@mastra/mcp-docs-server 1.2.0 → 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.
- package/.docs/docs/agents/goals.md +2 -2
- package/.docs/docs/harness/modes.md +2 -2
- package/.docs/docs/harness/overview.md +23 -25
- package/.docs/docs/harness/session.md +2 -2
- package/.docs/docs/harness/subagents.md +3 -3
- package/.docs/docs/harness/tool-approvals.md +2 -2
- package/.docs/guides/build-your-ui/openui.md +297 -0
- package/.docs/models/gateways/custom-gateways.md +12 -0
- package/.docs/models/gateways/netlify.md +4 -7
- package/.docs/models/gateways/openrouter.md +20 -40
- package/.docs/models/gateways/vercel.md +281 -246
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/alibaba-cn.md +5 -2
- package/.docs/models/providers/alibaba-coding-plan-cn.md +5 -2
- package/.docs/models/providers/alibaba-coding-plan.md +5 -2
- package/.docs/models/providers/alibaba-token-plan-cn.md +88 -0
- package/.docs/models/providers/alibaba-token-plan.md +88 -0
- package/.docs/models/providers/alibaba.md +3 -1
- package/.docs/models/providers/ambient.md +6 -5
- package/.docs/models/providers/anthropic.md +8 -11
- package/.docs/models/providers/anyapi.md +99 -0
- package/.docs/models/providers/baseten.md +19 -19
- package/.docs/models/providers/cerebras.md +5 -7
- package/.docs/models/providers/claudinio.md +3 -2
- package/.docs/models/providers/cloudflare-workers-ai.md +4 -9
- package/.docs/models/providers/cortecs.md +9 -2
- package/.docs/models/providers/crof.md +12 -10
- package/.docs/models/providers/deepinfra.md +18 -31
- package/.docs/models/providers/deepseek.md +1 -1
- package/.docs/models/providers/digitalocean.md +5 -1
- package/.docs/models/providers/fastrouter.md +34 -2
- package/.docs/models/providers/fireworks-ai.md +22 -27
- package/.docs/models/providers/freemodel.md +108 -0
- package/.docs/models/providers/google.md +7 -9
- package/.docs/models/providers/groq.md +7 -9
- package/.docs/models/providers/helicone.md +1 -1
- package/.docs/models/providers/hpc-ai.md +3 -3
- package/.docs/models/providers/huggingface.md +1 -1
- package/.docs/models/providers/kilo.md +9 -8
- package/.docs/models/providers/kimi-for-coding.md +4 -3
- package/.docs/models/providers/llmgateway.md +38 -29
- package/.docs/models/providers/llmtr.md +76 -0
- package/.docs/models/providers/lucidquery.md +11 -9
- package/.docs/models/providers/minimax-cn-coding-plan.md +3 -2
- package/.docs/models/providers/minimax-cn.md +3 -2
- package/.docs/models/providers/minimax-coding-plan.md +3 -2
- package/.docs/models/providers/minimax.md +3 -2
- package/.docs/models/providers/mistral.md +25 -31
- package/.docs/models/providers/moonshotai-cn.md +13 -11
- package/.docs/models/providers/moonshotai.md +13 -11
- package/.docs/models/providers/nano-gpt.md +621 -529
- package/.docs/models/providers/nearai.md +5 -1
- package/.docs/models/providers/nebius.md +2 -15
- package/.docs/models/providers/neon.md +96 -0
- package/.docs/models/providers/neuralwatt.md +19 -20
- package/.docs/models/providers/novita-ai.md +7 -2
- package/.docs/models/providers/nvidia.md +5 -14
- package/.docs/models/providers/ollama-cloud.md +8 -12
- package/.docs/models/providers/openai.md +2 -3
- package/.docs/models/providers/opencode-go.md +10 -9
- package/.docs/models/providers/opencode.md +7 -2
- package/.docs/models/providers/ovhcloud.md +7 -3
- package/.docs/models/providers/poe.md +2 -1
- package/.docs/models/providers/poolside.md +72 -0
- package/.docs/models/providers/routing-run.md +5 -3
- package/.docs/models/providers/scaleway.md +3 -5
- package/.docs/models/providers/siliconflow-cn.md +4 -11
- package/.docs/models/providers/siliconflow.md +7 -13
