@mastra/mcp-docs-server 1.2.8-alpha.9 → 1.2.9-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/agent-builder/integrations.md +1 -3
- package/.docs/docs/agent-builder/overview.md +2 -0
- package/.docs/docs/agents/overview.md +17 -13
- package/.docs/docs/agents/skills.md +1 -3
- package/.docs/docs/agents/structured-output.md +2 -0
- package/.docs/docs/agents/using-tools.md +66 -49
- package/.docs/docs/browser/agent-browser.md +1 -0
- package/.docs/docs/browser/firecrawl.md +129 -0
- package/.docs/docs/browser/overview.md +16 -2
- package/.docs/docs/capabilities/channels/slack.md +111 -1
- package/.docs/docs/deployment/mastra-server.md +35 -0
- package/.docs/docs/deployment/monorepo.md +2 -0
- package/.docs/docs/deployment/overview.md +6 -0
- package/.docs/docs/deployment/sandbox.md +277 -0
- package/.docs/docs/editor/overview.md +2 -6
- package/.docs/docs/editor/tools.md +2 -6
- package/.docs/docs/evals/running-in-ci.md +3 -9
- package/.docs/docs/getting-started/build-with-ai.md +2 -6
- package/.docs/docs/getting-started/manual-install.md +1 -1
- package/.docs/docs/index.md +17 -13
- package/.docs/docs/long-running-agents/background-tasks.md +2 -2
- package/.docs/docs/long-running-agents/goals.md +3 -1
- package/.docs/docs/mastra-platform/database.md +12 -6
- package/.docs/docs/mastra-platform/deploy.md +14 -7
- package/.docs/docs/mastra-platform/environments.md +5 -4
- package/.docs/docs/mastra-platform/observability.md +4 -12
- package/.docs/docs/mastra-platform/overview.md +1 -1
- package/.docs/docs/mastra-platform/regions.md +73 -0
- package/.docs/docs/mastra-platform/workspace.md +111 -0
- package/.docs/docs/memory/observational-memory.md +77 -2
- package/.docs/docs/memory/overview.md +4 -0
- package/.docs/docs/observability/feedback.md +4 -0
- package/.docs/docs/observability/integrations/bridges/otel.md +1 -3
- package/.docs/docs/observability/integrations/exporters/otel.md +1 -3
- package/.docs/docs/server/auth/fga.md +40 -0
- package/.docs/docs/server/auth/simple-auth.md +1 -3
- package/.docs/docs/studio/overview.md +2 -0
- package/.docs/docs/workflows/control-flow.md +1 -3
- package/.docs/docs/workspace/filesystem.md +1 -0
- package/.docs/docs/workspace/sandbox.md +1 -0
- package/.docs/guides/getting-started/quickstart.md +40 -25
- package/.docs/guides/index.md +1 -1
- package/.docs/guides/migrations/vnext-to-standard-apis.md +1 -3
- package/.docs/models/environment-variables.md +2 -0
- package/.docs/models/gateways/netlify.md +3 -6
- package/.docs/models/gateways/openrouter.md +343 -346
- package/.docs/models/gateways/vercel.md +6 -5
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/aki-io.md +78 -0
- package/.docs/models/providers/alibaba-token-plan-cn.md +22 -21
- package/.docs/models/providers/alibaba-token-plan.md +22 -21
- package/.docs/models/providers/ambient.md +12 -10
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/cline-pass.md +82 -0
- package/.docs/models/providers/cortecs.md +2 -1
- package/.docs/models/providers/crossmodel.md +2 -1
- package/.docs/models/providers/deepinfra.md +4 -7
- package/.docs/models/providers/deepseek.md +3 -1
- package/.docs/models/providers/empiriolabs.md +2 -1
- package/.docs/models/providers/google.md +4 -2
- package/.docs/models/providers/huggingface.md +2 -1
- package/.docs/models/providers/inferx.md +3 -3
- package/.docs/models/providers/kenari.md +44 -29
- package/.docs/models/providers/kimi-for-coding.md +6 -9
- package/.docs/models/providers/llmgateway.md +4 -1
- package/.docs/models/providers/moonshotai-cn.md +1 -1
- package/.docs/models/providers/moonshotai.md +1 -1
- package/.docs/models/providers/nebius.md +3 -1
- package/.docs/models/providers/novita-ai.md +3 -1
- package/.docs/models/providers/opencode-go.md +4 -3
- package/.docs/models/providers/opencode.md +4 -2
- package/.docs/models/providers/poolside.md +2 -2
- package/.docs/models/providers/togetherai.md +2 -6
