@mastra/mcp-docs-server 1.2.2 → 1.2.3-alpha.11
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.
- package/.docs/docs/{harness → agent-controller}/modes.md +19 -19
- package/.docs/docs/agent-controller/overview.md +128 -0
- package/.docs/docs/agent-controller/session.md +143 -0
- package/.docs/docs/{harness → agent-controller}/subagents.md +12 -12
- package/.docs/docs/agent-controller/threads-and-state.md +141 -0
- package/.docs/docs/{harness → agent-controller}/tool-approvals.md +23 -23
- package/.docs/docs/agents/agent-approval.md +38 -0
- package/.docs/docs/agents/channels.md +47 -0
- package/.docs/docs/agents/heartbeats.md +211 -0
- package/.docs/docs/agents/signals.md +25 -1
- package/.docs/docs/observability/metrics/overview.md +2 -2
- package/.docs/models/gateways/openrouter.md +1 -2
- package/.docs/models/gateways/vercel.md +3 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/anthropic.md +4 -5
- package/.docs/models/providers/chutes.md +17 -43
- package/.docs/models/providers/deepinfra.md +3 -2
- package/.docs/models/providers/friendli.md +1 -3
- package/.docs/models/providers/gmicloud.md +18 -15
- package/.docs/models/providers/huggingface.md +2 -1
- package/.docs/models/providers/inceptron.md +10 -8
- package/.docs/models/providers/llmgateway.md +3 -6
- package/.docs/models/providers/neuralwatt.md +9 -5
- package/.docs/models/providers/novita-ai.md +1 -1
- package/.docs/models/providers/nvidia.md +2 -1
- package/.docs/models/providers/siliconflow-cn.md +50 -78
- package/.docs/models/providers/siliconflow.md +52 -73
- package/.docs/models/providers/stepfun.md +1 -1
- package/.docs/models/providers/subconscious.md +71 -0
- package/.docs/models/providers/synthetic.md +8 -6
- package/.docs/models/providers/tinfoil.md +77 -0
- package/.docs/models/providers/xiaomi.md +2 -2
- package/.docs/models/providers.md +2 -0
- package/.docs/reference/{harness/harness-class.md → agent-controller/agent-controller-class.md} +106 -106
- package/.docs/reference/{harness → agent-controller}/session.md +97 -91
- package/.docs/reference/agents/channels.md +3 -1
- package/.docs/reference/agents/listSuspendedRuns.md +91 -0
- package/.docs/reference/channels/channel-provider.md +65 -0
- package/.docs/reference/channels/slack-provider.md +226 -0
- package/.docs/reference/client-js/agents.md +21 -0
- package/.docs/reference/index.md +6 -2
- package/.docs/reference/observability/metrics/automatic-metrics.md +2 -2
- package/.docs/reference/pubsub/lease-provider.md +131 -0
- package/.docs/reference/pubsub/redis-streams.md +10 -2
- package/CHANGELOG.md +42 -0
- package/package.json +4 -4
- package/.docs/docs/harness/overview.md +0 -128
- package/.docs/docs/harness/session.md +0 -143
- package/.docs/docs/harness/threads-and-state.md +0 -141
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# SiliconFlow
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 49 SiliconFlow models through Mastra's model router. Authentication is handled automatically using the `SILICONFLOW_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [SiliconFlow documentation](https://cloud.siliconflow.com/models).
|
|
6
6
|
|
|
@@ -32,78 +32,57 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `siliconflow/baidu/ERNIE-4.5-300B-A47B`
|
|
38
|
-
| `siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct`
|
|
39
|
-
| `siliconflow/deepseek-ai/DeepSeek-R1`
|
|
40
|
-
| `siliconflow/deepseek-ai/DeepSeek-
|
|
41
|
-
| `siliconflow/deepseek-ai/DeepSeek-
|
|
42
|
-
| `siliconflow/deepseek-ai/DeepSeek-V3`
|
|
43
|
-
| `siliconflow/deepseek-ai/DeepSeek-V3.
|
|
44
|
-
| `siliconflow/deepseek-ai/DeepSeek-V3.
