancine/glm-5.3` | 1.0M | | | | | | $1 | $4 |
45
+ | `vancine/glm-5.3-flash` | 1.0M | | | | | | $0.06 | $0.20 |
46
+ | `vancine/hy4-preview` | 1.0M | | | | | | $0.67 | $2 |
47
+ | `vancine/kimi-k3` | 1.0M | | | | | | $2 | $12 |
48
+ | `vancine/LongCat-2.0` | 1.0M | | | | | | $0.24 | $0.96 |
49
+ | `vancine/mimo-v2.5-pro` | 1.0M | | | | | | $0.35 | $0.70 |
50
+ | `vancine/MiniMax-M3` | 1.0M | | | | | | $0.24 | $0.96 |
51
+ | `vancine/qwen3.8-flash` | 1.0M | | | | | | $0.12 | $0.38 |
52
+ | `vancine/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
49
53
 
50
54
  ## Advanced configuration
51
55
 
@@ -57,7 +61,7 @@ const agent = new Agent({
57
61
  name: "custom-agent",
58
62
  model: {
59
63
  url: "https://vancine.com/v1",
60
- id: "vancine/MiniMax-M3",
64
+ id: "vancine/LongCat-2.0",
61
65
  apiKey: process.env.VANCINE_API_KEY,
62
66
  headers: {
63
67
  "X-Custom-Header": "value"
@@ -76,7 +80,7 @@ const agent = new Agent({
76
80
  const useAdvanced = requestContext.task === "complex";
77
81
  return useAdvanced
78
82
  ? "vancine/qwen3.8-max"
79
- : "vancine/MiniMax-M3";
83
+ : "vancine/LongCat-2.0";
80
84
  }
81
85
  });
82
86
  ```
package/.docs/reference/agents/durable-agent.md CHANGED
@@ -219,11 +219,83 @@ interface PrepareResult {
219
219
  }
220
220
  ```
221
221
 
222
+ ### Cancellation
223
+
224
+ #### `abortRunStream(runId)`
225
+
226
+ Stops a run by ID from any process that shares the agent's [PubSub](https://mastra.ai/docs/server/pubsub). Only the `runId` from `stream()` or `prepare()` is needed, so a later request can stop a run it didn't start. The run ends the same way as `abort()` on the stream result: the `finish` event carries reason `abort`, `onAbort` fires, and `observe()` consumers see the stream end.
227
+
228
+ ```typescript
229
+ const { runId } = await durableAgent.stream('Summarize the document')
230
+
231
+ // later, from a different request handler
232
+ durableAgent.abortRunStream(runId)
233
+ ```
234
+
235
+ The abort request is published over PubSub, so a multi-process deployment needs a shared backend such as [`RedisStreamsPubSub`](https://mastra.ai/reference/pubsub/redis-streams). The default `EventEmitterPubSub` only reaches runs in the same process. `InngestAgent` doesn't implement this method. Cancel an Inngest run with the `abort()` returned by its `stream()`.
236
+
237
+ Stopping a durable run through `abortRunStream()` or `abortThreadStream()` requires `@mastra/core@1.62.0` or later. Earlier versions record the abort without stopping the run.
238
+
239
+ Returns: `boolean`. `true` when this process aborted the run locally or can see it executing. The abort request is published either way.
240
+
241
+ #### `abortThreadStream({ threadId, resourceId? })`
242
+
243
+ Aborts the active run on a memory thread with the same abort request as `abortRunStream()`. The run is resolved from this process's thread runtime, so it must have been started here or observed through `subscribeToThread()` on this process. The server route `POST /agents/:agentId/threads/abort` uses this method.
244
+
245
+ ```typescript
246
+ durableAgent.abortThreadStream({ resourceId: 'user-1', threadId: 'thread-1' })
247
+ ```
248
+
249
+ Returns: `boolean`. `false` when this process has no active run recorded for the thread. No abort request is sent in that case.
250
+
222
251
  ### Recovery
223
252
 
253
+ #### `listActiveRuns(options?)`
254
+
255
+ Lists this agent's runs whose persisted snapshot is in `running` status: runs whose agentic loop was mid-execution when the workflow engine last saved state. On a live process they transition to `suspended` or a terminal status. After a crash or restart they stay `running` with nothing driving them, which is what `recoverActiveRuns()` re-drives. Runs started by other durable agents on the same storage aren't included.
256
+
257
+ ```typescript
258
+ const { runs, total } = await durableAgent.listActiveRuns({ resourceId: 'user-1' })
259
+
260
+ for (const run of runs) {
261
+ await durableAgent.recoverActiveRuns({ runId: run.runId })
262
+ }
263
+ ```
264
+
265
+ Reads workflow snapshot storage on the Mastra instance the agent is registered with, and throws if the agent isn't registered with one. Use persistent storage: the default in-memory store loses these rows on the restart that orphans them.
266
+
267
+ Only runs in `running` status are returned. Suspended runs keep their snapshots but aren't included, and finished runs aren't retained. Filter by `resourceId` to scope the list to one user.
268
+
269
+ Returns:
270
+
271
+ ```typescript
272
+ interface DurableAgentListActiveRunsResult {
273
+ runs: Array<{
274
+ runId: string
275
+ status: 'running'
276
+ threadId?: string
277
+ resourceId?: string
278
+ updatedAt: Date
279
+ }>
280
+ total: number
281
+ }
282
+ ```
283
+
284
+ **options.threadId** (`string`): Only return runs that belong to this memory thread.
285
+
286
+ **options.resourceId** (`string`): Only return runs that belong to this memory resource.
287
+
288
+ **options.fromDate** (`Date`): Only return runs created at or after this date.
289
+
290
+ **options.toDate** (`Date`): Only return runs created at or before this date.
291
+
292
+ **options.perPage** (`number`): Runs per page. Applies only when page is also set. Must be a positive integer.
293
+
294
+ **options.page** (`number`): Zero-indexed page number. Applies only when perPage is also set. Must be a non-negative integer.
295
+
224
296
  #### `recoverActiveRuns(options?)`
225
297
 