- package/.docs/models/providers/wandb.md +2 -1
- package/.docs/models/providers/zenmux.md +3 -1
- package/.docs/models/providers.md +2 -0
- package/.docs/reference/agent-controller/session.md +13 -0
- package/.docs/reference/agents/agent.md +13 -1
- package/.docs/reference/agents/generate.md +18 -0
- package/.docs/reference/browser/firecrawl-browser.md +71 -0
- package/.docs/reference/cli/create-mastra.md +118 -43
- package/.docs/reference/cli/mastra.md +59 -5
- package/.docs/reference/code-sdk/mount-agent-controller.md +4 -4
- package/.docs/reference/core/getMCPServer.md +1 -3
- package/.docs/reference/core/getMCPServerById.md +1 -3
- package/.docs/reference/core/getWorkflow.md +1 -3
- package/.docs/reference/core/listMCPServers.md +2 -6
- package/.docs/reference/datasets/addItem.md +1 -3
- package/.docs/reference/datasets/addItems.md +1 -3
- package/.docs/reference/datasets/compareExperiments.md +1 -3
- package/.docs/reference/datasets/create.md +1 -3
- package/.docs/reference/datasets/dataset.md +2 -6
- package/.docs/reference/datasets/datasets-manager.md +5 -15
- package/.docs/reference/datasets/delete.md +1 -3
- package/.docs/reference/datasets/deleteExperiment.md +1 -3
- package/.docs/reference/datasets/deleteItem.md +1 -3
- package/.docs/reference/datasets/deleteItems.md +1 -3
- package/.docs/reference/datasets/get.md +1 -3
- package/.docs/reference/datasets/getDetails.md +1 -3
- package/.docs/reference/datasets/getExperiment.md +1 -3
- package/.docs/reference/datasets/getItem.md +1 -3
- package/.docs/reference/datasets/getItemHistory.md +1 -3
- package/.docs/reference/datasets/list.md +1 -3
- package/.docs/reference/datasets/listExperimentResults.md +1 -3
- package/.docs/reference/datasets/listExperiments.md +1 -3
- package/.docs/reference/datasets/listItems.md +1 -3
- package/.docs/reference/datasets/listVersions.md +1 -3
- package/.docs/reference/datasets/startExperiment.md +1 -3
- package/.docs/reference/datasets/startExperimentAsync.md +1 -3
- package/.docs/reference/datasets/update.md +1 -3
- package/.docs/reference/datasets/updateItem.md +1 -3
- package/.docs/reference/editor/mastra-editor.md +1 -3
- package/.docs/reference/evals/context-recall.md +205 -0
- package/.docs/reference/evals/create-scorer.md +3 -9
- package/.docs/reference/evals/mastra-scorer.md +1 -3
- package/.docs/reference/file-based-agents/tools.md +7 -6
- package/.docs/reference/index.md +5 -0
- package/.docs/reference/memory/observational-memory.md +21 -0
- package/.docs/reference/observability/tracing/exporters/posthog.md +39 -1
- package/.docs/reference/observability/tracing/processors/sensitive-data-filter.md +1 -3
- package/.docs/reference/processors/token-limiter-processor.md +1 -3
- package/.docs/reference/rag/database-config.md +12 -0
- package/.docs/reference/streaming/agents/stream.md +2 -0
- package/.docs/reference/templates/overview.md +6 -32
- package/.docs/reference/tools/create-tool.md +78 -52
- package/.docs/reference/tools/mcp-client.md +8 -24
- package/.docs/reference/tools/mcp-server.md +143 -44
- package/.docs/reference/tools/tavily.md +1 -1
- package/.docs/reference/tools/vector-query-tool.md +22 -0
- package/.docs/reference/vectors/mongodb.md +2 -0
- package/.docs/reference/vectors/turbopuffer.md +4 -0
- package/.docs/reference/voice/mistral.md +127 -0
- package/.docs/reference/workspace/daytona-sandbox.md +2 -6
- package/.docs/reference/workspace/platform-filesystem.md +182 -0
- package/.docs/reference/workspace/platform-sandbox.md +200 -0
- package/.docs/reference/workspace/railway-sandbox.md +37 -1
- package/CHANGELOG.md +71 -0
- package/dist/{chunk-GLPCVXXO.js → chunk-HGADBLKG.js} +2 -2
- package/dist/{chunk-GLPCVXXO.js.map → chunk-HGADBLKG.js.map} +1 -1
- package/dist/index.js +1 -1
- package/dist/stdio.js +1 -1
- package/dist/tools/docs.d.ts.map +1 -1
- package/package.json +8 -8
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Vercel
|
|
4
4
|
|
|
5
|
-
