@mastra/mcp-docs-server 1.1.2-alpha.0 → 1.1.3-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 (76) hide show
  1. package/.docs/docs/agents/processors.md +52 -0
  2. package/.docs/docs/observability/datasets/overview.md +188 -0
  3. package/.docs/docs/observability/datasets/running-experiments.md +266 -0
  4. package/.docs/docs/observability/tracing/exporters/cloud.md +7 -4
  5. package/.docs/docs/server/server-adapters.md +5 -4
  6. package/.docs/guides/deployment/amazon-ec2.md +47 -24
  7. package/.docs/guides/deployment/netlify.md +5 -5
  8. package/.docs/guides/deployment/vercel.md +3 -3
  9. package/.docs/guides/getting-started/next-js.md +4 -4
  10. package/.docs/models/gateways/openrouter.md +5 -1
  11. package/.docs/models/index.md +1 -1
  12. package/.docs/models/providers/alibaba-cn.md +3 -1
  13. package/.docs/models/providers/alibaba.md +3 -1
  14. package/.docs/models/providers/cerebras.md +1 -1
  15. package/.docs/models/providers/chutes.md +7 -4
  16. package/.docs/models/providers/cloudflare-ai-gateway.md +17 -119
  17. package/.docs/models/providers/fireworks-ai.md +2 -1
  18. package/.docs/models/providers/firmware.md +2 -7
  19. package/.docs/models/providers/huggingface.md +4 -1
  20. package/.docs/models/providers/kilo.md +333 -0
  21. package/.docs/models/providers/kuae-cloud-coding-plan.md +71 -0
  22. package/.docs/models/providers/minimax-cn-coding-plan.md +8 -7
  23. package/.docs/models/providers/minimax-cn.md +8 -7
  24. package/.docs/models/providers/minimax-coding-plan.md +8 -7
  25. package/.docs/models/providers/minimax.md +8 -7
  26. package/.docs/models/providers/nano-gpt.md +5 -1
  27. package/.docs/models/providers/nebius.md +2 -2
  28. package/.docs/models/providers/novita-ai.md +2 -1
  29. package/.docs/models/providers/nvidia.md +3 -2
  30. package/.docs/models/providers/ollama-cloud.md +2 -1
  31. package/.docs/models/providers/opencode.md +4 -1
  32. package/.docs/models/providers/poe.md +1 -1
  33. package/.docs/models/providers/siliconflow-cn.md +3 -8
  34. package/.docs/models/providers/siliconflow.md +4 -9
  35. package/.docs/models/providers/stepfun.md +73 -0
  36. package/.docs/models/providers/togetherai.md +7 -5
  37. package/.docs/models/providers/vivgrid.md +7 -4
  38. package/.docs/models/providers/zai-coding-plan.md +13 -12
  39. package/.docs/models/providers/zenmux.md +5 -2
  40. package/.docs/models/providers.md +3 -1
  41. package/.docs/reference/agents/generate.md +1 -1
  42. package/.docs/reference/configuration.md +3 -4
  43. package/.docs/reference/datasets/addItem.md +35 -0
  44. package/.docs/reference/datasets/addItems.md +33 -0
  45. package/.docs/reference/datasets/compareExperiments.md +48 -0
  46. package/.docs/reference/datasets/create.md +49 -0
  47. package/.docs/reference/datasets/dataset.md +78 -0
  48. package/.docs/reference/datasets/datasets-manager.md +84 -0
  49. package/.docs/reference/datasets/delete.md +23 -0
  50. package/.docs/reference/datasets/deleteExperiment.md +25 -0
  51. package/.docs/reference/datasets/deleteItem.md +25 -0
  52. package/.docs/reference/datasets/deleteItems.md +27 -0
  53. package/.docs/reference/datasets/get.md +29 -0
  54. package/.docs/reference/datasets/getDetails.md +45 -0
  55. package/.docs/reference/datasets/getExperiment.md +28 -0
  56. package/.docs/reference/datasets/getItem.md +31 -0
  57. package/.docs/reference/datasets/getItemHistory.md +29 -0
  58. package/.docs/reference/datasets/list.md +29 -0
  59. package/.docs/reference/datasets/listExperimentResults.md +37 -0
  60. package/.docs/reference/datasets/listExperiments.md +31 -0
  61. package/.docs/reference/datasets/listItems.md +44 -0
  62. package/.docs/reference/datasets/listVersions.md +31 -0
  63. package/.docs/reference/datasets/startExperiment.md +60 -0
  64. package/.docs/reference/datasets/startExperimentAsync.md +41 -0
  65. package/.docs/reference/datasets/update.md +46 -0
  66. package/.docs/reference/datasets/updateItem.md +36 -0
  67. package/.docs/reference/index.md +24 -0
  68. package/.docs/reference/memory/observational-memory.md +36 -0
  69. package/.docs/reference/observability/tracing/exporters/cloud-exporter.md +1 -1
  70. package/.docs/reference/processors/processor-interface.md +4 -0
  71. package/.docs/reference/server/koa-adapter.md +38 -0
  72. package/.docs/reference/streaming/agents/stream.md +1 -1
  73. package/.docs/reference/tools/create-tool.md +1 -1
  74. package/.docs/reference/workspace/e2b-sandbox.md +0 -11
  75. package/CHANGELOG.md +14 -0
  76. package/package.json +6 -6
package/.docs/guides/deployment/netlify.md CHANGED
@@ -1,8 +1,8 @@
1
1
  # Deploy Mastra to Netlify
2
2
 
