@mastra/mcp-docs-server 1.2.0-alpha.0 → 1.2.1-alpha.0

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 (102) hide show
  1. package/.docs/docs/agents/goals.md +2 -2
  2. package/.docs/docs/harness/modes.md +2 -2
  3. package/.docs/docs/harness/overview.md +23 -25
  4. package/.docs/docs/harness/session.md +2 -2
  5. package/.docs/docs/harness/subagents.md +3 -3
  6. package/.docs/docs/harness/tool-approvals.md +2 -2
  7. package/.docs/guides/build-your-ui/openui.md +297 -0
  8. package/.docs/models/gateways/custom-gateways.md +12 -0
  9. package/.docs/models/gateways/netlify.md +4 -7
  10. package/.docs/models/gateways/openrouter.md +20 -40
  11. package/.docs/models/gateways/vercel.md +281 -246
  12. package/.docs/models/index.md +1 -1
  13. package/.docs/models/providers/alibaba-cn.md +5 -2
  14. package/.docs/models/providers/alibaba-coding-plan-cn.md +5 -2
  15. package/.docs/models/providers/alibaba-coding-plan.md +5 -2
  16. package/.docs/models/providers/alibaba-token-plan-cn.md +88 -0
  17. package/.docs/models/providers/alibaba-token-plan.md +88 -0
  18. package/.docs/models/providers/alibaba.md +3 -1
  19. package/.docs/models/providers/ambient.md +6 -5
  20. package/.docs/models/providers/anthropic.md +8 -11
  21. package/.docs/models/providers/anyapi.md +99 -0
  22. package/.docs/models/providers/baseten.md +19 -19
  23. package/.docs/models/providers/cerebras.md +5 -7
  24. package/.docs/models/providers/claudinio.md +3 -2
  25. package/.docs/models/providers/cloudflare-workers-ai.md +4 -9
  26. package/.docs/models/providers/cortecs.md +9 -2
  27. package/.docs/models/providers/crof.md +12 -10
  28. package/.docs/models/providers/deepinfra.md +18 -31
  29. package/.docs/models/providers/deepseek.md +1 -1
  30. package/.docs/models/providers/digitalocean.md +5 -1
  31. package/.docs/models/providers/fastrouter.md +34 -2
  32. package/.docs/models/providers/fireworks-ai.md +22 -27
  33. package/.docs/models/providers/freemodel.md +108 -0
  34. package/.docs/models/providers/google.md +7 -9
  35. package/.docs/models/providers/groq.md +7 -9
  36. package/.docs/models/providers/helicone.md +1 -1
  37. package/.docs/models/providers/hpc-ai.md +3 -3
  38. package/.docs/models/providers/huggingface.md +1 -1
  39. package/.docs/models/providers/kilo.md +9 -8
  40. package/.docs/models/providers/kimi-for-coding.md +4 -3
  41. package/.docs/models/providers/llmgateway.md +38 -29
  42. package/.docs/models/providers/llmtr.md +76 -0
  43. package/.docs/models/providers/lucidquery.md +11 -9
  44. package/.docs/models/providers/minimax-cn-coding-plan.md +3 -2
  45. package/.docs/models/providers/minimax-cn.md +3 -2
  46. package/.docs/models/providers/minimax-coding-plan.md +3 -2
  47. package/.docs/models/providers/minimax.md +3 -2
  48. package/.docs/models/providers/mistral.md +25 -31
  49. package/.docs/models/providers/moonshotai-cn.md +13 -11
  50. package/.docs/models/providers/moonshotai.md +13 -11
  51. package/.docs/models/providers/nano-gpt.md +621 -529
  52. package/.docs/models/providers/nearai.md +5 -1
  53. package/.docs/models/providers/nebius.md +2 -15
  54. package/.docs/models/providers/neon.md +96 -0
  55. package/.docs/models/providers/neuralwatt.md +19 -20
  56. package/.docs/models/providers/novita-ai.md +7 -2
  57. package/.docs/models/providers/nvidia.md +5 -14
  58. package/.docs/models/providers/ollama-cloud.md +8 -12
  59. package/.docs/models/providers/openai.md +2 -3
  60. package/.docs/models/providers/opencode-go.md +10 -9
  61. package/.docs/models/providers/opencode.md +7 -2
  62. package/.docs/models/providers/ovhcloud.md +7 -3
  63. package/.docs/models/providers/poe.md +2 -1
  64. package/.docs/models/providers/poolside.md +72 -0
  65. package/.docs/models/providers/routing-run.md +5 -3
  66. package/.docs/models/providers/scaleway.md +3 -5
  67. package/.docs/models/providers/siliconflow-cn.md +4 -11
  68. package/.docs/models/providers/siliconflow.md +7 -13
  69. package/.docs/models/providers/snowflake-cortex.md +89 -0
  70. package/.docs/models/providers/stepfun-ai.md +5 -5
  71. package/.docs/models/providers/stepfun.md +1 -1
  72. package/.docs/models/providers/synthetic.md +2 -1
  73. package/.docs/models/providers/togetherai.md +30 -24
  74. package/.docs/models/providers/umans-ai-coding-plan.md +3 -2
  75. package/.docs/models/providers/umans-ai.md +75 -0
  76. package/.docs/models/providers/vivgrid.md +1 -1
  77. package/.docs/models/providers/vultr.md +14 -12
  78. package/.docs/models/providers/wafer.ai.md +9 -4
  79. package/.docs/models/providers/xai.md +3 -3
  80. package/.docs/models/providers/xiaomi-token-plan-ams.md +15 -13
  81. package/.docs/models/providers/xiaomi-token-plan-cn.md +15 -13
  82. package/.docs/models/providers/xiaomi-token-plan-sgp.md +15 -13
  83. package/.docs/models/providers/xiaomi.md +10 -9
  84. package/.docs/models/providers/xpersona.md +4 -3
  85. package/.docs/models/providers/zai-coding-plan.md +2 -1
  86. package/.docs/models/providers/zai.md +2 -1
  87. package/.docs/models/providers/zeldoc.md +71 -0
  88. package/.docs/models/providers/zenmux.md +19 -3
  89. package/.docs/models/providers/zhipuai-coding-plan.md +3 -1
  90. package/.docs/models/providers/zhipuai.md +2 -1
  91. package/.docs/models/providers.md +12 -3
  92. package/.docs/reference/agents/agent.md +18 -5
  93. package/.docs/reference/harness/harness-class.md +3 -137
  94. package/.docs/reference/harness/session.md +128 -2
  95. package/.docs/reference/index.md +1 -0
  96. package/.docs/reference/tools/mcp-client.md +11 -0
  97. package/.docs/reference/voice/google-gemini-live.md +22 -0
  98. package/.docs/reference/workspace/archil-filesystem.md +203 -0
  99. package/.docs/reference/workspace/gcs-filesystem.md +1 -0
  100. package/.docs/reference/workspace/s3-filesystem.md +1 -0
  101. package/CHANGELOG.md +20 -0
  102. package/package.json +6 -6
package/.docs/models/providers/nearai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![NEAR AI Cloud logo](https://models.dev/logos/nearai.svg)NEAR AI Cloud
2
2
 