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
5
|
+
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 306 models through Mastra's model router.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
|
|
8
8
|
|
|
@@ -140,6 +140,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
140
140
|
| `google/gemini-3.1-flash-lite-preview` |
|
|
141
141
|
| `google/gemini-3.1-pro-preview` |
|
|
142
142
|
| `google/gemini-3.5-flash` |
|
|
143
|
+
| `google/gemini-3.5-flash-lite` |
|
|
144
|
+
| `google/gemini-3.6-flash` |
|
|
143
145
|
| `google/gemini-embedding-001` |
|
|
144
146
|
| `google/gemini-embedding-2` |
|
|
145
147
|
| `google/gemini-omni-flash-preview` |
|
|
@@ -171,10 +173,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
171
173
|
| `kwaipilot/kat-coder-pro-v2.5` |
|
|
172
174
|
| `meta/llama-3.1-70b` |
|
|
173
175
|
| `meta/llama-3.1-8b` |
|
|
174
|
-
| `meta/llama-3.2-11b` |
|
|
175
|
-
| `meta/llama-3.2-1b` |
|
|
176
|
-
| `meta/llama-3.2-3b` |
|
|
177
|
-
| `meta/llama-3.2-90b` |
|
|
178
176
|
| `meta/llama-3.3-70b` |
|
|
179
177
|
| `meta/llama-4-maverick` |
|
|
180
178
|
| `meta/llama-4-scout` |
|
|
@@ -280,6 +278,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
280
278
|
| `perplexity/sonar` |
|
|
281
279
|
| `perplexity/sonar-pro` |
|
|
282
280
|
| `perplexity/sonar-reasoning-pro` |
|
|
281
|
+
| `poolside/laguna-s-2.1` |
|
|
282
|
+
| `poolside/laguna-s-2.1-free` |
|
|
283
283
|
| `prodia/flux-fast-schnell` |
|
|
284
284
|
| `quiverai/arrow-1.1` |
|
|
285
285
|
| `recraft/recraft-v2` |
|
|
@@ -293,6 +293,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
293
293
|
| `sakana/fugu-ultra` |
|
|
294
294
|
| `stepfun/step-3.5-flash` |
|
|
295
295
|
| `stepfun/step-3.7-flash` |
|
|
296
|
+
| `tencent/hy3` |
|
|
296
297
|
| `thinkingmachines/inkling` |
|
|
297
298
|
| `voyage/rerank-2.5` |
|
|
298
299
|
| `voyage/rerank-2.5-lite` |
|
package/.docs/models/index.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Model Providers
|
|
4
4
|
|
|
5
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
5
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 4898 models from 158 providers through a single API.
|
|
6
6
|
|
|
7
7
|
## Features
|
|
8
8
|
|
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# AKI.IO
|
|
4
|
+
|
|
5
|
+
Access 6 AKI.IO models through Mastra's model router. Authentication is handled automatically using the `AKI_IO_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [AKI.IO documentation](https://aki.io/docs/).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
AKI_IO_API_KEY=your-api-key
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
```typescript
|
|
14
|
+
import { Agent } from "@mastra/core/agent";
|
|
15
|
+
|
|
16
|
+
const agent = new Agent({
|
|
17
|
+
id: "my-agent",
|
|
18
|
+
name: "My Agent",
|
|
19
|
+
instructions: "You are a helpful assistant",
|
|
20
|
+
model: "aki-io/gemma4-26b"
|
|
21
|
+
});
|
|
22
|
+
|
|
23
|
+
// Generate a response
|
|
24
|
+
const response = await agent.generate("Hello!");
|
|
25
|
+
|
|
26
|
+
// Stream a response
|
|
27
|
+
const stream = await agent.stream("Tell me a story");
|
|
28
|
+
for await (const chunk of stream) {
|
|
29
|
+
console.log(chunk);
|
|
30
|
+
}
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [AKI.IO documentation](https://aki.io/docs/) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ----------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `aki-io/gemma4-26b` | 256K | | | | | | $0.10 | $0.50 |
|
|
40
|
+
| `aki-io/gpt-oss-120b` | 128K | | | | | | $0.15 | $0.55 |
|
|
41
|
+
| `aki-io/kimi-k2.7-code-1100b` | 262K | | | | | | $0.86 | $3 |
|
|
42
|
+
| `aki-io/minimax-m2.5-230b` | 197K | | | | | | $0.25 | $1 |
|
|
43
|
+
| `aki-io/mistral4-119b` | 262K | | | | | | $0.20 | $0.60 |
|
|
44
|
+
| `aki-io/qwen3.6-35b` | 256K | | | | | | $0.15 | $0.50 |
|
|
45
|
+
|
|
46
|
+
## Advanced configuration
|
|
47
|
+
|
|
48
|
+