|
|
45
|
-
| `siliconflow/deepseek-ai/DeepSeek-
|
|
46
|
-
| `siliconflow/deepseek-ai/DeepSeek-
|
|
47
|
-
| `siliconflow/
|
|
48
|
-
| `siliconflow/
|
|
49
|
-
| `siliconflow/
|
|
50
|
-
| `siliconflow/
|
|
51
|
-
| `siliconflow/
|
|
52
|
-
| `siliconflow/
|
|
53
|
-
| `siliconflow/
|
|
54
|
-
| `siliconflow/
|
|
55
|
-
| `siliconflow/
|
|
56
|
-
| `siliconflow/
|
|
57
|
-
| `siliconflow/
|
|
58
|
-
| `siliconflow/
|
|
59
|
-
| `siliconflow/
|
|
60
|
-
| `siliconflow/
|
|
61
|
-
| `siliconflow/Qwen/
|
|
62
|
-
| `siliconflow/Qwen/
|
|
63
|
-
| `siliconflow/Qwen/
|
|
64
|
-
| `siliconflow/Qwen/
|
|
65
|
-
| `siliconflow/Qwen/
|
|
66
|
-
| `siliconflow/Qwen/
|
|
67
|
-
| `siliconflow/Qwen/
|
|
68
|
-
| `siliconflow/Qwen/
|
|
69
|
-
| `siliconflow/Qwen/
|
|
70
|
-
| `siliconflow/Qwen/Qwen3-
|
|
71
|
-
| `siliconflow/Qwen/Qwen3-
|
|
72
|
-
| `siliconflow/Qwen/Qwen3-
|
|
73
|
-
| `siliconflow/Qwen/Qwen3-
|
|
74
|
-
| `siliconflow/Qwen/Qwen3-
|
|
75
|
-
| `siliconflow/Qwen/Qwen3-
|
|
76
|
-
| `siliconflow/Qwen/Qwen3-
|
|
77
|
-
| `siliconflow/Qwen/Qwen3-
|
|
78
|
-
| `siliconflow/
|
|
79
|
-
| `siliconflow/
|
|
80
|
-
| `siliconflow/
|
|
81
|
-
| `siliconflow/
|
|
82
|
-
| `siliconflow/
|
|
83
|
-
| `siliconflow/
|
|
84
|
-
| `siliconflow/
|
|
85
|
-
| `siliconflow/
|
|
86
|
-
| `siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking` | 262K | | | | | | $0.45 | $4 |
|
|
87
|
-
| `siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct` | 262K | | | | | | $0.29 | $1 |
|
|
88
|
-
| `siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking` | 262K | | | | | | $0.29 | $1 |
|
|
89
|
-
| `siliconflow/Qwen/Qwen3-VL-32B-Instruct` | 262K | | | | | | $0.20 | $0.60 |
|
|
90
|
-
| `siliconflow/Qwen/Qwen3-VL-32B-Thinking` | 262K | | | | | | $0.20 | $2 |
|
|
91
|
-
| `siliconflow/Qwen/Qwen3-VL-8B-Instruct` | 262K | | | | | | $0.18 | $0.68 |
|
|
92
|
-
| `siliconflow/Qwen/Qwen3-VL-8B-Thinking` | 262K | | | | | | $0.18 | $2 |
|
|
93
|
-
| `siliconflow/Qwen/QwQ-32B` | 131K | | | | | | $0.15 | $0.58 |
|
|
94
|
-
| `siliconflow/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
95
|
-
| `siliconflow/tencent/Hunyuan-A13B-Instruct` | 131K | | | | | | $0.14 | $0.57 |
|
|
96
|
-
| `siliconflow/tencent/Hy3-preview` | 262K | | | | | | $0.07 | $0.26 |
|
|
97
|
-
| `siliconflow/zai-org/GLM-4.5` | 131K | | | | | | $0.40 | $2 |
|
|
98
|
-
| `siliconflow/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.14 | $0.86 |
|
|
99
|
-
| `siliconflow/zai-org/GLM-4.5V` | 66K | | | | | | $0.14 | $0.86 |
|
|
100
|
-
| `siliconflow/zai-org/GLM-4.6` | 205K | | | | | | $0.50 | $2 |
|
|
101
|