3
- Access 33 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
3
+ Access 37 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [NEAR AI Cloud documentation](https://docs.near.ai/).
6
6
 
@@ -43,7 +43,10 @@ for await (const chunk of stream) {
43
43
  | `nearai/google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
44
44
  | `nearai/google/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
45
45
  | `nearai/google/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
46
+ | `nearai/google/gemini-3-pro` | 1.0M | | | | | | $1 | $15 |
46
47
  | `nearai/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
48
+ | `nearai/google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
49
+ | `nearai/google/gemma-4-31B-it` | 262K | | | | | | $0.13 | $0.40 |
47
50
  | `nearai/openai/gpt-4.1` | 1.0M | | | | | | $2 | $8 |
48
51
  | `nearai/openai/gpt-4.1-mini` | 1.0M | | | | | | $0.40 | $2 |
49
52
  | `nearai/openai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
@@ -66,6 +69,7 @@ for await (const chunk of stream) {
66
69
  | `nearai/Qwen/Qwen3-Reranker-0.6B` | 41K | | | | | | $0.01 | $0.01 |
67
70
  | `nearai/Qwen/Qwen3-VL-30B-A3B-Instruct` | 256K | | | | | | $0.15 | $0.55 |
68
71
  | `nearai/Qwen/Qwen3.5-122B-A10B` | 131K | | | | | | $0.40 | $3 |
72
+ | `nearai/Qwen/Qwen3.6-35B-A3B-FP8` | 262K | | | | | | $0.17 | $1 |
69
73
  | `nearai/zai-org/GLM-5.1-FP8` | 203K | | | | | | $0.85 | $3 |
70
74
 
71
75
  ## Advanced configuration
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 31 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
3
+ Access 18 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
 
@@ -34,17 +34,10 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
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
37
  | `nebius/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $4 |
40
- | `nebius/google/gemma-2-2b-it` | 8K | | | | | | $0.02 | $0.06 |
41
38
  | `nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
42
39
  | `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
40
  | `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
41
  | `nebius/NousResearch/Hermes-4-405B` | 128K | | | | | | $1 | $3 |
49
42
  | `nebius/NousResearch/Hermes-4-70B` | 128K | | | | | | $0.13 | $0.40 |
50
43
  | `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1` | 128K | | | | | | $0.60 | $2 |
@@ -52,19 +45,13 @@ for await (const chunk of stream) {
52
45
  | `nebius/nvidia/nemotron-3-super-120b-a12b` | 256K | | | | | | $0.30 | $0.90 |
53
46
  | `nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B` | 32K | | | | | | $0.06 | $0.24 |
54
47
  | `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
48
  | `nebius/Qwen/Qwen2.5-VL-72B-Instruct` | 128K | | | | | | $0.25 | $0.75 |
58
49
  | `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
50
  | `nebius/Qwen/Qwen3-30B-A3B-Instruct-2507` | 128K | | | | | | $0.10 | $0.30 |
61
51
  | `nebius/Qwen/Qwen3-32B` | 128K | | | | | | $0.10 | $0.30 |
62
52
  | `nebius/Qwen/Qwen3-Embedding-8B` | 33K | | | | | | $0.01 | — |
63
53
  | `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
54
  | `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 |
68
55
 