- package/.docs/models/providers/snowflake-cortex.md +89 -0
- package/.docs/models/providers/stepfun-ai.md +5 -5
- package/.docs/models/providers/stepfun.md +1 -1
- package/.docs/models/providers/synthetic.md +2 -1
- package/.docs/models/providers/togetherai.md +30 -24
- package/.docs/models/providers/umans-ai-coding-plan.md +3 -2
- package/.docs/models/providers/umans-ai.md +75 -0
- package/.docs/models/providers/vivgrid.md +1 -1
- package/.docs/models/providers/vultr.md +14 -12
- package/.docs/models/providers/wafer.ai.md +9 -4
- package/.docs/models/providers/xai.md +3 -3
- package/.docs/models/providers/xiaomi-token-plan-ams.md +15 -13
- package/.docs/models/providers/xiaomi-token-plan-cn.md +15 -13
- package/.docs/models/providers/xiaomi-token-plan-sgp.md +15 -13
- package/.docs/models/providers/xiaomi.md +10 -9
- package/.docs/models/providers/xpersona.md +4 -3
- package/.docs/models/providers/zai-coding-plan.md +2 -1
- package/.docs/models/providers/zai.md +2 -1
- package/.docs/models/providers/zeldoc.md +71 -0
- package/.docs/models/providers/zenmux.md +19 -3
- package/.docs/models/providers/zhipuai-coding-plan.md +3 -1
- package/.docs/models/providers/zhipuai.md +2 -1
- package/.docs/models/providers.md +12 -3
- package/.docs/reference/agents/agent.md +18 -5
- package/.docs/reference/harness/harness-class.md +3 -137
- package/.docs/reference/harness/session.md +128 -2
- package/.docs/reference/index.md +1 -0
- package/.docs/reference/tools/mcp-client.md +11 -0
- package/.docs/reference/voice/google-gemini-live.md +22 -0
- package/.docs/reference/workspace/archil-filesystem.md +203 -0
- package/.docs/reference/workspace/gcs-filesystem.md +1 -0
- package/.docs/reference/workspace/s3-filesystem.md +1 -0
- package/CHANGELOG.md +8 -0
- package/package.json +5 -5
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Alibaba Coding Plan (China)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 12 Alibaba Coding Plan (China) models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_CODING_PLAN_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Alibaba Coding Plan (China) documentation](https://help.aliyun.com/zh/model-studio/coding-plan).
|
|
6
6
|
|
|
@@ -42,7 +42,10 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `alibaba-coding-plan-cn/qwen3-coder-plus` | 1.0M | | | | | | — | — |
|
|
43
43
|
| `alibaba-coding-plan-cn/qwen3-max-2026-01-23` | 262K | | | | | | — | — |
|
|
44
44
|
| `alibaba-coding-plan-cn/qwen3.5-plus` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-coding-plan-cn/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
45
46
|
| `alibaba-coding-plan-cn/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
47
|
+
| `alibaba-coding-plan-cn/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
48
|
+
| `alibaba-coding-plan-cn/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
46
49
|
|
|
47
50
|
## Advanced configuration
|
|
48
51
|
|
|
@@ -72,7 +75,7 @@ const agent = new Agent({
|
|
|
72
75
|
model: ({ requestContext }) => {
|
|
73
76
|
const useAdvanced = requestContext.task === "complex";
|
|
74
77
|
return useAdvanced
|
|
75
|
-
? "alibaba-coding-plan-cn/qwen3.
|
|
78
|
+
? "alibaba-coding-plan-cn/qwen3.7-plus"
|
|
76
79
|
: "alibaba-coding-plan-cn/MiniMax-M2.5";
|
|
77
80
|
}
|
|
78
81
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Alibaba Coding Plan
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 12 Alibaba Coding Plan models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_CODING_PLAN_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Alibaba Coding Plan documentation](https://www.alibabacloud.com/help/en/model-studio/coding-plan).