3
- Use `@mastra/deployer-netlify` to deploy your mastra server as serverless functions on Netlify. The deployer bundles your code and generates a `.netlify` directory conforming to Netlify's [frameworks API](https://docs.netlify.com/build/frameworks/frameworks-api/#netlifyv1functions), ready to deploy.
3
+ Use `@mastra/deployer-netlify` to deploy your Mastra server as serverless functions on Netlify. The deployer bundles your code and generates a `.netlify` directory conforming to Netlify's [frameworks API](https://docs.netlify.com/build/frameworks/frameworks-api/#netlifyv1functions), ready to deploy.
4
4
 
5
- > **Info:** If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
5
+ > **Info:** This guide covers deploying the [Mastra server](https://mastra.ai/docs/server/mastra-server). If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
6
6
 
7
7
  ## Before you begin
8
8
 
@@ -56,7 +56,7 @@ Create a `netlify.toml` file with the following contents in your project root:
56
56
  command = "mastra build"
57
57
  ```
58
58
 
59
- ## Usage
59
+ ## Deploy
60
60
 
61
61
  After setting up your project, push it to your remote Git provider of choice (e.g. GitHub).
62
62
 
@@ -66,7 +66,7 @@ After setting up your project, push it to your remote Git provider of choice (e.
66
66
 
67
67
  2. Once you're ready, click the **Deploy** button and wait for the first deployment to complete. It'll tell you that one function has been deployed.
68
68
 
69
- 3. Try out your newly deployed function by going to `https://<random-slug>.netlify.app/api/agents`. You should get a JSON response listing all available agents.
69
+ 3. Verify your deployment at `https://<random-slug>.netlify.app/api/agents`, which should return a JSON list of your agents.
70
70
 
71
71
  Since the [Mastra server](https://mastra.ai/docs/server/mastra-server) prefixes every API endpoint with `/api`, you have to add it to your URLs when making requests.
72
72
 
@@ -74,4 +74,4 @@ After setting up your project, push it to your remote Git provider of choice (e.
74
74
 
75
75
  4. You can now call your Mastra endpoints over HTTP.
76
76
 
77
- > **Note:** Set up [authentication](https://mastra.ai/docs/server/auth) before exposing your endpoints publicly.
77
+ > **Warning:** Set up [authentication](https://mastra.ai/docs/server/auth) before exposing your endpoints publicly.
package/.docs/guides/deployment/vercel.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  Use `@mastra/deployer-vercel` to deploy your Mastra server as serverless functions on Vercel. The deployer bundles your code and generates a `.vercel/output` directory conforming to Vercel's [Build Output API](https://vercel.com/docs/build-output-api/v3), ready to deploy with no additional configuration.
4
4
 
5
- > **Info:** If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
5
+ > **Info:** This guide covers deploying the [Mastra server](https://mastra.ai/docs/server/mastra-server). If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
6
6
 
7
7
  ## Before you begin
8
8
 
@@ -49,7 +49,7 @@ export const mastra = new Mastra({
49
49
  });
50
50
  ```
51
51
 
52
- ## Usage
52
+ ## Deploy
53
53
 
54
54
  1. Push your project to a remote Git provider (e.g. GitHub) and connect your repository to Vercel.
55
55
 