69
56
  ## Advanced configuration
70
57
 
@@ -94,7 +81,7 @@ const agent = new Agent({
94
81
  model: ({ requestContext }) => {
95
82
  const useAdvanced = requestContext.task === "complex";
96
83
  return useAdvanced
97
- ? "nebius/zai-org/GLM-5"
84
+ ? "nebius/openai/gpt-oss-120b"
98
85
  : "nebius/MiniMaxAI/MiniMax-M2.5";
99
86
  }
100
87
  });
package/.docs/models/providers/neon.md ADDED
@@ -0,0 +1,96 @@
1
+ # ![Neon logo](https://models.dev/logos/neon.svg)Neon
2
+
3
+ Access 25 Neon models through Mastra's model router. Authentication is handled automatically using the `NEON_AI_GATEWAY_TOKEN` environment variable. Configure `NEON_AI_GATEWAY_BASE_URL` as well.
4
+
5
+ Learn more in the [Neon documentation](https://neon.com/docs).
6
+
7
+ ```bash
8
+ NEON_AI_GATEWAY_BASE_URL=your-value
9
+ NEON_AI_GATEWAY_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: "neon/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 [Neon documentation](https://neon.com/docs) for details.
33
+
34
+ ## Models
35
+
36
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
37
+ | ---------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
38
+ | `neon/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
39
+ | `neon/claude-opus-4-1` | 200K | | | | | | $15 | $75 |
40
+ | `neon/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
+ | `neon/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
42
+ | `neon/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
43
+ | `neon/claude-sonnet-4` | 200K | | | | | | $3 | $15 |
44
+ | `neon/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
45
+ | `neon/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
46
+ | `neon/gemini-2-5-flash` | 1.0M | | | | | | $0.30 | $3 |
47
+ | `neon/gemini-2-5-pro` | 1.0M | | | | | | $1 | $10 |
48
+ | `neon/gemini-3-1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
49
+ | `neon/gemini-3-1-pro` | 1.0M | | | | | | $2 | $12 |
50
+ | `neon/gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
51
+ | `neon/gemini-3-pro` | 1.0M | | | | | | $2 | $12 |
52
+ | `neon/gpt-5` | 400K | | | | | | $1 | $10 |
53
+ | `neon/gpt-5-1` | 400K | | | | | | $1 | $10 |
54
+ | `neon/gpt-5-2` | 400K | | | | | | $2 | $14 |
55
+ | `neon/gpt-5-4` | 1.1M | | | | | | $3 | $15 |
56
+ | `neon/gpt-5-4-mini` | 400K | | | | | | $0.75 | $5 |
57
+ | `neon/gpt-5-4-nano` | 400K | | | | | | $0.20 | $1 |
58
+ | `neon/gpt-5-5` | 1.1M | | | | | | $5 | $30 |
59
+ | `neon/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
60
+ | `neon/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
61
+ | `neon/gpt-oss-120b` | 131K | | | | | | $0.07 | $0.28 |
62
+ | `neon/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
63
+
64
+ ## Advanced configuration
65
+
66
+ ### Custom headers
67
+
68
+ ```typescript
69
+ const agent = new Agent({
70
+ id: "custom-agent",
71
+ name: "custom-agent",
72
+ model: {
73
+ url: "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1",
74
+ id: "neon/claude-haiku-4-5",
75
+ apiKey: process.env.NEON_AI_GATEWAY_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
+ ? "neon/gpt-oss-20b"
93
+ : "neon/claude-haiku-4-5";
94
+ }
95
+ });
96
+ ```
package/.docs/models/providers/neuralwatt.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Neuralwatt logo](https://models.dev/logos/neuralwatt.svg)Neuralwatt
2
2
 
3
- Access 14 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
3
+ Access 13 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).
6
6
 
@@ -15,7 +15,7 @@ const agent = new Agent({
15
15
  id: "my-agent",
16
16
  name: "My Agent",
17
17
  instructions: "You are a helpful assistant",
18
- model: "neuralwatt/MiniMaxAI/MiniMax-M2.5"
18
+ model: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -32,22 +32,21 @@ 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
- | `neuralwatt/glm-5-fast` | 203K | | | | | | $1 | $4 |
38
- | `neuralwatt/glm-5.1-fast` | 203K | | | | | | $1 | $4 |
39
- | `neuralwatt/kimi-k2.5-fast` | 262K | | | | | | $0.52 | $3 |
40
- | `neuralwatt/kimi-k2.6-fast` | 262K | | | | | | $0.69 | $3 |
41
- | `neuralwatt/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.35 | $1 |
42
- | `neuralwatt/mistralai/Devstral-Small-2-24B-Instruct-2512` | 262K | | | | | | $0.12 | $0.35 |
43
- | `neuralwatt/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.52 | $3 |
44
- | `neuralwatt/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.69 | $3 |
45
- | `neuralwatt/openai/gpt-oss-20b` | 16K | | | | | | $0.03 | $0.16 |
46
- | `neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8` | 262K | | | | | | $0.69 | $4 |
47
- | `neuralwatt/Qwen/Qwen3.6-35B-A3B` | 131K | | | | | | $0.05 | $0.10 |
48
- | `neuralwatt/qwen3.5-397b-fast` | 262K | | | | | | $0.69 | $4 |
49
- | `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.05 | $0.10 |
50
- | `neuralwatt/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
35
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
+ | --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
+ | `neuralwatt/glm-5-fast` | 203K | | | | | | $1 | $4 |
38
+ | `neuralwatt/glm-5.1-fast` | 203K | | | | | | $1 | $4 |
39
+ | `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
40
+ | `neuralwatt/kimi-k2.5-fast` | 262K | | | | | | $0.52 | $3 |
41
+ | `neuralwatt/kimi-k2.6-fast` | 262K | | | | | | $0.69 | $3 |
42
+ | `neuralwatt/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.52 | $3 |
43
+ | `neuralwatt/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.69 | $3 |
44
+ | `neuralwatt/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
45
+ | `neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8` | 262K | | | | | | $0.69 | $4 |
46
+ | `neuralwatt/Qwen/Qwen3.6-35B-A3B` | 131K | | | | | | $0.29 | $1 |
47
+ | `neuralwatt/qwen3.5-397b-fast` | 262K | | | | | | $0.69 | $4 |
48
+ | `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
49
+ | `neuralwatt/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
51
50
 
52
51
  ## Advanced configuration
53
52
 
@@ -59,7 +58,7 @@ const agent = new Agent({
59
58
  name: "custom-agent",
60
59
  model: {
61
60
  url: "https://api.neuralwatt.com/v1",
62
- id: "neuralwatt/MiniMaxAI/MiniMax-M2.5",
61
+ id: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8",
63
62
  apiKey: process.env.NEURALWATT_API_KEY,
64
63
  headers: {
65
64
  "X-Custom-Header": "value"
@@ -78,7 +77,7 @@ const agent = new Agent({
78
77
  const useAdvanced = requestContext.task === "complex";
79
78
  return useAdvanced
80
79
  ? "neuralwatt/zai-org/GLM-5.1-FP8"
81
- : "neuralwatt/MiniMaxAI/MiniMax-M2.5";
80
+ : "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8";
82
81
  }
83
82
  });
84
83
  ```
package/.docs/models/providers/novita-ai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![NovitaAI logo](https://models.dev/logos/novita-ai.svg)NovitaAI
2
2
 