### Custom headers
|
|
49
|
+
|
|
50
|
+
```typescript
|
|
51
|
+
const agent = new Agent({
|
|
52
|
+
id: "custom-agent",
|
|
53
|
+
name: "custom-agent",
|
|
54
|
+
model: {
|
|
55
|
+
url: "https://aki.io/v1",
|
|
56
|
+
id: "aki-io/gemma4-26b",
|
|
57
|
+
apiKey: process.env.AKI_IO_API_KEY,
|
|
58
|
+
headers: {
|
|
59
|
+
"X-Custom-Header": "value"
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
});
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
### Dynamic model selection
|
|
66
|
+
|
|
67
|
+
```typescript
|
|
68
|
+
const agent = new Agent({
|
|
69
|
+
id: "dynamic-agent",
|
|
70
|
+
name: "Dynamic Agent",
|
|
71
|
+
model: ({ requestContext }) => {
|
|
72
|
+
const useAdvanced = requestContext.task === "complex";
|
|
73
|
+
return useAdvanced
|
|
74
|
+
? "aki-io/qwen3.6-35b"
|
|
75
|
+
: "aki-io/gemma4-26b";
|
|
76
|
+
}
|
|
77
|
+
});
|
|
78
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan (China)
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 19 Alibaba Token Plan (China) models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba Token Plan (China) documentation](https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview).
|
|
8
8
|
|
|
@@ -34,26 +34,27 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `alibaba-token-plan-cn/deepseek-v3.2`
|
|
40
|
-
| `alibaba-token-plan-cn/deepseek-v4-flash`
|
|
41
|
-
| `alibaba-token-plan-cn/deepseek-v4-pro`
|
|
42
|
-
| `alibaba-token-plan-cn/glm-5`
|
|
43
|
-
| `alibaba-token-plan-cn/glm-5.1`
|
|
44
|
-
| `alibaba-token-plan-cn/glm-5.2`
|
|
45
|
-
| `alibaba-token-plan-cn/kimi-k2.5`
|
|
46
|
-
| `alibaba-token-plan-cn/kimi-k2.6`
|
|
47
|
-
| `alibaba-token-plan-cn/kimi-k2.7-code`
|
|
48
|
-
| `alibaba-token-plan-cn/MiniMax-M2.5`
|
|
49
|
-
| `alibaba-token-plan-cn/qwen-image-2.0`
|
|
50
|
-
| `alibaba-token-plan-cn/qwen-image-2.0-pro`
|
|
51
|
-
| `alibaba-token-plan-cn/qwen3.6-flash`
|
|
52
|
-
| `alibaba-token-plan-cn/qwen3.6-plus`
|
|
53
|
-
| `alibaba-token-plan-cn/qwen3.7-max`
|
|
54
|
-
| `alibaba-token-plan-cn/qwen3.7-plus`
|
|
55
|
-
| `alibaba-token-plan-cn/
|
|
56
|
-
| `alibaba-token-plan-cn/wan2.7-image
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `alibaba-token-plan-cn/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan-cn/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan-cn/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan-cn/glm-5` | 203K | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan-cn/glm-5.1` | 203K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan-cn/glm-5.2` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan-cn/kimi-k2.5` | 262K | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan-cn/kimi-k2.6` | 262K | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan-cn/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan-cn/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan-cn/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan-cn/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan-cn/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan-cn/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan-cn/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan-cn/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
55
|
+
| `alibaba-token-plan-cn/qwen3.8-max-preview` | 1.0M | | | | | | — | — |
|
|
56
|
+
| `alibaba-token-plan-cn/wan2.7-image` | 8K | | | | | | — | — |
|
|
57
|
+
| `alibaba-token-plan-cn/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
57
58
|
|
|
58
59
|
## Advanced configuration
|
|
59
60
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Alibaba Token Plan
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 19 Alibaba Token Plan models through Mastra's model router. Authentication is handled automatically using the `ALIBABA_TOKEN_PLAN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Alibaba Token Plan documentation](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview).