|
|
6
6
|
|
|
@@ -42,7 +42,10 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `alibaba-coding-plan/qwen3-coder-plus` | 1.0M | | | | | | — | — |
|
|
43
43
|
| `alibaba-coding-plan/qwen3-max-2026-01-23` | 262K | | | | | | — | — |
|
|
44
44
|
| `alibaba-coding-plan/qwen3.5-plus` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-coding-plan/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
45
46
|
| `alibaba-coding-plan/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
47
|
+
| `alibaba-coding-plan/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
48
|
+
| `alibaba-coding-plan/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
46
49
|
|
|
47
50
|
## Advanced configuration
|
|
48
51
|
|
|
@@ -72,7 +75,7 @@ const agent = new Agent({
|
|
|
72
75
|
model: ({ requestContext }) => {
|
|
73
76
|
const useAdvanced = requestContext.task === "complex";
|
|
74
77
|
return useAdvanced
|
|
75
|
-
? "alibaba-coding-plan/qwen3.
|
|
78
|
+
? "alibaba-coding-plan/qwen3.7-plus"
|
|
76
79
|
: "alibaba-coding-plan/MiniMax-M2.5";
|
|
77
80
|
}
|
|
78
81
|
});
|
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
# Alibaba Token Plan (China)
|
|
2
|
+
|
|
3
|
+
Access 18 Alibaba Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Alibaba Token Plan (China) documentation](https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
ALIBABA_TOKEN_PLAN_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: "alibaba-token-plan-cn/MiniMax-M2.5"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Alibaba Token Plan (China) documentation](https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `alibaba-token-plan-cn/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
38
|
+
| `alibaba-token-plan-cn/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
39
|
+
| `alibaba-token-plan-cn/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan-cn/glm-5` | 203K | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan-cn/glm-5.1` | 203K | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan-cn/glm-5.2` | 1.0M | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan-cn/kimi-k2.5` | 262K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan-cn/kimi-k2.6` | 262K | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan-cn/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan-cn/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan-cn/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan-cn/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan-cn/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan-cn/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan-cn/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan-cn/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan-cn/wan2.7-image` | 8K | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan-cn/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
55
|
+
|
|
56
|
+
## Advanced configuration
|
|
57
|
+
|
|
58
|
+
### Custom headers
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "custom-agent",
|
|
63
|
+
name: "custom-agent",
|
|
64
|
+
model: {
|
|
65
|
+
url: "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
|
|
66
|
+
id: "alibaba-token-plan-cn/MiniMax-M2.5",
|
|
67
|
+
apiKey: process.env.ALIBABA_TOKEN_PLAN_API_KEY,
|
|
68
|
+
headers: {
|
|
69
|
+
"X-Custom-Header": "value"
|
|
70
|
+
}
|
|
71
|
+
}
|
|
72
|
+
});
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
### Dynamic model selection
|
|
76
|
+
|
|
77
|
+
```typescript
|
|
78
|
+
const agent = new Agent({
|
|
79
|
+
id: "dynamic-agent",
|
|
80
|
+
name: "Dynamic Agent",
|
|
81
|
+
model: ({ requestContext }) => {
|
|
82
|
+
const useAdvanced = requestContext.task === "complex";
|
|
83
|
+
return useAdvanced
|
|
84
|
+
? "alibaba-token-plan-cn/wan2.7-image-pro"
|
|
85
|
+
: "alibaba-token-plan-cn/MiniMax-M2.5";
|
|
86
|
+
}
|
|
87
|
+
});
|
|
88
|
+
```
|
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
# Alibaba Token Plan
|
|
2
|
+
|
|
3
|
+