3
- Access 99 NovitaAI models through Mastra's model router. Authentication is handled automatically using the `NOVITA_API_KEY` environment variable.
3
+ Access 104 NovitaAI models through Mastra's model router. Authentication is handled automatically using the `NOVITA_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [NovitaAI documentation](https://novita.ai/docs/guides/introduction).
6
6
 
@@ -38,7 +38,7 @@ for await (const chunk of stream) {
38
38
  | `novita-ai/baidu/ernie-4.5-21B-a3b` | 120K | | | | | | $0.07 | $0.28 |
39
39
  | `novita-ai/baidu/ernie-4.5-21B-a3b-thinking` | 131K | | | | | | $0.07 | $0.28 |
40
40
  | `novita-ai/baidu/ernie-4.5-300b-a47b-paddle` | 123K | | | | | | $0.28 | $1 |
41
- | `novita-ai/baidu/ernie-4.5-vl-28b-a3b` | 30K | | | | | | $1 | $6 |
41
+ | `novita-ai/baidu/ernie-4.5-vl-28b-a3b` | 30K | | | | | | $0.14 | $0.56 |
42
42
  | `novita-ai/baidu/ernie-4.5-vl-28b-a3b-thinking` | 131K | | | | | | $0.39 | $0.39 |
43
43
  | `novita-ai/baidu/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
44
44
  | `novita-ai/deepseek/deepseek-ocr` | 8K | | | | | | $0.03 | $0.03 |
@@ -65,6 +65,7 @@ for await (const chunk of stream) {
65
65
  | `novita-ai/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.09 | $0.09 |
66
66
  | `novita-ai/inclusionai/ling-2.6-1t` | 262K | | | | | | — | — |
67
67
  | `novita-ai/inclusionai/ling-2.6-flash` | 262K | | | | | | $0.10 | $0.30 |
68
+ | `novita-ai/inclusionai/ring-2.6-1t` | 262K | | | | | | $0.30 | $3 |
68
69
  | `novita-ai/kwaipilot/kat-coder-pro` | 256K | | | | | | $0.30 | $1 |
69
70
  | `novita-ai/meta-llama/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
70
71
  | `novita-ai/meta-llama/llama-3-8b-instruct` | 8K | | | | | | $0.04 | $0.04 |
@@ -79,6 +80,7 @@ for await (const chunk of stream) {
79
80
  | `novita-ai/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
80
81
  | `novita-ai/minimax/minimax-m2.5-highspeed` | 205K | | | | | | $0.60 | $2 |
81
82
  | `novita-ai/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
83
+ | `novita-ai/minimax/minimax-m2.7-highspeed` | 205K | | | | | | $0.60 | $2 |
82
84
  | `novita-ai/minimaxai/minimax-m1-80k` | 1.0M | | | | | | $0.55 | $2 |
83
85
  | `novita-ai/mistralai/mistral-nemo` | 60K | | | | | | $0.04 | $0.17 |
84
86
  | `novita-ai/moonshotai/kimi-k2-0905` | 262K | | | | | | $0.60 | $3 |
@@ -118,11 +120,14 @@ for await (const chunk of stream) {
118
120
  | `novita-ai/qwen/qwen3.5-27b` | 262K | | | | | | $0.30 | $2 |
119
121
  | `novita-ai/qwen/qwen3.5-35b-a3b` | 262K | | | | | | $0.25 | $2 |
120
122
  | `novita-ai/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.60 | $4 |
123
+ | `novita-ai/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
121
124
  | `novita-ai/sao10K/l3-70b-euryale-v2.1` | 8K | | | | | | $1 | $1 |
122
125
  | `novita-ai/sao10K/l3-8b-lunaris` | 8K | | | | | | $0.05 | $0.05 |
123
126
  | `novita-ai/sao10K/L3-8B-stheno-v3.2` | 8K | | | | | | $0.05 | $0.05 |
124
127
  | `novita-ai/sao10K/l31-70b-euryale-v2.2` | 8K | | | | | | $1 | $1 |
125
128
  | `novita-ai/xiaomimimo/mimo-v2-flash` | 262K | | | | | | $0.10 | $0.30 |
129
+ | `novita-ai/xiaomimimo/mimo-v2-pro` | 1.0M | | | | | | $2 | $6 |
130
+ | `novita-ai/xiaomimimo/mimo-v2.5-pro` | 1.0M | | | | | | $2 | $6 |
126
131
  | `novita-ai/zai-org/autoglm-phone-9b-multilingual` | 66K | | | | | | $0.04 | $0.14 |
127
132
  | `novita-ai/zai-org/glm-4.5` | 131K | | | | | | $0.60 | $2 |
128
133
  | `novita-ai/zai-org/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
package/.docs/models/providers/nvidia.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Nvidia logo](https://models.dev/logos/nvidia.svg)Nvidia
2
2
 