-
| `siliconflow/zai-org/GLM-4.6V` | 131K | | | | | | $0.30 | $0.90 |
|
|
102
|
-
| `siliconflow/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
103
|
-
| `siliconflow/zai-org/GLM-5` | 205K | | | | | | $0.95 | $3 |
|
|
104
|
-
| `siliconflow/zai-org/GLM-5.1` | 205K | | | | | | $1 | $4 |
|
|
105
|
-
| `siliconflow/zai-org/GLM-5.2` | 205K | | | | | | $1 | $4 |
|
|
106
|
-
| `siliconflow/zai-org/GLM-5V-Turbo` | 200K | | | | | | $1 | $4 |
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| -------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `siliconflow/baidu/ERNIE-4.5-300B-A47B` | 131K | | | | | | $0.28 | $1 |
|
|
38
|
+
| `siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct` | 262K | | | | | | $0.21 | $0.57 |
|
|
39
|
+
| `siliconflow/deepseek-ai/DeepSeek-R1` | 164K | | | | | | $0.50 | $2 |
|
|
40
|
+
| `siliconflow/deepseek-ai/DeepSeek-V3` | 164K | | | | | | $0.25 | $1 |
|
|
41
|
+
| `siliconflow/deepseek-ai/DeepSeek-V3.1` | 164K | | | | | | $0.27 | $1 |
|
|
42
|
+
| `siliconflow/deepseek-ai/DeepSeek-V3.1-Terminus` | 164K | | | | | | $0.27 | $1 |
|
|
43
|
+
| `siliconflow/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.27 | $0.42 |
|
|
44
|
+
| `siliconflow/deepseek-ai/DeepSeek-V3.2-Exp` | 164K | | | | | | $0.27 | $0.41 |
|
|
45
|
+
| `siliconflow/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
46
|
+
| `siliconflow/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $3 |
|
|
47
|
+
| `siliconflow/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.12 | $0.40 |
|
|
48
|
+
| `siliconflow/google/gemma-4-31B-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
49
|
+
| `siliconflow/inclusionAI/Ling-flash-2.0` | 131K | | | | | | $0.14 | $0.57 |
|
|
50
|
+
| `siliconflow/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.30 | $1 |
|
|
51
|
+
| `siliconflow/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.45 | $2 |
|
|
52
|
+
| `siliconflow/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.77 | $4 |
|
|
53
|
+
| `siliconflow/openai/gpt-oss-120b` | 131K | | | | | | $0.05 | $0.45 |
|
|
54
|
+
| `siliconflow/openai/gpt-oss-20b` | 131K | | | | | | $0.04 | $0.18 |
|
|
55
|
+
| `siliconflow/Qwen/Qwen2.5-72B-Instruct` | 33K | | | | | | $0.59 | $0.59 |
|
|
56
|
+
| `siliconflow/Qwen/Qwen2.5-7B-Instruct` | 33K | | | | | | $0.05 | $0.05 |
|
|
57
|
+
| `siliconflow/Qwen/Qwen3-14B` | 131K | | | | | | $0.07 | $0.28 |
|
|
58
|
+
| `siliconflow/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.13 | $0.60 |
|
|
59
|
+
| `siliconflow/Qwen/Qwen3-30B-A3B-Instruct-2507` | 262K | | | | | | $0.09 | $0.30 |
|
|
60
|
+