@@ -65,7 +65,7 @@ export const mastra = new Mastra({
65
65
 
66
66
  4. You can now call your Mastra endpoints over HTTP.
67
67
 
68
- > **Note:** Set up [authentication](https://mastra.ai/docs/server/auth) before exposing your endpoints publicly.
68
+ > **Warning:** Set up [authentication](https://mastra.ai/docs/server/auth) before exposing your endpoints publicly.
69
69
 
70
70
  ## Optional overrides
71
71
 
package/.docs/guides/getting-started/next-js.md CHANGED
@@ -58,25 +58,25 @@ Run [`mastra init`](https://mastra.ai/reference/cli/mastra). When prompted, choo
58
58
  **npm**:
59
59
 
60
60
  ```bash
61
- npx --force mastra@latest init
61
+ npx mastra@latest init
62
62
  ```
63
63
 
64
64
  **pnpm**:
65
65
 
66
66
  ```bash
67
- pnpm dlx --force mastra@latest init
67
+ pnpm dlx mastra@latest init
68
68
  ```
69
69
 
70
70
  **Yarn**:
71
71
 
72
72
  ```bash
73
- yarn dlx --force mastra@latest init
73
+ yarn dlx mastra@latest init
74
74
  ```
75
75
 
76
76
  **Bun**:
77
77
 
78
78
  ```bash
79
- bun x --force mastra@latest init
79
+ bun x mastra@latest init
80
80
  ```
81
81
 
82
82
  This creates a `src/mastra` folder with an example weather agent and the following files:
package/.docs/models/gateways/openrouter.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
2
2
 
3
- OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 179 models through Mastra's model router.
3
+ OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 183 models through Mastra's model router.
4
4
 
5
5
  Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
6
6
 
@@ -157,8 +157,10 @@ ANTHROPIC_API_KEY=ant-...
157
157
  | `openai/gpt-oss-20b:free` |
158
158
  | `openai/gpt-oss-safeguard-20b` |
159
159
  | `openai/o4-mini` |
160
+ | `openrouter/aurora-alpha` |
160
161
  | `openrouter/sherlock-dash-alpha` |
161
162
  | `openrouter/sherlock-think-alpha` |
163
+ | `prime-intellect/intellect-3` |
162
164
  | `qwen/qwen-2.5-coder-32b-instruct` |
163
165
  | `qwen/qwen-2.5-vl-7b-instruct:free` |
164
166
  | `qwen/qwen2.5-vl-32b-instruct:free` |
@@ -184,6 +186,8 @@ ANTHROPIC_API_KEY=ant-...
184
186
  | `qwen/qwen3-next-80b-a3b-instruct` |
185
187
  | `qwen/qwen3-next-80b-a3b-instruct:free` |
186
188
  | `qwen/qwen3-next-80b-a3b-thinking` |
189
+ | `qwen/qwen3.5-397b-a17b` |
190
+ | `qwen/qwen3.5-plus-02-15` |
187
191
  | `qwen/qwq-32b:free` |
188
192
  | `rekaai/reka-flash-3` |
189
193
  | `sarvamai/sarvam-m:free` |
package/.docs/models/index.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Model Providers
2
2
 
3
- Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 2211 models from 79 providers through a single API.
3
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 2436 models from 81 providers through a single API.
4
4
 
5
5
  ## Features
6
6
 
package/.docs/models/providers/alibaba-cn.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Alibaba (China) logo](https://models.dev/logos/alibaba-cn.svg)Alibaba (China)
2
2
 
3
- Access 63 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
3
+ Access 65 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Alibaba (China) documentation](https://www.alibabacloud.com/help/en/model-studio/models).
6
6
 
@@ -94,6 +94,8 @@ for await (const chunk of stream) {
94
94
  | `alibaba-cn/qwen3-vl-235b-a22b` | 131K | | | | | | $0.29 | $1 |
95
95
  | `alibaba-cn/qwen3-vl-30b-a3b` | 131K | | | | | | $0.11 | $0.43 |
96
96
  | `alibaba-cn/qwen3-vl-plus` | 262K | | | | | | $0.14 | $1 |
97
+ | `alibaba-cn/qwen3.5-397b-a17b` | 262K | | | | | | $0.43 | $3 |
98
+ | `alibaba-cn/qwen3.5-plus` | 1.0M | | | | | | $0.57 | $3 |
97
99
  | `alibaba-cn/qwq-32b` | 131K | | | | | | $0.29 | $0.86 |
98
100
  | `alibaba-cn/qwq-plus` | 131K | | | | | | $0.23 | $0.57 |
99
101
  | `alibaba-cn/tongyi-intent-detect-v3` | 8K | | | | | | $0.06 | $0.14 |
package/.docs/models/providers/alibaba.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Alibaba logo](https://models.dev/logos/alibaba.svg)Alibaba
2
2
 