3
- Access 92 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
3
+ Access 83 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
6
6
 
@@ -41,12 +41,9 @@ for await (const chunk of stream) {
41
41
  | `nvidia/black-forest-labs/flux_2-klein-4b` | 41K | | | | | | — | — |
42
42
  | `nvidia/black-forest-labs/flux.1-dev` | 4K | | | | | | — | — |
43
43
  | `nvidia/bytedance/seed-oss-36b-instruct` | 262K | | | | | | — | — |
44
- | `nvidia/deepseek-ai/deepseek-v3.1-terminus` | 128K | | | | | | — | — |
45
- | `nvidia/deepseek-ai/deepseek-v3.2` | 164K | | | | | | — | — |
46
44
  | `nvidia/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
47
- | `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
45
+ | `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
48
46
  | `nvidia/google/gemma-2-2b-it` | 128K | | | | | | — | — |
49
- | `nvidia/google/gemma-3-27b-it` | 131K | | | | | | — | — |
50
47
  | `nvidia/google/gemma-3n-e2b-it` | 128K | | | | | | — | — |
51
48
  | `nvidia/google/gemma-3n-e4b-it` | 128K | | | | | | — | — |
52
49
  | `nvidia/google/gemma-4-31b-it` | 256K | | | | | | — | — |
@@ -64,9 +61,7 @@ for await (const chunk of stream) {
64
61
  | `nvidia/meta/llama-guard-4-12b` | 128K | | | | | | — | — |
65
62
  | `nvidia/microsoft/phi-4-mini-instruct` | 131K | | | | | | — | — |
66
63
  | `nvidia/microsoft/phi-4-multimodal-instruct` | 128K | | | | | | — | — |
67
- | `nvidia/minimaxai/minimax-m2.5` | 205K | | | | | | — | — |
68
64
  | `nvidia/minimaxai/minimax-m2.7` | 205K | | | | | | — | — |
69
- | `nvidia/mistralai/devstral-2-123b-instruct-2512` | 262K | | | | | | — | — |
70
65
  | `nvidia/mistralai/magistral-small-2506` | 33K | | | | | | — | — |
71
66
  | `nvidia/mistralai/mistral-7b-instruct-v03` | 66K | | | | | | — | — |
72
67
  | `nvidia/mistralai/mistral-large-3-675b-instruct-2512` | 262K | | | | | | — | — |
@@ -75,9 +70,7 @@ for await (const chunk of stream) {
75
70
  | `nvidia/mistralai/mistral-small-4-119b-2603` | 128K | | | | | | — | — |
76
71
  | `nvidia/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | — | — |
77
72
  | `nvidia/mistralai/mixtral-8x7b-instruct` | 33K | | | | | | — | — |
78
- | `nvidia/moonshotai/kimi-k2-instruct` | 128K | | | | | | — | — |
79
73
  | `nvidia/moonshotai/kimi-k2-instruct-0905` | 262K | | | | | | — | — |
80
- | `nvidia/moonshotai/kimi-k2-thinking` | 262K | | | | | | — | — |
81
74
  | `nvidia/moonshotai/kimi-k2.6` | 262K | | | | | | — | — |
82
75
  | `nvidia/nvidia/active-speaker-detection` | — | | | | | | — | — |
83
76
  | `nvidia/nvidia/bevformer` | 128K | | | | | | — | — |
@@ -87,8 +80,6 @@ for await (const chunk of stream) {
87
80
  | `nvidia/nvidia/gliner-pii` | 128K | | | | | | — | — |
88
81
  | `nvidia/nvidia/llama-3_1-nemotron-safety-guard-8b-v3` | 128K | | | | | | — | — |
89
82
  | `nvidia/nvidia/llama-3_2-nemoretriever-300m-embed-v1` | 33K | | | | | | — | — |
90
- | `nvidia/nvidia/llama-3_3-nemotron-super-49b-v1` | 131K | | | | | | — | — |
91
- | `nvidia/nvidia/llama-3_3-nemotron-super-49b-v1_5` | 131K | | | | | | — | — |
92
83
  | `nvidia/nvidia/llama-nemotron-embed-vl-1b-v2` | 33K | | | | | | — | — |
93
84
  | `nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2` | 128K | | | | | | — | — |
94
85
  | `nvidia/nvidia/magpie-tts-zeroshot` | — | | | | | | — | — |
@@ -96,6 +87,7 @@ for await (const chunk of stream) {
96
87
  | `nvidia/nvidia/nemotron-3-nano-30b-a3b` | 131K | | | | | | — | — |
97
88
  | `nvidia/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` | 256K | | | | | | — | — |
98
89
  | `nvidia/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.20 | $0.80 |
90
+ | `nvidia/nvidia/nemotron-3-ultra-550b-a55b` | 1.0M | | | | | | $0.50 | $3 |
99
91
  | `nvidia/nvidia/nemotron-content-safety-reasoning-4b` | 128K | | | | | | — | — |
100
92
  | `nvidia/nvidia/nemotron-mini-4b-instruct` | 128K | | | | | | — | — |
101
93
  | `nvidia/nvidia/nemotron-voicechat` | 128K | | | | | | — | — |
@@ -118,14 +110,13 @@ for await (const chunk of stream) {
118
110
  | `nvidia/qwen/qwen2.5-coder-32b-instruct` | 128K | | | | | | — | — |
119
111
  | `nvidia/qwen/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | — | — |
120
112
  | `nvidia/qwen/qwen3-next-80b-a3b-instruct` | 262K | | | | | | — | — |
121
- | `nvidia/qwen/qwen3-next-80b-a3b-thinking` | 262K | | | | | | — | — |
122
113
  | `nvidia/qwen/qwen3.5-122b-a10b` | 262K | | | | | | — | — |
123
114
  | `nvidia/qwen/qwen3.5-397b-a17b` | 262K | | | | | | — | — |
124
115
  | `nvidia/sarvamai/sarvam-m` | 128K | | | | | | — | — |
125
116
  | `nvidia/stepfun-ai/step-3.5-flash` | 256K | | | | | | — | — |
117
+ | `nvidia/stepfun-ai/step-3.7-flash` | 256K | | | | | | — | — |
126
118
  | `nvidia/upstage/solar-10_7b-instruct` | 128K | | | | | | — | — |
127
119
  | `nvidia/z-ai/glm-5.1` | 131K | | | | | | — | — |
128
- | `nvidia/z-ai/glm4.7` | 205K | | | | | | — | — |
129
120
 