Access 18 Alibaba Token Plan models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Alibaba Token Plan documentation](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
ALIBABA_TOKEN_PLAN_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: "alibaba-token-plan/MiniMax-M2.5"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Alibaba Token Plan documentation](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `alibaba-token-plan/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
38
|
+
| `alibaba-token-plan/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
39
|
+
| `alibaba-token-plan/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan/glm-5` | 203K | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan/glm-5.1` | 203K | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan/glm-5.2` | 1.0M | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan/kimi-k2.5` | 262K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan/kimi-k2.6` | 262K | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan/wan2.7-image` | 8K | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
55
|
+
|
|
56
|
+
## Advanced configuration
|
|
57
|
+
|
|
58
|
+
### Custom headers
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "custom-agent",
|
|
63
|
+
name: "custom-agent",
|
|
64
|
+
model: {
|
|
65
|
+
url: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
|
|
66
|
+
id: "alibaba-token-plan/MiniMax-M2.5",
|
|
67
|
+
apiKey: process.env.ALIBABA_TOKEN_PLAN_API_KEY,
|
|
68
|
+
headers: {
|
|
69
|
+
"X-Custom-Header": "value"
|
|
70
|
+
}
|
|
71
|
+
}
|
|
72
|
+
});
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
### Dynamic model selection
|
|
76
|
+
|
|
77
|
+
```typescript
|
|
78
|
+
const agent = new Agent({
|
|
79
|
+
id: "dynamic-agent",
|
|
80
|
+
name: "Dynamic Agent",
|
|
81
|
+
model: ({ requestContext }) => {
|
|
82
|
+
const useAdvanced = requestContext.task === "complex";
|
|
83
|
+
return useAdvanced
|
|
84
|
+
? "alibaba-token-plan/wan2.7-image-pro"
|
|
85
|
+
: "alibaba-token-plan/MiniMax-M2.5";
|
|
86
|
+
}
|
|
87
|
+
});
|
|
88
|
+
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Alibaba
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 51 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
|
|
|
@@ -79,9 +79,11 @@ for await (const chunk of stream) {
|
|
|
79
79
|
| `alibaba/qwen3.5-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
80
80
|
| `alibaba/qwen3.6-27b` | 262K | | | | | | $0.60 | $4 |
|
|
81
81
|
| `alibaba/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
|
|
82
|
+
| `alibaba/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
82
83
|
| `alibaba/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
|
|
83
84
|
| `alibaba/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
84
85
|
| `alibaba/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
86
|
+
| `alibaba/qwen3.7-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
85
87
|
| `alibaba/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
86
88
|
|
|
87
89
|
## Advanced configuration
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Ambient
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 3 Ambient models through Mastra's model router. Authentication is handled automatically using the `AMBIENT_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Ambient documentation](https://ambient.xyz).
|
|
6
6
|
|
|
@@ -32,10 +32,11 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `ambient/moonshotai/kimi-k2.6`
|
|
38
|
-
| `ambient/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ----------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `ambient/moonshotai/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
38
|
+
| `ambient/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.75 | $4 |
|
|
39
|
+
| `ambient/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
39
40
|
|
|
40
41
|
## Advanced configuration
|
|
41
42
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Anthropic