3
- Access 39 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
3
+ Access 41 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Alibaba documentation](https://www.alibabacloud.com/help/en/model-studio/models).
6
6
 
@@ -72,6 +72,8 @@ for await (const chunk of stream) {
72
72
  | `alibaba/qwen3-vl-235b-a22b` | 131K | | | | | | $0.70 | $3 |
73
73
  | `alibaba/qwen3-vl-30b-a3b` | 131K | | | | | | $0.20 | $0.80 |
74
74
  | `alibaba/qwen3-vl-plus` | 262K | | | | | | $0.20 | $2 |
75
+ | `alibaba/qwen3.5-397b-a17b` | 262K | | | | | | $0.60 | $4 |
76
+ | `alibaba/qwen3.5-plus` | 1.0M | | | | | | $0.40 | $2 |
75
77
  | `alibaba/qwq-plus` | 131K | | | | | | $0.80 | $2 |
76
78
 
77
79
  ## Advanced Configuration
package/.docs/models/providers/cerebras.md CHANGED
@@ -35,7 +35,7 @@ for await (const chunk of stream) {
35
35
  | `cerebras/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
36
36
  | `cerebras/llama3.1-8b` | 32K | | | | | | $0.10 | $0.10 |
37
37
  | `cerebras/qwen-3-235b-a22b-instruct-2507` | 131K | | | | | | $0.60 | $1 |
38
- | `cerebras/zai-glm-4.7` | 131K | | | | | | — | — |
38
+ | `cerebras/zai-glm-4.7` | 131K | | | | | | $2 | $3 |
39
39
 
40
40
  ## Advanced Configuration
41
41
 
package/.docs/models/providers/chutes.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Chutes logo](https://models.dev/logos/chutes.svg)Chutes
2
2
 
3
- Access 63 Chutes models through Mastra's model router. Authentication is handled automatically using the `CHUTES_API_KEY` environment variable.
3
+ Access 66 Chutes models through Mastra's model router. Authentication is handled automatically using the `CHUTES_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Chutes documentation](https://llm.chutes.ai).
6
6
 
@@ -46,7 +46,8 @@ for await (const chunk of stream) {
46
46
  | `chutes/deepseek-ai/DeepSeek-V3.2-Speciale-TEE` | 164K | | | | | | $0.27 | $0.41 |
47
47
  | `chutes/deepseek-ai/DeepSeek-V3.2-TEE` | 164K | | | | | | $0.25 | $0.38 |
48
48
  | `chutes/MiniMaxAI/MiniMax-M2.1-TEE` | 197K | | | | | | $0.27 | $1 |
49
- | `chutes/miromind-ai/MiroThinker-v1.5-235B` | 33K | | | | | | $0.30 | $1 |
49
+ | `chutes/MiniMaxAI/MiniMax-M2.5-TEE` | 197K | | | | | | $0.15 | $0.60 |
50
+ | `chutes/miromind-ai/MiroThinker-v1.5-235B` | 262K | | | | | | $0.30 | $1 |
50
51
  | `chutes/mistralai/Devstral-2-123B-Instruct-2512-TEE` | 262K | | | | | | $0.05 | $0.22 |
51
52
  | `chutes/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $0.39 | $2 |
52
53
  | `chutes/moonshotai/Kimi-K2-Thinking-TEE` | 262K | | | | | | $0.40 | $2 |
@@ -82,9 +83,10 @@ for await (const chunk of stream) {
82
83
  | `chutes/tngtech/TNG-R1T-Chimera-TEE` | 164K | | | | | | $0.25 | $0.85 |
83
84
  | `chutes/tngtech/TNG-R1T-Chimera-Turbo` | 164K | | | | | | $0.22 | $0.60 |
84
85
  | `chutes/unsloth/gemma-3-12b-it` | 131K | | | | | | $0.03 | $0.10 |
85
- | `chutes/unsloth/gemma-3-27b-it` | 96K | | | | | | $0.04 | $0.15 |
86
+ | `chutes/unsloth/gemma-3-27b-it` | 128K | | | | | | $0.04 | $0.15 |
86
87
  | `chutes/unsloth/gemma-3-4b-it` | 96K | | | | | | $0.01 | $0.03 |
87
88
  | `chutes/unsloth/Llama-3.2-1B-Instruct` | 33K | | | | | | $0.01 | $0.01 |
89
+ | `chutes/unsloth/Llama-3.2-3B-Instruct` | 16K | | | | | | $0.01 | $0.01 |
88
90
  | `chutes/unsloth/Mistral-Nemo-Instruct-2407` | 131K | | | | | | $0.02 | $0.04 |
89
91
  | `chutes/unsloth/Mistral-Small-24B-Instruct-2501` | 33K | | | | | | $0.03 | $0.11 |
90
92
  | `chutes/XiaomiMiMo/MiMo-V2-Flash` | 33K | | | | | | $0.09 | $0.29 |
@@ -97,6 +99,7 @@ for await (const chunk of stream) {
97
99
  | `chutes/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.35 |
98
100
  | `chutes/zai-org/GLM-4.7-FP8` | 203K | | | | | | $0.30 | $1 |
99
101
  | `chutes/zai-org/GLM-4.7-TEE` | 203K | | | | | | $0.40 | $2 |
102
+ | `chutes/zai-org/GLM-5-TEE` | 203K | | | | | | $0.75 | $3 |
100
103
 