|
|
8
8
|
|
|
@@ -34,26 +34,27 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `alibaba-token-plan/deepseek-v3.2`
|
|
40
|
-
| `alibaba-token-plan/deepseek-v4-flash`
|
|
41
|
-
| `alibaba-token-plan/deepseek-v4-pro`
|
|
42
|
-
| `alibaba-token-plan/glm-5`
|
|
43
|
-
| `alibaba-token-plan/glm-5.1`
|
|
44
|
-
| `alibaba-token-plan/glm-5.2`
|
|
45
|
-
| `alibaba-token-plan/kimi-k2.5`
|
|
46
|
-
| `alibaba-token-plan/kimi-k2.6`
|
|
47
|
-
| `alibaba-token-plan/kimi-k2.7-code`
|
|
48
|
-
| `alibaba-token-plan/MiniMax-M2.5`
|
|
49
|
-
| `alibaba-token-plan/qwen-image-2.0`
|
|
50
|
-
| `alibaba-token-plan/qwen-image-2.0-pro`
|
|
51
|
-
| `alibaba-token-plan/qwen3.6-flash`
|
|
52
|
-
| `alibaba-token-plan/qwen3.6-plus`
|
|
53
|
-
| `alibaba-token-plan/qwen3.7-max`
|
|
54
|
-
| `alibaba-token-plan/qwen3.7-plus`
|
|
55
|
-
| `alibaba-token-plan/
|
|
56
|
-
| `alibaba-token-plan/wan2.7-image
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ---------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `alibaba-token-plan/deepseek-v3.2` | 131K | | | | | | — | — |
|
|
40
|
+
| `alibaba-token-plan/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
41
|
+
| `alibaba-token-plan/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `alibaba-token-plan/glm-5` | 203K | | | | | | — | — |
|
|
43
|
+
| `alibaba-token-plan/glm-5.1` | 203K | | | | | | — | — |
|
|
44
|
+
| `alibaba-token-plan/glm-5.2` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `alibaba-token-plan/kimi-k2.5` | 262K | | | | | | — | — |
|
|
46
|
+
| `alibaba-token-plan/kimi-k2.6` | 262K | | | | | | — | — |
|
|
47
|
+
| `alibaba-token-plan/kimi-k2.7-code` | 262K | | | | | | — | — |
|
|
48
|
+
| `alibaba-token-plan/MiniMax-M2.5` | 197K | | | | | | — | — |
|
|
49
|
+
| `alibaba-token-plan/qwen-image-2.0` | 8K | | | | | | — | — |
|
|
50
|
+
| `alibaba-token-plan/qwen-image-2.0-pro` | 8K | | | | | | — | — |
|
|
51
|
+
| `alibaba-token-plan/qwen3.6-flash` | 1.0M | | | | | | — | — |
|
|
52
|
+
| `alibaba-token-plan/qwen3.6-plus` | 1.0M | | | | | | — | — |
|
|
53
|
+
| `alibaba-token-plan/qwen3.7-max` | 1.0M | | | | | | — | — |
|
|
54
|
+
| `alibaba-token-plan/qwen3.7-plus` | 1.0M | | | | | | — | — |
|
|
55
|
+
| `alibaba-token-plan/qwen3.8-max-preview` | 1.0M | | | | | | — | — |
|
|
56
|
+
| `alibaba-token-plan/wan2.7-image` | 8K | | | | | | — | — |
|
|
57
|
+
| `alibaba-token-plan/wan2.7-image-pro` | 8K | | | | | | — | — |
|
|
57
58
|
|
|
58
59
|
## Advanced configuration
|
|
59
60
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Ambient
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 9 Ambient models through Mastra's model router. Authentication is handled automatically using the `AMBIENT_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Ambient documentation](https://ambient.xyz).
|
|
8
8
|
|
|
@@ -34,15 +34,17 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
## Models
|
|
36
36
|
|
|
37
|
-
| Model
|
|
38
|
-
|
|
|
39
|
-
| `ambient/ambient/large`
|
|
40
|
-
| `ambient/
|
|
41
|
-
| `ambient/moonshotai/kimi-k2.