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 18 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
|
|
6
6
|
|
|
@@ -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: "anthropic/claude-3-5-haiku-
|
|
18
|
+
model: "anthropic/claude-3-5-haiku-latest"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -32,14 +32,8 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
34
34
|
| -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
35
|
-
| `anthropic/claude-3-5-haiku-20241022` | 200K | | | | | | $0.80 | $4 |
|
|
36
35
|
| `anthropic/claude-3-5-haiku-latest` | 200K | | | | | | $0.80 | $4 |
|
|
37
|
-
| `anthropic/claude-
|
|
38
|
-
| `anthropic/claude-3-5-sonnet-20241022` | 200K | | | | | | $3 | $15 |
|
|
39
|
-
| `anthropic/claude-3-7-sonnet-20250219` | 200K | | | | | | $3 | $15 |
|
|
40
|
-
| `anthropic/claude-3-haiku-20240307` | 200K | | | | | | $0.25 | $1 |
|
|
41
|
-
| `anthropic/claude-3-opus-20240229` | 200K | | | | | | $15 | $75 |
|
|
42
|
-
| `anthropic/claude-3-sonnet-20240229` | 200K | | | | | | $3 | $15 |
|
|
36
|
+
| `anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
|
|
43
37
|
| `anthropic/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
|
|
44
38
|
| `anthropic/claude-haiku-4-5-20251001` | 200K | | | | | | $1 | $5 |
|
|
45
39
|
| `anthropic/claude-opus-4-0` | 200K | | | | | | $15 | $75 |
|
|
@@ -50,6 +44,7 @@ for await (const chunk of stream) {
|
|
|
50
44
|
| `anthropic/claude-opus-4-5-20251101` | 200K | | | | | | $5 | $25 |
|
|
51
45
|
| `anthropic/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
52
46
|
| `anthropic/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
|
|
47
|
+
| `anthropic/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
|
|
53
48
|
| `anthropic/claude-sonnet-4-0` | 200K | | | | | | $3 | $15 |
|
|
54
49
|
| `anthropic/claude-sonnet-4-20250514` | 200K | | | | | | $3 | $15 |
|
|
55
50
|
| `anthropic/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
|
|
@@ -65,7 +60,7 @@ const agent = new Agent({
|
|
|
65
60
|
id: "custom-agent",
|
|
66
61
|
name: "custom-agent",
|
|
67
62
|
model: {
|
|
68
|
-
id: "anthropic/claude-3-5-haiku-
|
|
63
|
+
id: "anthropic/claude-3-5-haiku-latest",
|
|
69
64
|
apiKey: process.env.ANTHROPIC_API_KEY,
|
|
70
65
|
headers: {
|
|
71
66
|
"X-Custom-Header": "value"
|
|
@@ -84,7 +79,7 @@ const agent = new Agent({
|
|
|
84
79
|
const useAdvanced = requestContext.task === "complex";
|
|
85
80
|
return useAdvanced
|
|
86
81
|
? "anthropic/claude-sonnet-4-6"
|
|
87
|
-
: "anthropic/claude-3-5-haiku-
|
|
82
|
+
: "anthropic/claude-3-5-haiku-latest";
|
|
88
83
|
}
|
|
89
84
|
});
|
|
90
85
|
```
|
|
@@ -131,6 +126,8 @@ const response = await agent.generate("Hello!", {
|
|
|
131
126
|
|
|
132
127
|
**inferenceGeo** (`"us" | "global" | undefined`)
|
|
133
128
|
|
|
129
|
+
**fallbacks** (`{ model: string; max_tokens?: number | undefined; thinking?: Record<string, unknown> | undefined; output_config?: Record<string, unknown> | undefined; speed?: "fast" | "standard" | undefined; }[] | undefined`)
|
|
130
|
+
|
|
134
131
|
**anthropicBeta** (`string[] | undefined`)
|
|
135
132
|
|
|
136
133
|
**contextManagement** (`{ edits: ({ type: "clear_tool_uses_20250919"; trigger?: { type: "input_tokens"; value: number; } | { type: "tool_uses"; value: number; } | undefined; keep?: { type: "tool_uses"; value: number; } | undefined; clearAtLeast?: { ...; } | undefined; clearToolInputs?: boolean | undefined; excludeTools?: string[] | undefin...`)
|
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
# AnyAPI
|
|
2
|
+
|
|
3
|
+
Access 29 AnyAPI models through Mastra's model router. Authentication is handled automatically using the `ANYAPI_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [AnyAPI documentation](https://docs.anyapi.ai).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
ANYAPI_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: "anyapi/anthropic/claude-haiku-4-5"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [AnyAPI documentation](https://docs.anyapi.ai) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `anyapi/anthropic/claude-haiku-4-5` | 200K | | | | | | — | — |