226
- Discovers runs stuck in `running` status for this agent and re-drives them from the last persisted snapshot. Recovers up to `options.limit` runs (default: 100). Returns a summary of what was recovered.
298
+ Discovers runs stuck in `running` status for this agent and re-drives them from the last persisted snapshot. Accepts the same filters and pagination as `listActiveRuns()`, plus `runId`. Returns a summary of what was recovered.
227
299
 
228
300
  ```typescript
229
301
  const result = await durableAgent.recoverActiveRuns()
@@ -246,11 +318,7 @@ interface DurableAgentRecoverActiveRunsResult {
246
318
  }
247
319
  ```
248
320
 
249
- **options.runId** (`string`): Recover a specific run by ID. When set, discovery filters are ignored.
250
-
251
- **options.limit** (`number`): Maximum number of active runs to discover. Defaults to 100.
252
-
253
- **options.createdBefore** (`Date`): Only recover runs created before this date.
321
+ **options.runId** (`string`): Recover a specific run by ID. When set, the discovery filters and pagination are ignored.
254
322
 
255
323
  #### `recover(runId, options?)`
256
324
 
@@ -272,7 +340,7 @@ Returns: [`Promise<DurableAgentStreamResult>`](#durableagentstreamresult)
272
340
 
273
341
  `stream()` accepts a `DurableAgentStreamOptions` object. It supports the agent execution options below, plus lifecycle callbacks.
274
342
 
275
- **runId** (`string`): Unique identifier for this run. Use it later with resume() or observe().
343
+ **runId** (`string`): Unique identifier for this run. Use it later with resume(), observe(), or abortRunStream().
276
344
 
277
345
  **instructions** (`AgentExecutionOptions['instructions']`): Overrides the agent's default instructions for this run. Accepts a static string or the same dynamic instructions value the agent supports.
278
346
 
@@ -340,7 +408,7 @@ Returns: [`Promise<DurableAgentStreamResult>`](#durableagentstreamresult)
340
408
 
341
409
  **onSuspended** (`(data: AgentSuspendedEventData) => void | Promise<void>`): Called when the run suspends, for example for tool approval.
342
410
 
343
- **onAbort** (`AgentExecutionOptions['onAbort']`): Called when the run is aborted via abortSignal or result.abort(). Receives the steps completed before the abort and, in text, the assistant text streamed so far.
411
+ **onAbort** (`AgentExecutionOptions['onAbort']`): Called when the run is aborted via abortSignal, result.abort(), abortRunStream(), or abortThreadStream(). Receives the steps completed before the abort and, in text, the assistant text streamed so far.
344
412
 
345
413
  **onIterationComplete** (`AgentExecutionOptions['onIterationComplete']`): Called after every agentic-loop iteration with the latest messageList, finishReason, and isFinal flag. Observation-only on durable agents: returning continue: false or feedback does not influence the loop.
346
414
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mastra/mcp-docs-server",
3
- "version": "1.2.23-alpha.5",
3
+ "version": "1.2.23-alpha.6",
4
4
  "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -28,8 +28,8 @@
28
28
  "jsdom": "^26.1.0",
29
29
  "local-pkg": "^1.1.2",
30
30
  "zod": "^4.4.3",
31
- "@mastra/core": "1.63.3-alpha.1",
32
- "@mastra/mcp": "^1.17.2"
31
+ "@mastra/mcp": "^1.17.2",
32
+ "@mastra/core": "1.63.3-alpha.1"
33
33
  },
34
34
  "devDependencies": {
35
35
  "@hono/node-server": "^2.0.0",
@@ -45,8 +45,8 @@
45
45
  "tsx": "^4.23.1",
46
46
  "typescript": "^7.0.2",
47
47
  "vitest": "4.1.10",
48
- "@internal/types-builder": "0.0.104",
49
48
  "@internal/lint": "0.0.129",
49
+ "@internal/types-builder": "0.0.104",
50
50
  "@mastra/core": "1.63.3-alpha.1"
51
51
  },
52
52
  "homepage": "https://mastra.ai",