|
|
42
|
-
| `ambient/
|
|
43
|
-
| `ambient/
|
|
44
|
-
| `ambient/
|
|
45
|
-
| `ambient/
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `ambient/ambient/large` | 101K | | | | | | $1 | $4 |
|
|
40
|
+
| `ambient/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.50 | $0.80 |
|
|
41
|
+
| `ambient/moonshotai/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
42
|
+
| `ambient/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.85 | $4 |
|
|
43
|
+
| `ambient/stepfun/step-3.7-flash` | 262K | | | | | | $0.19 | $1 |
|
|
44
|
+
| `ambient/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
|
|
45
|
+
| `ambient/z-ai/glm-5.2` | 101K | | | | | | $1 | $4 |
|
|
46
|
+
| `ambient/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
47
|
+
| `ambient/zai-org/GLM-5.2-FP8` | 203K | | | | | | $1 | $4 |
|
|
46
48
|
|
|
47
49
|
## Advanced configuration
|
|
48
50
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Baseten
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 12 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Baseten documentation](https://docs.baseten.co).
|
|
8
8
|
|
|
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
|
|
|
43
43
|
| `baseten/nvidia/Nemotron-120B-A12B` | 203K | | | | | | $0.30 | $0.75 |
|
|
44
44
|
| `baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B` | 203K | | | | | | $0.60 | $2 |
|
|
45
45
|
| `baseten/openai/gpt-oss-120b` | 128K | | | | | | $0.10 | $0.50 |
|
|
46
|
+
| `baseten/thinkingmachines/inkling` | 1.0M | | | | | | $1 | $4 |
|
|
46
47
|
| `baseten/zai-org/GLM-4.7` | 200K | | | | | | $0.60 | $2 |
|
|
47
48
|
| `baseten/zai-org/GLM-5` | 203K | | | | | | $0.95 | $3 |
|
|
48
49
|
| `baseten/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
|
|
2
|
+
|
|
3
|
+
# ClinePass
|
|
4
|
+
|
|
5
|
+
Access 10 ClinePass models through Mastra's model router. Authentication is handled automatically using the `CLINE_API_KEY` environment variable.
|
|
6
|
+
|
|
7
|
+
Learn more in the [ClinePass documentation](https://docs.cline.bot/getting-started/clinepass).
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
CLINE_API_KEY=your-api-key
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
```typescript
|
|
14
|
+
import { Agent } from "@mastra/core/agent";
|
|
15
|
+
|
|
16
|
+
const agent = new Agent({
|
|
17
|
+
id: "my-agent",
|
|
18
|
+
name: "My Agent",
|
|
19
|
+
instructions: "You are a helpful assistant",
|
|
20
|
+
model: "cline-pass/cline-pass/deepseek-v4-flash"
|
|
21
|
+
});
|
|
22
|
+
|
|
23
|
+
// Generate a response
|
|
24
|
+
const response = await agent.generate("Hello!");
|
|
25
|
+
|
|
26
|
+
// Stream a response
|
|
27
|
+
const stream = await agent.stream("Tell me a story");
|
|
28
|
+
for await (const chunk of stream) {
|
|
29
|
+
console.log(chunk);
|
|
30
|
+
}
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [ClinePass documentation](https://docs.cline.bot/getting-started/clinepass) for details.
|
|
34
|
+
|
|
35
|
+
## Models
|
|
36
|
+
|
|
37
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
|
+
| ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
|
+
| `cline-pass/cline-pass/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
40
|
+
| `cline-pass/cline-pass/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
41
|
+
| `cline-pass/cline-pass/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
42
|
+
| `cline-pass/cline-pass/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
43
|
+
| `cline-pass/cline-pass/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
44
|
+
| `cline-pass/cline-pass/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
45
|
+
| `cline-pass/cline-pass/mimo-v2.5-pro` | 1.0M | | | | | | $2 | $3 |
|
|
46
|
+
| `cline-pass/cline-pass/minimax-m3` | 512K | | | | | | $0.30 | $1 |
|
|
47
|
+
| `cline-pass/cline-pass/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
48
|
+
| `cline-pass/cline-pass/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
49
|
+
|
|
50
|
+
## Advanced configuration
|
|
51
|
+
|
|
52
|
+
### Custom headers
|
|
53
|
+
|
|
54
|
+
```typescript
|
|
55
|
+
const agent = new Agent({
|
|
56
|
+
id: "custom-agent",
|
|
57
|
+
name: "custom-agent",
|
|
58
|
+
model: {
|
|
59
|
+
url: "https://api.cline.bot/api/v1",
|
|
60
|
+
id: "cline-pass/cline-pass/deepseek-v4-flash",
|
|
61
|
+
apiKey: process.env.CLINE_API_KEY,
|
|
62
|
+
headers: {
|
|
63
|
+
"X-Custom-Header": "value"
|
|
64
|
+
}
|
|
65
|
+
}
|
|
66
|
+
});
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
### Dynamic model selection
|
|
70
|
+
|
|
71
|
+
```typescript
|
|
72
|
+
const agent = new Agent({
|
|
73
|
+
id: "dynamic-agent",
|
|
74
|
+
name: "Dynamic Agent",
|
|
75
|
+
model: ({ requestContext }) => {
|
|
76
|
+
const useAdvanced = requestContext.task === "complex";
|
|
77
|
+
return useAdvanced
|
|
78
|
+
? "cline-pass/cline-pass/qwen3.7-plus"
|
|
79
|
+
: "cline-pass/cline-pass/deepseek-v4-flash";
|
|
80
|
+
}
|
|
81
|
+
});
|
|
82
|
+
```
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Cortecs
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 57 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Cortecs documentation](https://cortecs.ai).