|
|
38
|
+
| `anyapi/anthropic/claude-opus-4-6` | 1.0M | | | | | | — | — |
|
|
39
|
+
| `anyapi/anthropic/claude-opus-4-7` | 1.0M | | | | | | — | — |
|
|
40
|
+
| `anyapi/anthropic/claude-sonnet-4-5` | 200K | | | | | | — | — |
|
|
41
|
+
| `anyapi/anthropic/claude-sonnet-4-6` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `anyapi/cohere/command-r-plus-08-2024` | 128K | | | | | | — | — |
|
|
43
|
+
| `anyapi/deepseek/deepseek-chat` | 1.0M | | | | | | — | — |
|
|
44
|
+
| `anyapi/deepseek/deepseek-r1` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `anyapi/deepseek/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
46
|
+
| `anyapi/deepseek/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
47
|
+
| `anyapi/google/gemini-2.5-flash` | 1.0M | | | | | | — | — |
|
|
48
|
+
| `anyapi/google/gemini-2.5-flash-lite` | 1.0M | | | | | | — | — |
|
|
49
|
+
| `anyapi/google/gemini-2.5-pro` | 1.0M | | | | | | — | — |
|
|
50
|
+
| `anyapi/google/gemini-3-flash-preview` | 1.0M | | | | | | — | — |
|
|
51
|
+
| `anyapi/google/gemini-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
52
|
+
| `anyapi/mistralai/mistral-large-2512` | 262K | | | | | | — | — |
|
|
53
|
+
| `anyapi/openai/gpt-4.1` | 1.0M | | | | | | — | — |
|
|
54
|
+
| `anyapi/openai/gpt-4.1-mini` | 1.0M | | | | | | — | — |
|
|
55
|
+
| `anyapi/openai/gpt-5` | 400K | | | | | | — | — |
|
|
56
|
+
| `anyapi/openai/gpt-5-mini` | 400K | | | | | | — | — |
|
|
57
|
+
| `anyapi/openai/gpt-5.1` | 400K | | | | | | — | — |
|
|
58
|
+
| `anyapi/openai/gpt-5.2` | 400K | | | | | | — | — |
|
|
59
|
+
| `anyapi/openai/gpt-5.4` | 1.1M | | | | | | — | — |
|
|
60
|
+
| `anyapi/openai/o3` | 200K | | | | | | — | — |
|
|
61
|
+
| `anyapi/openai/o3-mini` | 200K | | | | | | — | — |
|
|
62
|
+
| `anyapi/openai/o4-mini` | 200K | | | | | | — | — |
|
|
63
|
+
| `anyapi/perplexity/sonar-pro` | 200K | | | | | | — | — |
|
|
64
|
+
| `anyapi/perplexity/sonar-reasoning-pro` | 128K | | | | | | — | — |
|
|
65
|
+
| `anyapi/xai/grok-4.3` | 1.0M | | | | | | — | — |
|
|
66
|
+
|
|
67
|
+
## Advanced configuration
|
|
68
|
+
|
|
69
|
+
### Custom headers
|
|
70
|
+
|
|
71
|
+
```typescript
|
|
72
|
+
const agent = new Agent({
|
|
73
|
+
id: "custom-agent",
|
|
74
|
+
name: "custom-agent",
|
|
75
|
+
model: {
|
|
76
|
+
url: "https://api.anyapi.ai/v1",
|
|
77
|
+
id: "anyapi/anthropic/claude-haiku-4-5",
|
|
78
|
+
apiKey: process.env.ANYAPI_API_KEY,
|
|
79
|
+
headers: {
|
|
80
|
+
"X-Custom-Header": "value"
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
});
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
### Dynamic model selection
|
|
87
|
+
|
|
88
|
+
```typescript
|
|
89
|
+
const agent = new Agent({
|
|
90
|
+
id: "dynamic-agent",
|
|
91
|
+
name: "Dynamic Agent",
|
|
92
|
+
model: ({ requestContext }) => {
|
|
93
|
+
const useAdvanced = requestContext.task === "complex";
|
|
94
|
+
return useAdvanced
|
|
95
|
+
? "anyapi/xai/grok-4.3"
|
|
96
|
+
: "anyapi/anthropic/claude-haiku-4-5";
|
|
97
|
+
}
|
|
98
|
+
});
|
|
99
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
Access 11 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
4
4
|
|
|
5
|
-
Learn more in the [Baseten documentation](https://docs.baseten.co
|
|
5
|
+
Learn more in the [Baseten documentation](https://docs.baseten.co).
|
|
6
6
|
|
|
7
7
|
```bash
|
|
8
8
|
BASETEN_API_KEY=your-api-key
|
|
@@ -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: "baseten/
|
|
18
|
+
model: "baseten/deepseek-ai/DeepSeek-V4-Pro"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -28,23 +28,23 @@ for await (const chunk of stream) {
|
|
|
28
28
|
}
|
|
29
29
|
```
|
|
30
30
|
|
|
31
|
-
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Baseten documentation](https://docs.baseten.co
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Baseten documentation](https://docs.baseten.co) for details.