101
104
  ## Advanced Configuration
102
105
 
@@ -126,7 +129,7 @@ const agent = new Agent({
126
129
  model: ({ requestContext }) => {
127
130
  const useAdvanced = requestContext.task === "complex";
128
131
  return useAdvanced
129
- ? "chutes/zai-org/GLM-4.7-TEE"
132
+ ? "chutes/zai-org/GLM-5-TEE"
130
133
  : "chutes/MiniMaxAI/MiniMax-M2.1-TEE";
131
134
  }
132
135
  });
package/.docs/models/providers/cloudflare-ai-gateway.md CHANGED
@@ -1,135 +1,33 @@
1
1
  # ![Cloudflare AI Gateway logo](https://models.dev/logos/cloudflare-ai-gateway.svg)Cloudflare AI Gateway
2
2
 
3
- Access 65 Cloudflare AI Gateway models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_TOKEN` environment variable.
3
+ Cloudflare AI Gateway is available through the AI SDK. Install the provider package to use their models with Mastra.
4
4
 
5
- Learn more in the [Cloudflare AI Gateway documentation](https://developers.cloudflare.com/ai-gateway/).
5
+ For detailed provider-specific documentation, see the [AI SDK Cloudflare AI Gateway provider docs](https://ai-sdk.dev/providers/community-providers/cloudflare-ai-gateway).
6
6
 