|
|
8
8
|
|
|
@@ -65,6 +65,7 @@ for await (const chunk of stream) {
|
|
|
65
65
|
| `cortecs/gpt-5.4` | 1.1M | | | | | | $3 | $16 |
|
|
66
66
|
| `cortecs/gpt-oss-120b` | 128K | | | | | | — | — |
|
|
67
67
|
| `cortecs/hermes-4-70b` | 128K | | | | | | $0.12 | $0.36 |
|
|
68
|
+
| `cortecs/hy3` | 262K | | | | | | $0.41 | $1 |
|
|
68
69
|
| `cortecs/intellect-3` | 128K | | | | | | $0.22 | $1 |
|
|
69
70
|
| `cortecs/kimi-k2-instruct` | 131K | | | | | | $0.55 | $3 |
|
|
70
71
|
| `cortecs/kimi-k2-thinking` | 262K | | | | | | $0.66 | $3 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# CrossModel
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 44 CrossModel models through Mastra's model router. Authentication is handled automatically using the `CROSSMODEL_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [CrossModel documentation](https://www.crossmodel.ai/docs).
|
|
8
8
|
|
|
@@ -55,6 +55,7 @@ for await (const chunk of stream) {
|
|
|
55
55
|
| `crossmodel/moonshot/kimi-k2.5` | 262K | | | | | | $0.62 | $3 |
|
|
56
56
|
| `crossmodel/moonshot/kimi-k2.6` | 262K | | | | | | $1 | $4 |
|
|
57
57
|
| `crossmodel/moonshot/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
|
|
58
|
+
| `crossmodel/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
58
59
|
| `crossmodel/openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
59
60
|
| `crossmodel/openai/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
|
|
60
61
|
| `crossmodel/openai/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Deep Infra
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 37 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
|
|
8
8
|
|
|
@@ -17,7 +17,7 @@ const agent = new Agent({
|
|
|
17
17
|
id: "my-agent",
|
|
18
18
|
name: "My Agent",
|
|
19
19
|
instructions: "You are a helpful assistant",
|
|
20
|
-
model: "deepinfra/MiniMaxAI/MiniMax-M2.
|
|
20
|
+
model: "deepinfra/MiniMaxAI/MiniMax-M2.7"
|
|
21
21
|
});
|
|
22
22
|
|
|
23
23
|
// Generate a response
|
|
@@ -43,15 +43,12 @@ for await (const chunk of stream) {
|
|
|
43
43
|
| `deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo` | 131K | | | | | | $0.10 | $0.32 |
|
|
44
44
|
| `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M | | | | | | $0.20 | $0.80 |
|
|
45
45
|
| `deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct` | 328K | | | | | | $0.10 | $0.30 |
|
|
46
|
-
| `deepinfra/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.15 | $1 |
|
|
47
46
|
| `deepinfra/MiniMaxAI/MiniMax-M2.7` | 197K | | | | | | $0.25 | $1 |
|
|
48
47
|
| `deepinfra/MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.30 | $1 |
|
|
49
48
|
| `deepinfra/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.45 | $2 |
|
|
50
49
|
| `deepinfra/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.75 | $4 |
|
|
51
50
|
| `deepinfra/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.74 | $4 |
|
|
52
|
-
| `deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5` | 131K | | | | | | $0.40 | $0.40 |
|
|
53
51
|
| `deepinfra/nvidia/Nemotron-3-Nano-30B-A3B` | 262K | | | | | | $0.05 | $0.20 |
|
|
54
|
-
| `deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning` | 262K | | | | | | $0.20 | $0.80 |
|
|
55
52
|
| `deepinfra/openai/gpt-oss-120b` | 131K | | | | | | $0.04 | $0.17 |
|
|
56
53
|
| `deepinfra/openai/gpt-oss-20b` | 131K | | | | | | $0.03 | $0.14 |
|
|
57
54
|
| `deepinfra/Qwen/Qwen3-32B` | 41K | | | | | | $0.08 | $0.28 |
|
|
@@ -84,7 +81,7 @@ const agent = new Agent({
|
|
|
84
81
|
id: "custom-agent",
|
|
85
82
|
name: "custom-agent",
|
|
86
83
|
model: {
|
|
87
|
-
id: "deepinfra/MiniMaxAI/MiniMax-M2.