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `baseten/deepseek-ai/DeepSeek-
|
|
38
|
-
| `baseten/
|
|
39
|
-
| `baseten/
|
|
40
|
-
| `baseten/
|
|
41
|
-
| `baseten/
|
|
42
|
-
| `baseten/
|
|
43
|
-
| `baseten/
|
|
44
|
-
| `baseten/
|
|
45
|
-
| `baseten/zai-org/GLM-
|
|
46
|
-
| `baseten/zai-org/GLM-
|
|
47
|
-
| `baseten/zai-org/GLM-5`
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| -------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `baseten/deepseek-ai/DeepSeek-V4-Pro` | 131K | | | | | | $2 | $3 |
|
|
38
|
+
| `baseten/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
39
|
+
| `baseten/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
40
|
+
| `baseten/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
41
|
+
| `baseten/nvidia/Nemotron-120B-A12B` | 203K | | | | | | $0.30 | $0.75 |
|
|
42
|
+
| `baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B` | 203K | | | | | | $0.60 | $2 |
|
|
43
|
+
| `baseten/openai/gpt-oss-120b` | 128K | | | | | | $0.10 | $0.50 |
|
|
44
|
+
| `baseten/zai-org/GLM-4.7` | 200K | | | | | | $0.60 | $2 |
|
|
45
|
+
| `baseten/zai-org/GLM-5` | 203K | | | | | | $0.95 | $3 |
|
|
46
|
+
| `baseten/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
47
|
+
| `baseten/zai-org/GLM-5.2` | 131K | | | | | | $2 | $5 |
|
|
48
48
|
|
|
49
49
|
## Advanced configuration
|
|
50
50
|
|
|
@@ -56,7 +56,7 @@ const agent = new Agent({
|
|
|
56
56
|
name: "custom-agent",
|
|
57
57
|
model: {
|
|
58
58
|
url: "https://inference.baseten.co/v1",
|
|
59
|
-
id: "baseten/
|
|
59
|
+
id: "baseten/deepseek-ai/DeepSeek-V4-Pro",
|
|
60
60
|
apiKey: process.env.BASETEN_API_KEY,
|
|
61
61
|
headers: {
|
|
62
62
|
"X-Custom-Header": "value"
|
|
@@ -74,8 +74,8 @@ const agent = new Agent({
|
|
|
74
74
|
model: ({ requestContext }) => {
|
|
75
75
|
const useAdvanced = requestContext.task === "complex";
|
|
76
76
|
return useAdvanced
|
|
77
|
-
? "baseten/zai-org/GLM-5"
|
|
78
|
-
: "baseten/
|
|
77
|
+
? "baseten/zai-org/GLM-5.2"
|
|
78
|
+
: "baseten/deepseek-ai/DeepSeek-V4-Pro";
|
|
79
79
|
}
|
|
80
80
|
});
|
|
81
81
|
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Cerebras
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 2 Cerebras models through Mastra's model router. Authentication is handled automatically using the `CEREBRAS_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Cerebras documentation](https://inference-docs.cerebras.ai/models/overview).
|
|
6
6
|
|
|
@@ -30,12 +30,10 @@ for await (const chunk of stream) {
|
|
|
30
30
|
|
|
31
31
|
## Models
|
|
32
32
|
|
|
33
|
-
| Model
|
|
34
|
-
|
|
|
35
|
-
| `cerebras/gpt-oss-120b`
|
|
36
|
-
| `cerebras/
|
|
37
|
-
| `cerebras/qwen-3-235b-a22b-instruct-2507` | 131K | | | | | | $0.60 | $1 |
|
|
38
|
-
| `cerebras/zai-glm-4.7` | 131K | | | | | | $2 | $3 |
|
|
33
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
34
|
+
| ----------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
35
|
+
| `cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
|
|
36
|
+
| `cerebras/zai-glm-4.7` | 131K | | | | | | $2 | $3 |
|
|
39
37
|
|
|
40
38
|
## Advanced configuration
|
|
41
39
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Claudinio
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 2 Claudinio models through Mastra's model router. Authentication is handled automatically using the `CLAUDINIO_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Claudinio documentation](https://claudin.io).