7
- ```bash
8
- CLOUDFLARE_API_TOKEN=your-api-key
9
- ```
10
-
11
- ```typescript
12
- import { Agent } from "@mastra/core/agent";
7
+ To use this provider with Mastra agents, see the [Agent Overview documentation](https://mastra.ai/docs/agents/overview).
13
8
 
14
- const agent = new Agent({
15
- id: "my-agent",
16
- name: "My Agent",
17
- instructions: "You are a helpful assistant",
18
- model: "cloudflare-ai-gateway/anthropic/claude-3-5-haiku"
19
- });
9
+ ## Installation
20
10
 
21
- // Generate a response
22
- const response = await agent.generate("Hello!");
11
+ **npm**:
23
12
 
24
- // Stream a response
25
- const stream = await agent.stream("Tell me a story");
26
- for await (const chunk of stream) {
27
- console.log(chunk);
28
- }
13
+ ```bash
14
+ npm install ai-gateway-provider
29
15
  ```
30
16
 
31
- > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Cloudflare AI Gateway documentation](https://developers.cloudflare.com/ai-gateway/) for details.
32
-
33
- ## Models
17
+ **pnpm**:
34
18
 
35
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
36
- | ------------------------------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
37
- | `cloudflare-ai-gateway/anthropic/claude-3-5-haiku` | 200K | | | | | | $0.80 | $4 |
38
- | `cloudflare-ai-gateway/anthropic/claude-3-haiku` | 200K | | | | | | $0.25 | $1 |
39
- | `cloudflare-ai-gateway/anthropic/claude-3-opus` | 200K | | | | | | $15 | $75 |
40
- | `cloudflare-ai-gateway/anthropic/claude-3-sonnet` | 200K | | | | | | $3 | $15 |
41
- | `cloudflare-ai-gateway/anthropic/claude-3.5-haiku` | 200K | | | | | | $0.80 | $4 |
42
- | `cloudflare-ai-gateway/anthropic/claude-3.5-sonnet` | 200K | | | | | | $3 | $15 |
43
- | `cloudflare-ai-gateway/anthropic/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
44
- | `cloudflare-ai-gateway/anthropic/claude-opus-4` | 200K | | | | | | $15 | $75 |
45
- | `cloudflare-ai-gateway/anthropic/claude-opus-4-1` | 200K | | | | | | $15 | $75 |
46
- | `cloudflare-ai-gateway/anthropic/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
47
- | `cloudflare-ai-gateway/anthropic/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
48
- | `cloudflare-ai-gateway/anthropic/claude-sonnet-4` | 200K | | | | | | $3 | $15 |
49
- | `cloudflare-ai-gateway/anthropic/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
50
- | `cloudflare-ai-gateway/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
51
- | `cloudflare-ai-gateway/openai/gpt-4` | 8K | | | | | | $30 | $60 |
52
- | `cloudflare-ai-gateway/openai/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
53
- | `cloudflare-ai-gateway/openai/gpt-4o` | 128K | | | | | | $3 | $10 |
54
- | `cloudflare-ai-gateway/openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
55
- | `cloudflare-ai-gateway/openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
56
- | `cloudflare-ai-gateway/openai/gpt-5.1-codex` | 400K | | | | | | $1 | $10 |
57
- | `cloudflare-ai-gateway/openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
58
- | `cloudflare-ai-gateway/openai/o1` | 200K | | | | | | $15 | $60 |
59
- | `cloudflare-ai-gateway/openai/o3` | 200K | | | | | | $2 | $8 |
60
- | `cloudflare-ai-gateway/openai/o3-mini` | 200K | | | | | | $1 | $4 |
61
- | `cloudflare-ai-gateway/openai/o3-pro` | 200K | | | | | | $20 | $80 |
62
- | `cloudflare-ai-gateway/openai/o4-mini` | 200K | | | | | | $1 | $4 |
63
- | `cloudflare-ai-gateway/workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B` | 128K | | | | | | $0.34 | $0.34 |
64
- | `cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it` | 128K | | | | | | $0.35 | $0.56 |
65
- | `cloudflare-ai-gateway/workers-ai/@cf/baai/bge-base-en-v1.5` | 128K | | | | | | $0.07 | — |
66
- | `cloudflare-ai-gateway/workers-ai/@cf/baai/bge-large-en-v1.5` | 128K | | | | | | $0.20 | — |
67
- | `cloudflare-ai-gateway/workers-ai/@cf/baai/bge-m3` | 128K | | | | | | $0.01 | — |
68