130
121
  ## Advanced configuration
131
122
 
@@ -155,7 +146,7 @@ const agent = new Agent({
155
146
  model: ({ requestContext }) => {
156
147
  const useAdvanced = requestContext.task === "complex";
157
148
  return useAdvanced
158
- ? "nvidia/z-ai/glm4.7"
149
+ ? "nvidia/z-ai/glm-5.1"
159
150
  : "nvidia/abacusai/dracarys-llama-3_1-70b-instruct";
160
151
  }
161
152
  });
package/.docs/models/providers/ollama-cloud.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Ollama Cloud logo](https://models.dev/logos/ollama-cloud.svg)Ollama Cloud
2
2
 
3
- Access 39 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
3
+ Access 35 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
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: "ollama-cloud/cogito-2.1:671b"
18
+ model: "ollama-cloud/deepseek-v3.1:671b"
19
19
  });
20
20
 
21
21
  // Generate a response
@@ -34,7 +34,6 @@ for await (const chunk of stream) {
34
34
 
35
35
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
36
  | ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `ollama-cloud/cogito-2.1:671b` | 164K | | | | | | — | — |
38
37
  | `ollama-cloud/deepseek-v3.1:671b` | 164K | | | | | | — | — |
39
38
  | `ollama-cloud/deepseek-v3.2` | 164K | | | | | | — | — |
40
39
  | `ollama-cloud/deepseek-v4-flash` | 1.0M | | | | | | — | — |
@@ -46,31 +45,28 @@ for await (const chunk of stream) {
46
45
  | `ollama-cloud/gemma3:27b` | 131K | | | | | | — | — |
47
46
  | `ollama-cloud/gemma3:4b` | 131K | | | | | | — | — |
48
47
  | `ollama-cloud/gemma4:31b` | 262K | | | | | | — | — |
49
- | `ollama-cloud/glm-4.6` | 203K | | | | | | — | — |
50
48
  | `ollama-cloud/glm-4.7` | 203K | | | | | | — | — |
51
49
  | `ollama-cloud/glm-5` | 203K | | | | | | — | — |
52
50
  | `ollama-cloud/glm-5.1` | 203K | | | | | | — | — |
51
+ | `ollama-cloud/glm-5.2` | 976K | | | | | | — | — |
53
52
  | `ollama-cloud/gpt-oss:120b` | 131K | | | | | | — | — |
54
53
  | `ollama-cloud/gpt-oss:20b` | 131K | | | | | | — | — |
55
- | `ollama-cloud/kimi-k2-thinking` | 262K | | | | | | — | — |
56
- | `ollama-cloud/kimi-k2:1t` | 262K | | | | | | — | — |
57
54
  | `ollama-cloud/kimi-k2.5` | 262K | | | | | | — | — |
58
55
  | `ollama-cloud/kimi-k2.6` | 262K | | | | | | — | — |
59
- | `ollama-cloud/minimax-m2` | 205K | | | | | | — | — |
56
+ | `ollama-cloud/kimi-k2.7-code` | 262K | | | | | | — | — |
60
57
  | `ollama-cloud/minimax-m2.1` | 205K | | | | | | — | — |
61
58
  | `ollama-cloud/minimax-m2.5` | 205K | | | | | | — | — |
62
59
  | `ollama-cloud/minimax-m2.7` | 197K | | | | | | — | — |
60
+ | `ollama-cloud/minimax-m3` | 512K | | | | | | — | — |
63
61
  | `ollama-cloud/ministral-3:14b` | 262K | | | | | | — | — |
64
62
  | `ollama-cloud/ministral-3:3b` | 262K | | | | | | — | — |
65
63
  | `ollama-cloud/ministral-3:8b` | 262K | | | | | | — | — |
66
64
  | `ollama-cloud/mistral-large-3:675b` | 262K | | | | | | — | — |
67
65
  | `ollama-cloud/nemotron-3-nano:30b` | 1.0M | | | | | | — | — |
68
66
  | `ollama-cloud/nemotron-3-super` | 262K | | | | | | — | — |
67
+ | `ollama-cloud/nemotron-3-ultra` | 262K | | | | | | — | — |
69
68
  | `ollama-cloud/qwen3-coder-next` | 262K | | | | | | — | — |
70
69
  | `ollama-cloud/qwen3-coder:480b` | 262K | | | | | | — | — |
71
- | `ollama-cloud/qwen3-next:80b` | 262K | | | | | | — | — |
72
- | `ollama-cloud/qwen3-vl:235b` | 262K | | | | | | — | — |
73
- | `ollama-cloud/qwen3-vl:235b-instruct` | 262K | | | | | | — | — |
74
70
  | `ollama-cloud/qwen3.5:397b` | 262K | | | | | | — | — |
75
71
  | `ollama-cloud/rnj-1:8b` | 33K | | | | | | — | — |
76
72
 