|
|
6
6
|
|
|
@@ -35,6 +35,7 @@ for await (const chunk of stream) {
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| --------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `claudinio/claudinio` | 256K | | | | | | $0.50 | $2 |
|
|
38
|
+
| `claudinio/claudius` | 256K | | | | | | $3 | $8 |
|
|
38
39
|
|
|
39
40
|
## Advanced configuration
|
|
40
41
|
|
|
@@ -64,7 +65,7 @@ const agent = new Agent({
|
|
|
64
65
|
model: ({ requestContext }) => {
|
|
65
66
|
const useAdvanced = requestContext.task === "complex";
|
|
66
67
|
return useAdvanced
|
|
67
|
-
? "claudinio/
|
|
68
|
+
? "claudinio/claudius"
|
|
68
69
|
: "claudinio/claudinio";
|
|
69
70
|
}
|
|
70
71
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Cloudflare Workers AI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 22 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
|
|
6
6
|
|
|
@@ -37,13 +37,8 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| -------------------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
38
38
|
| `cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it` | 128K | | | | | | $0.35 | $0.56 |
|
|
39
39
|
| `cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b` | 80K | | | | | | $0.50 | $5 |
|
|
40
|
-
| `cloudflare-workers-ai/@cf/google/gemma-3-12b-it` | 80K | | | | | | $0.34 | $0.56 |
|
|
41
40
|
| `cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it` | 256K | | | | | | $0.10 | $0.30 |
|
|
42
41
|
| `cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro` | 131K | | | | | | $0.02 | $0.11 |
|
|
43
|
-
| `cloudflare-workers-ai/@cf/meta/llama-2-7b-chat-fp16` | 4K | | | | | | $0.56 | $7 |
|
|
44
|
-
| `cloudflare-workers-ai/@cf/meta/llama-3-8b-instruct` | 8K | | | | | | $0.28 | $0.83 |
|
|
45
|
-
| `cloudflare-workers-ai/@cf/meta/llama-3-8b-instruct-awq` | 8K | | | | | | $0.12 | $0.27 |
|
|
46
|
-
| `cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-awq` | 8K | | | | | | $0.12 | $0.27 |
|
|
47
42
|
| `cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8` | 32K | | | | | | $0.15 | $0.29 |
|
|
48
43
|
| `cloudflare-workers-ai/@cf/meta/llama-3.2-11b-vision-instruct` | 128K | | | | | | $0.05 | $0.68 |
|
|
49
44
|
| `cloudflare-workers-ai/@cf/meta/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
|
|
@@ -51,10 +46,9 @@ for await (const chunk of stream) {
|
|
|
51
46
|
| `cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast` | 24K | | | | | | $0.29 | $2 |
|
|
52
47
|
| `cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct` | 131K | | | | | | $0.27 | $0.85 |
|
|
53
48
|
| `cloudflare-workers-ai/@cf/meta/llama-guard-3-8b` | 131K | | | | | | $0.48 | $0.03 |
|
|
54
|
-
| `cloudflare-workers-ai/@cf/mistral/mistral-7b-instruct-v0.1` | 3K | | | | | | $0.11 | $0.19 |
|
|
55
49
|
| `cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct` | 128K | | | | | | $0.35 | $0.56 |
|
|
56
|
-
| `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.5` | 256K | | | | | | $0.60 | $3 |
|
|
57
50
|
| `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
51
|
+
| `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
58
52
|
| `cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b` | 256K | | | | | | $0.50 | $2 |
|
|
59
53
|
| `cloudflare-workers-ai/@cf/openai/gpt-oss-120b` | 128K | | | | | | $0.35 | $0.75 |
|
|
60
54
|
| `cloudflare-workers-ai/@cf/openai/gpt-oss-20b` | 128K | | | | | | $0.20 | $0.30 |
|
|
@@ -62,6 +56,7 @@ for await (const chunk of stream) {
|
|
|
62
56
|
| `cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8` | 33K | | | | | | $0.05 | $0.34 |
|
|
63
57
|
| `cloudflare-workers-ai/@cf/qwen/qwq-32b` | 24K | | | | | | $0.66 | $1 |
|
|
64
58
|
| `cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash` | 131K | | | | | | $0.06 | $0.40 |
|
|
59
|
+
| `cloudflare-workers-ai/@cf/zai-org/glm-5.2` | 262K | | | | | | $1 | $4 |
|
|
65
60
|
|
|
66
61
|
## Advanced configuration
|
|
67
62
|
|
|
@@ -91,7 +86,7 @@ const agent = new Agent({
|
|
|
91
86
|
model: ({ requestContext }) => {
|
|
92
87
|
const useAdvanced = requestContext.task === "complex";
|
|
93
88
|
return useAdvanced
|
|
94
|
-
? "cloudflare-workers-ai/@cf/zai-org/glm-
|
|
89
|
+
? "cloudflare-workers-ai/@cf/zai-org/glm-5.2"
|
|
95
90
|
: "cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it";
|
|
96
91
|
}
|
|
97
92
|
});
|