- | `cloudflare-ai-gateway/workers-ai/@cf/baai/bge-reranker-base` | 128K | | | | | | $0.00 | — |
69
- | `cloudflare-ai-gateway/workers-ai/@cf/baai/bge-small-en-v1.5` | 128K | | | | | | $0.02 | — |
70
- | `cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-en` | 128K | | | | | | — | — |
71
- | `cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-es` | 128K | | | | | | — | — |
72
- | `cloudflare-ai-gateway/workers-ai/@cf/deepgram/nova-3` | 128K | | | | | | — | — |
73
- | `cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b` | 128K | | | | | | $0.50 | $5 |
74
- | `cloudflare-ai-gateway/workers-ai/@cf/facebook/bart-large-cnn` | 128K | | | | | | — | — |
75
- | `cloudflare-ai-gateway/workers-ai/@cf/google/gemma-3-12b-it` | 128K | | | | | | $0.35 | $0.56 |
76
- | `cloudflare-ai-gateway/workers-ai/@cf/huggingface/distilbert-sst-2-int8` | 128K | | | | | | $0.03 | — |
77
- | `cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro` | 128K | | | | | | $0.02 | $0.11 |
78
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-2-7b-chat-fp16` | 128K | | | | | | $0.56 | $7 |
79
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct` | 128K | | | | | | $0.28 | $0.83 |
80
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct-awq` | 128K | | | | | | $0.12 | $0.27 |
81
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct` | 128K | | | | | | $0.28 | $0.83 |
82
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-awq` | 128K | | | | | | $0.12 | $0.27 |
83
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8` | 128K | | | | | | $0.15 | $0.29 |
84
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct` | 128K | | | | | | $0.05 | $0.68 |
85
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct` | 128K | | | | | | $0.03 | $0.20 |
86
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct` | 128K | | | | | | $0.05 | $0.34 |
87
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast` | 128K | | | | | | $0.29 | $2 |
88
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct` | 128K | | | | | | $0.27 | $0.85 |
89
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b` | 128K | | | | | | $0.48 | $0.03 |
90
- | `cloudflare-ai-gateway/workers-ai/@cf/meta/m2m100-1.2b` | 128K | | | | | | $0.34 | $0.34 |
91
- | `cloudflare-ai-gateway/workers-ai/@cf/mistral/mistral-7b-instruct-v0.1` | 128K | | | | | | $0.11 | $0.19 |
92
- | `cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct` | 128K | | | | | | $0.35 | $0.56 |
93
- | `cloudflare-ai-gateway/workers-ai/@cf/myshell-ai/melotts` | 128K | | | | | | — | — |
94
- | `cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b` | 128K | | | | | | $0.35 | $0.75 |
95
- | `cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b` | 128K | | | | | | $0.20 | $0.30 |
96
- | `cloudflare-ai-gateway/workers-ai/@cf/pfnet/plamo-embedding-1b` | 128K | | | | | | $0.02 | — |
97
- | `cloudflare-ai-gateway/workers-ai/@cf/pipecat-ai/smart-turn-v2` | 128K | | | | | | — | — |
98
- | `cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct` | 128K | | | | | | $0.66 | $1 |
99
- | `cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8` | 128K | | | | | | $0.05 | $0.34 |
100
- | `cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-embedding-0.6b` | 128K | | | | | | $0.01 | — |
101
- | `cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b` | 128K | | | | | | $0.66 | $1 |
102
-
103
- ## Advanced Configuration
19
+ ```bash
20
+ pnpm add ai-gateway-provider
21
+ ```
104
22
 
105
- ### Custom Headers
23
+ **Yarn**:
106
24
 
107
- ```typescript
108
- const agent = new Agent({
109
- id: "custom-agent",
110
- name: "custom-agent",
111
- model: {
112
- url: "https://gateway.ai.cloudflare.com/v1/${CLOUDFLARE_ACCOUNT_ID}/${CLOUDFLARE_GATEWAY_ID}/compat/",
113
- id: "cloudflare-ai-gateway/anthropic/claude-3-5-haiku",
114
- apiKey: process.env.CLOUDFLARE_API_TOKEN,
115
- headers: {
116
- "X-Custom-Header": "value"
117
- }
118
- }
119
- });
25
+ ```bash
26
+ yarn add ai-gateway-provider
120
27
  ```
121
28
 