@@ -84,7 +80,7 @@ const agent = new Agent({
84
80
  name: "custom-agent",
85
81
  model: {
86
82
  url: "https://ollama.com/v1",
87
- id: "ollama-cloud/cogito-2.1:671b",
83
+ id: "ollama-cloud/deepseek-v3.1:671b",
88
84
  apiKey: process.env.OLLAMA_API_KEY,
89
85
  headers: {
90
86
  "X-Custom-Header": "value"
@@ -103,7 +99,7 @@ const agent = new Agent({
103
99
  const useAdvanced = requestContext.task === "complex";
104
100
  return useAdvanced
105
101
  ? "ollama-cloud/rnj-1:8b"
106
- : "ollama-cloud/cogito-2.1:671b";
102
+ : "ollama-cloud/deepseek-v3.1:671b";
107
103
  }
108
104
  });
109
105
  ```
package/.docs/models/providers/openai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OpenAI logo](https://models.dev/logos/openai.svg)OpenAI
2
2
 
3
- Access 52 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
3
+ Access 51 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [OpenAI documentation](https://platform.openai.com/docs/models).
6
6
 
@@ -71,9 +71,8 @@ for await (const chunk of stream) {
71
71
  | `openai/gpt-image-1` | — | | | | | | — | — |
72
72
  | `openai/gpt-image-1-mini` | — | | | | | | — | — |
73
73
  | `openai/gpt-image-1.5` | — | | | | | | — | — |
74
+ | `openai/gpt-image-2` | — | | | | | | $5 | $30 |
74
75
  | `openai/o1` | 200K | | | | | | $15 | $60 |
75
- | `openai/o1-mini` | 128K | | | | | | $1 | $4 |
76
- | `openai/o1-preview` | 128K | | | | | | $15 | $60 |
77
76
  | `openai/o1-pro` | 200K | | | | | | $150 | $600 |
78
77
  | `openai/o3` | 200K | | | | | | $2 | $8 |
79
78
  | `openai/o3-deep-research` | 200K | | | | | | $10 | $40 |
package/.docs/models/providers/opencode-go.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OpenCode Go logo](https://models.dev/logos/opencode-go.svg)OpenCode Go
2
2
 
3
- Access 12 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
3
+ Access 13 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/zen).
6
6
 
@@ -36,16 +36,17 @@ for await (const chunk of stream) {
36
36
  | ------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
37
  | `opencode-go/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
38
38
  | `opencode-go/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
39
- | `opencode-go/glm-5` | 203K | | | | | | $1 | $3 |
40
39
  | `opencode-go/glm-5.1` | 203K | | | | | | $1 | $4 |
41
- | `opencode-go/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
40
+ | `opencode-go/glm-5.2` | 1.0M | | | | | | $1 | $4 |
42
41
  | `opencode-go/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
43
- | `opencode-go/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
44
- | `opencode-go/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
45
- | `opencode-go/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
42
+ | `opencode-go/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
43
+ | `opencode-go/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
44
+ | `opencode-go/mimo-v2.5-pro` | 1.0M | | | | | | $2 | $3 |
46
45
  | `opencode-go/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
47
- | `opencode-go/qwen3.5-plus` | 262K | | | | | | $0.20 | $1 |
48
- | `opencode-go/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
46
+ | `opencode-go/minimax-m3` | 512K | | | | | | $0.10 | $0.40 |
47
+ | `opencode-go/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
48
+ | `opencode-go/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
49
+ | `opencode-go/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
49
50
 
50
51
  ## Advanced configuration
51
52
 
@@ -75,7 +76,7 @@ const agent = new Agent({
75
76
  model: ({ requestContext }) => {
76
77
  const useAdvanced = requestContext.task === "complex";
77
78
  return useAdvanced
78
- ? "opencode-go/qwen3.6-plus"
79
+ ? "opencode-go/qwen3.7-plus"