| `siliconflow/Qwen/Qwen3-32B` | 131K | | | | | | $0.14 | $0.57 |
|
|
61
|
+
| `siliconflow/Qwen/Qwen3-8B` | 131K | | | | | | $0.06 | $0.06 |
|
|
62
|
+
| `siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct` | 262K | | | | | | $0.07 | $0.28 |
|
|
63
|
+
| `siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $0.25 | $1 |
|
|
64
|
+
| `siliconflow/Qwen/Qwen3-VL-235B-A22B-Instruct` | 262K | | | | | | $0.30 | $2 |
|
|
65
|
+
| `siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking` | 262K | | | | | | $0.45 | $4 |
|
|
66
|
+
| `siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct` | 262K | | | | | | $0.29 | $1 |
|
|
67
|
+
| `siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking` | 262K | | | | | | $0.29 | $1 |
|
|
68
|
+
| `siliconflow/Qwen/Qwen3-VL-32B-Instruct` | 262K | | | | | | $0.20 | $0.60 |
|
|
69
|
+
| `siliconflow/Qwen/Qwen3-VL-32B-Thinking` | 262K | | | | | | $0.20 | $2 |
|
|
70
|
+
| `siliconflow/Qwen/Qwen3-VL-8B-Instruct` | 262K | | | | | | $0.18 | $0.68 |
|
|
71
|
+
| `siliconflow/Qwen/Qwen3.5-122B-A10B` | 262K | | | | | | $0.26 | $2 |
|
|
72
|
+
| `siliconflow/Qwen/Qwen3.5-27B` | 262K | | | | | | $0.25 | $2 |
|
|
73
|
+
| `siliconflow/Qwen/Qwen3.5-35B-A3B` | 262K | | | | | | $0.24 | $2 |
|
|
74
|
+
| `siliconflow/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.39 | $2 |
|
|
75
|
+
| `siliconflow/Qwen/Qwen3.5-9B` | 262K | | | | | | $0.10 | $0.15 |
|
|
76
|
+
| `siliconflow/Qwen/Qwen3.6-27B` | 262K | | | | | | $0.30 | $3 |
|
|
77
|
+
| `siliconflow/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.20 | $2 |
|
|
78
|
+
| `siliconflow/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
79
|
+
| `siliconflow/tencent/Hunyuan-A13B-Instruct` | 131K | | | | | | $0.14 | $0.57 |
|
|
80
|
+
| `siliconflow/tencent/Hy3-preview` | 262K | | | | | | $0.07 | $0.26 |
|
|
81
|
+
| `siliconflow/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.14 | $0.86 |
|
|
82
|
+
| `siliconflow/zai-org/GLM-5` | 205K | | | | | | $0.95 | $3 |
|
|
83
|
+
| `siliconflow/zai-org/GLM-5.1` | 205K | | | | | | $1 | $4 |
|
|
84
|
+
| `siliconflow/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
85
|
+
| `siliconflow/zai-org/GLM-5V-Turbo` | 200K | | | | | | $1 | $4 |
|
|
107
86
|
|
|
108
87
|
## Advanced configuration
|
|
109
88
|
|
|
@@ -38,7 +38,7 @@ for await (const chunk of stream) {
|
|
|
38
38
|
| `stepfun/step-2-16k` | 16K | | | | | | $5 | $16 |
|
|
39
39
|
| `stepfun/step-3.5-flash` | 256K | | | | | | $0.10 | $0.30 |
|
|
40
40
|
| `stepfun/step-3.5-flash-2603` | 256K | | | | | | $0.10 | $0.30 |
|
|
41
|
-
| `stepfun/step-3.7-flash` | 256K | | | | | | $0.