122
- ### Dynamic Model Selection
29
+ **Bun**:
123
30
 
124
- ```typescript
125
- const agent = new Agent({
126
- id: "dynamic-agent",
127
- name: "Dynamic Agent",
128
- model: ({ requestContext }) => {
129
- const useAdvanced = requestContext.task === "complex";
130
- return useAdvanced
131
- ? "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b"
132
- : "cloudflare-ai-gateway/anthropic/claude-3-5-haiku";
133
- }
134
- });
31
+ ```bash
32
+ bun add ai-gateway-provider
135
33
  ```
package/.docs/models/providers/fireworks-ai.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Fireworks AI logo](https://models.dev/logos/fireworks-ai.svg)Fireworks AI
2
2
 
3
- Access 18 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
3
+ Access 19 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
6
6
 
@@ -50,6 +50,7 @@ for await (const chunk of stream) {
50
50
  | `fireworks-ai/accounts/fireworks/models/kimi-k2p5` | 256K | | | | | | $0.60 | $3 |
51
51
  | `fireworks-ai/accounts/fireworks/models/minimax-m2` | 192K | | | | | | $0.30 | $1 |
52
52
  | `fireworks-ai/accounts/fireworks/models/minimax-m2p1` | 200K | | | | | | $0.30 | $1 |
53
+ | `fireworks-ai/accounts/fireworks/models/minimax-m2p5` | 197K | | | | | | $0.30 | $1 |
53
54
  | `fireworks-ai/accounts/fireworks/models/qwen3-235b-a22b` | 128K | | | | | | $0.22 | $0.88 |
54
55
  | `fireworks-ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct` | 256K | | | | | | $0.45 | $2 |
55
56
 
package/.docs/models/providers/firmware.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Firmware logo](https://models.dev/logos/firmware.svg)Firmware
2
2
 
3
- Access 20 Firmware models through Mastra's model router. Authentication is handled automatically using the `FIRMWARE_API_KEY` environment variable.
3
+ Access 15 Firmware models through Mastra's model router. Authentication is handled automatically using the `FIRMWARE_API_KEY` environment variable.
4
4
 
5
5
  Learn more in the [Firmware documentation](https://docs.firmware.ai).
6
6
 
@@ -38,7 +38,6 @@ for await (const chunk of stream) {
38
38
  | `firmware/claude-opus-4-5` | 200K | | | | | | $5 | $25 |
39
39
  | `firmware/claude-opus-4-6` | 200K | | | | | | $5 | $25 |
40
40
  | `firmware/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
41
- | `firmware/deepseek-r1` | 128K | | | | | | $1 | $5 |
42
41
  | `firmware/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
43
42
  | `firmware/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
44
43
  | `firmware/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
@@ -50,10 +49,6 @@ for await (const chunk of stream) {
50
49
  | `firmware/gpt-5.2` | 400K | | | | | | $2 | $14 |
51
50
  | `firmware/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
52
51
  | `firmware/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.20 |
53
- | `firmware/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
54
- | `firmware/kimi-k2.5` | 256K | | | | | | $0.60 | $3 |
55
- | `firmware/zai-glm-4.7` | 131K | | | | | | $0.60 | $2 |
56
- | `firmware/zai-glm-4.7-flash` | 131K | | | | | | $0.07 | $0.40 |
57
52
 
58
53
  ## Advanced Configuration
59
54
 
@@ -83,7 +78,7 @@ const agent = new Agent({
83
78
  model: ({ requestContext }) => {
84
79
  const useAdvanced = requestContext.task === "complex";
85
80
  return useAdvanced
86
- ? "firmware/zai-glm-4.7-flash"
81
+ ? "firmware/gpt-oss-20b"
87
82
  : "firmware/claude-haiku-4-5";
88
83
  }
89
84
  });
package/.docs/models/providers/huggingface.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
2
2
 
3
- Access 17 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
3
+ Access 20 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
4
4
 
5
5
  Learn more in the [Hugging Face documentation](https://huggingface.co).
6
6
 
@@ -37,16 +37,19 @@ for await (const chunk of stream) {
37
37
  | `huggingface/deepseek-ai/DeepSeek-R1-0528` | 164K | | | | | | $3 | $5 |
38
38
  | `huggingface/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.28 | $0.40 |
39
39
  | `huggingface/MiniMaxAI/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
40
+ | `huggingface/MiniMaxAI/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
40
41
  | `huggingface/moonshotai/Kimi-K2-Instruct` | 131K | | | | | | $1 | $3 |
41
42
  | `huggingface/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $1 | $3 |
42
43
  | `huggingface/moonshotai/Kimi-K2-Thinking` | 262K | | | | | | $0.60 | $3 |
43
44
  | `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
44
45
  | `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.30 | $3 |
45
46
  | `huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $2 | $2 |
47
+ | `huggingface/Qwen/Qwen3-Coder-Next` | 262K | | | | | | $0.20 | $2 |
46
48
  | `huggingface/Qwen/Qwen3-Embedding-4B` | 32K | | | | | | $0.01 | — |
47
49
  | `huggingface/Qwen/Qwen3-Embedding-8B` | 32K | | | | | | $0.01 | — |
48
50
  | `huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.25 | $1 |
49
51
  | `huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking` | 262K | | | | | | $0.30 | $2 |
52
+ | `huggingface/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
50
53
  | `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
51
54
  | `huggingface/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
52
55
  | `huggingface/zai-org/GLM-4.7-Flash` | 200K | | | | | | — | — |