79
80
  : "opencode-go/deepseek-v4-flash";
80
81
  }
81
82
  });
package/.docs/models/providers/opencode.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
2
2
 
3
- Access 40 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
3
+ Access 45 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
6
6
 
@@ -40,10 +40,13 @@ for await (const chunk of stream) {
40
40
  | `opencode/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
41
41
  | `opencode/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
42
42
  | `opencode/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
43
+ | `opencode/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
43
44
  | `opencode/claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
44
45
  | `opencode/claude-sonnet-4-5` | 1.0M | | | | | | $3 | $15 |
45
46
  | `opencode/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
47
+ | `opencode/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
46
48
  | `opencode/deepseek-v4-flash-free` | 200K | | | | | | — | — |
49
+ | `opencode/deepseek-v4-pro` | 1.0M | | | | | | $2 | $4 |
47
50
  | `opencode/gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
48
51
  | `opencode/gemini-3.1-pro` | 1.0M | | | | | | $2 | $12 |
49
52
  | `opencode/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
@@ -69,9 +72,11 @@ for await (const chunk of stream) {
69
72
  | `opencode/grok-build-0.1` | 256K | | | | | | $1 | $2 |
70
73
  | `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
71
74
  | `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
75
+ | `opencode/mimo-v2.5-free` | 200K | | | | | | — | — |
72
76
  | `opencode/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
73
77
  | `opencode/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
74
- | `opencode/nemotron-3-super-free` | 205K | | | | | | — | — |
78
+ | `opencode/nemotron-3-ultra-free` | 1.0M | | | | | | — | — |
79
+ | `opencode/north-mini-code-free` | 256K | | | | | | — | — |
75
80
  | `opencode/qwen3.5-plus` | 262K | | | | | | $0.20 | $1 |
76
81
  | `opencode/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
77
82
 
package/.docs/models/providers/ovhcloud.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OVHcloud AI Endpoints logo](https://models.dev/logos/ovhcloud.svg)OVHcloud AI Endpoints
2
2
 
3
- Access 11 OVHcloud AI Endpoints models through Mastra's model router. Authentication is handled automatically using the `OVHCLOUD_API_KEY` environment variable.
3
+ Access 15 OVHcloud AI Endpoints models through Mastra's model router. Authentication is handled automatically using the `OVHCLOUD_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [OVHcloud AI Endpoints documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//).
6
6
 
@@ -44,7 +44,11 @@ for await (const chunk of stream) {
44
44
  | `ovhcloud/qwen2.5-vl-72b-instruct` | 33K | | | | | | $1 | $1 |
45
45
  | `ovhcloud/qwen3-32b` | 33K | | | | | | $0.09 | $0.25 |
46
46
  | `ovhcloud/qwen3-coder-30b-a3b-instruct` | 262K | | | | | | $0.07 | $0.26 |
47
- | `ovhcloud/qwen3.5-9b` | 262K | | | | | | $0.10 | $0.15 |
47
+ | `ovhcloud/qwen3.5-397b-a17b` | 262K | | | | | | $0.71 | $4 |
48
+ | `ovhcloud/qwen3.5-9b` | 262K | | | | | | $0.12 | $0.18 |
49
+ | `ovhcloud/qwen3.6-27b` | 262K | | | | | | $0.47 | $3 |
50
+ | `ovhcloud/qwen3guard-gen-0.6b` | 33K | | | | | | — | — |
51
+ | `ovhcloud/qwen3guard-gen-8b` | 33K | | | | | | — | — |
48
52
 
49
53
  ## Advanced configuration
50
54
 
@@ -74,7 +78,7 @@ const agent = new Agent({
74
78
  model: ({ requestContext }) => {
75
79
  const useAdvanced = requestContext.task === "complex";
76
80
  return useAdvanced
77
- ? "ovhcloud/qwen3.5-9b"
81
+ ? "ovhcloud/qwen3guard-gen-8b"
78
82
  : "ovhcloud/gpt-oss-120b";
79
83
  }
80
84
  });