|
|
41
|
+
| `stepfun/step-3.7-flash` | 256K | | | | | | $0.20 | $1 |
|
|
42
42
|
|
|
43
43
|
## Advanced configuration
|
|
44
44
|
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
# Subconscious
|
|
2
|
+
|
|
3
|
+
Access 1 Subconscious model through Mastra's model router. Authentication is handled automatically using the `SUBCONSCIOUS_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Subconscious documentation](https://docs.subconscious.dev).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
SUBCONSCIOUS_API_KEY=your-api-key
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
```typescript
|
|
12
|
+
import { Agent } from "@mastra/core/agent";
|
|
13
|
+
|
|
14
|
+
const agent = new Agent({
|
|
15
|
+
id: "my-agent",
|
|
16
|
+
name: "My Agent",
|
|
17
|
+
instructions: "You are a helpful assistant",
|
|
18
|
+
model: "subconscious/subconscious/tim-qwen3.6-27b"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Subconscious documentation](https://docs.subconscious.dev) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `subconscious/subconscious/tim-qwen3.6-27b` | 8K | | | | | | — | — |
|
|
38
|
+
|
|
39
|
+
## Advanced configuration
|
|
40
|
+
|
|
41
|
+
### Custom headers
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
const agent = new Agent({
|
|
45
|
+
id: "custom-agent",
|
|
46
|
+
name: "custom-agent",
|
|
47
|
+
model: {
|
|
48
|
+
url: "https://api.subconscious.dev/v1",
|
|
49
|
+
id: "subconscious/subconscious/tim-qwen3.6-27b",
|
|
50
|
+
apiKey: process.env.SUBCONSCIOUS_API_KEY,
|
|
51
|
+
headers: {
|
|
52
|
+
"X-Custom-Header": "value"
|
|
53
|
+
}
|
|
54
|
+
}
|
|
55
|
+
});
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
### Dynamic model selection
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "dynamic-agent",
|
|
63
|
+
name: "Dynamic Agent",
|
|
64
|
+
model: ({ requestContext }) => {
|
|
65
|
+
const useAdvanced = requestContext.task === "complex";
|
|
66
|
+
return useAdvanced
|
|
67
|
+
? "subconscious/subconscious/tim-qwen3.6-27b"
|
|
68
|
+
: "subconscious/subconscious/tim-qwen3.6-27b";
|
|
69
|
+
}
|
|
70
|
+
});
|
|
71
|
+
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Synthetic
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 10 Synthetic models through Mastra's model router. Authentication is handled automatically using the `SYNTHETIC_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Synthetic documentation](https://synthetic.new/pricing).
|
|
6
6
|
|
|
@@ -37,11 +37,13 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| `synthetic/hf:MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.60 | $1 |
|
|
38
38
|
| `synthetic/hf:moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
39
39
|
| `synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4` | 262K | | | | | | $0.30 | $1 |
|
|
40
|
-
| `synthetic/hf:openai/gpt-oss-120b` |
|
|
41
|
-
| `synthetic/hf:Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $
|
|
42
|
-
| `synthetic/hf:
|
|
43
|
-
| `synthetic/hf:zai-org/GLM-4.7
|
|
40
|
+
| `synthetic/hf:openai/gpt-oss-120b` | 131K | | | | | | $0.10 | $0.10 |
|
|
41
|
+
| `synthetic/hf:Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
|
|
42
|
+
| `synthetic/hf:Qwen/Qwen3.6-27B` | 262K | | | | | | $0.45 | $4 |
|
|
43
|
+
| `synthetic/hf:zai-org/GLM-4.7` | 203K | | | | | | $0.45 | $2 |
|
|
44
|
+
| `synthetic/hf:zai-org/GLM-4.7-Flash` | 197K | | | | | | $0.10 | $0.50 |
|
|
44
45
|
| `synthetic/hf:zai-org/GLM-5.1` | 197K | | | | | | $1 | $3 |
|
|
46
|
+
| `synthetic/hf:zai-org/GLM-5.2` | 524K | | | | | | $1 | $4 |
|
|
45
47
|
|
|
46
48
|
## Advanced configuration
|
|
47
49
|
|
|
@@ -71,7 +73,7 @@ const agent = new Agent({
|
|
|
71
73
|
model: ({ requestContext }) => {
|
|
72
74
|
const useAdvanced = requestContext.task === "complex";
|
|
73
75
|
return useAdvanced
|
|
74
|
-
? "synthetic/hf:zai-org/GLM-5.
|
|
76
|
+
? "synthetic/hf:zai-org/GLM-5.2"
|
|
75
77
|
: "synthetic/hf:MiniMaxAI/MiniMax-M3";
|
|
76
78
|
}
|
|
77
79
|
});
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
# Tinfoil
|
|
2
|
+
|
|
3
|
+
Access 7 Tinfoil models through Mastra's model router. Authentication is handled automatically using the `TINFOIL_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Tinfoil documentation](https://docs.tinfoil.sh).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
TINFOIL_API_KEY=your-api-key
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
```typescript
|
|
12
|
+
import { Agent } from "@mastra/core/agent";
|
|
13
|
+
|
|
14
|
+
const agent = new Agent({
|
|
15
|
+
id: "my-agent",
|
|
16
|
+
name: "My Agent",
|
|
17
|
+
instructions: "You are a helpful assistant",
|
|
18
|
+
model: "tinfoil/gemma4-31b"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Tinfoil documentation](https://docs.tinfoil.sh) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| -------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `tinfoil/gemma4-31b` | 256K | | | | | | $0.40 | $1 |
|
|
38
|
+
| `tinfoil/glm-5-2` | 384K | | | | | | $2 | $5 |
|
|
39
|
+
| `tinfoil/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
40
|
+
| `tinfoil/gpt-oss-safeguard-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
41
|
+
| `tinfoil/kimi-k2-6` | 256K | | | | | | $2 | $5 |
|
|
42
|
+
| `tinfoil/llama3-3-70b` | 128K | | | | | | $2 | $3 |
|
|
43
|
+
| `tinfoil/nomic-embed-text` | 8K | | | | | | $0.05 | — |
|
|
44
|
+
|
|
45
|
+
## Advanced configuration
|
|
46
|
+
|
|
47
|
+
### Custom headers
|
|
48
|
+
|
|
49
|
+
```typescript
|
|
50
|
+
const agent = new Agent({
|
|
51
|
+
id: "custom-agent",
|
|
52
|
+
name: "custom-agent",
|
|
53
|
+
model: {
|
|
54
|
+
url: "https://inference.tinfoil.sh/v1",
|
|
55
|
+
id: "tinfoil/gemma4-31b",
|
|
56
|
+
apiKey: process.env.TINFOIL_API_KEY,
|
|
57
|
+
headers: {
|
|
58
|
+
"X-Custom-Header": "value"
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
});
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
### Dynamic model selection
|
|
65
|
+
|
|
66
|
+
```typescript
|
|
67
|
+
const agent = new Agent({
|
|
68
|
+
id: "dynamic-agent",
|
|
69
|
+
name: "Dynamic Agent",
|
|
70
|
+
model: ({ requestContext }) => {
|
|
71
|
+
const useAdvanced = requestContext.task === "complex";
|
|
72
|
+
return useAdvanced
|
|
73
|
+
? "tinfoil/nomic-embed-text"
|
|
74
|
+
: "tinfoil/gemma4-31b";
|
|
75
|
+
}
|
|
76
|
+
});
|
|
77
|
+
```
|
|
@@ -34,8 +34,8 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.
|
|
38
|
-
| `xiaomi/mimo-v2.5-pro` | 1.0M | | | | | | $
|
|
37
|
+
| `xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
38
|
+
| `xiaomi/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
39
39
|
| `xiaomi/mimo-v2.5-pro-ultraspeed` | 1.0M | | | | | | $1 | $3 |
|
|
40
40
|
|
|
41
41
|
## Advanced configuration
|
|
@@ -106,11 +106,13 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
106
106
|
- [STACKIT](https://mastra.ai/models/providers/stackit)
|
|
107
107
|
- [StepFun](https://mastra.ai/models/providers/stepfun)
|
|
108
108
|
- [StepFun AI](https://mastra.ai/models/providers/stepfun-ai)
|
|
109
|
+
- [Subconscious](https://mastra.ai/models/providers/subconscious)
|
|
109
110
|
- [submodel](https://mastra.ai/models/providers/submodel)
|
|
110
111
|
- [Synthetic](https://mastra.ai/models/providers/synthetic)
|
|
111
112
|
- [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan)
|
|
112
113
|
- [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub)
|
|
113
114
|
- [The Grid AI](https://mastra.ai/models/providers/the-grid-ai)
|
|
115
|
+
- [Tinfoil](https://mastra.ai/models/providers/tinfoil)
|
|
114
116
|
- [Together AI](https://mastra.ai/models/providers/togetherai)
|
|
115
117
|
- [Umans AI](https://mastra.ai/models/providers/umans-ai)
|
|
116
118
|
- [Umans AI Coding Plan](https://mastra.ai/models/providers/umans-ai-coding-plan)
|