|
|
84
|
+
id: "deepinfra/MiniMaxAI/MiniMax-M2.7",
|
|
88
85
|
apiKey: process.env.DEEPINFRA_API_KEY,
|
|
89
86
|
headers: {
|
|
90
87
|
"X-Custom-Header": "value"
|
|
@@ -103,7 +100,7 @@ const agent = new Agent({
|
|
|
103
100
|
const useAdvanced = requestContext.task === "complex";
|
|
104
101
|
return useAdvanced
|
|
105
102
|
? "deepinfra/zai-org/GLM-5.2"
|
|
106
|
-
: "deepinfra/MiniMaxAI/MiniMax-M2.
|
|
103
|
+
: "deepinfra/MiniMaxAI/MiniMax-M2.7";
|
|
107
104
|
}
|
|
108
105
|
});
|
|
109
106
|
```
|
|
@@ -91,4 +91,6 @@ const response = await agent.generate("Hello!", {
|
|
|
91
91
|
|
|
92
92
|
**thinking** (`{ type?: "adaptive" | "enabled" | "disabled" | undefined; } | undefined`)
|
|
93
93
|
|
|
94
|
-
**reasoningEffort** (`"low" | "medium" | "high" | "xhigh" | "max" | undefined`)
|
|
94
|
+
**reasoningEffort** (`"low" | "medium" | "high" | "xhigh" | "max" | undefined`)
|
|
95
|
+
|
|
96
|
+
**strictJsonSchema** (`boolean | undefined`)
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# EmpirioLabs AI
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 37 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
|
|
8
8
|
|
|
@@ -47,6 +47,7 @@ for await (const chunk of stream) {
|
|
|
47
47
|
| `empiriolabs/kimi-k2-6` | 256K | | | | | | $0.89 | $4 |
|
|
48
48
|
| `empiriolabs/kimi-k2-7-code` | 256K | | | | | | $0.95 | $4 |
|
|
49
49
|
| `empiriolabs/kimi-k2-7-code-highspeed` | 256K | | | | | | $2 | $8 |
|
|
50
|
+
| `empiriolabs/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
50
51
|
| `empiriolabs/mimo-v2-5` | 1.0M | | | | | | $0.70 | $1 |
|
|
51
52
|
| `empiriolabs/mimo-v2-5-pro` | 1.0M | | | | | | $2 | $4 |
|
|
52
53
|
| `empiriolabs/minimax-m2-7` | 200K | | | | | | $0.15 | $0.60 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Google
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 21 Google models through Mastra's model router. Authentication is handled automatically using one of the following environment variables: `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
|
|
8
8
|
|
|
@@ -48,6 +48,8 @@ for await (const chunk of stream) {
|
|
|
48
48
|
| `google/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
49
49
|
| `google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
|
|
50
50
|
| `google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
|
|
51
|
+
| `google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
52
|
+
| `google/gemini-3.6-flash` | 1.0M | | | | | | $2 | $8 |
|
|
51
53
|
| `google/gemini-embedding-001` | 2K | | | | | | $0.15 | — |
|
|
52
54
|
| `google/gemini-flash-latest` | 1.0M | | | | | | $2 | $9 |
|
|
53
55
|
| `google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.25 | $2 |
|
|
@@ -122,7 +124,7 @@ const response = await agent.generate("Hello!", {
|
|
|
122
124
|
|
|
123
125
|
**mediaResolution** (`"MEDIA_RESOLUTION_UNSPECIFIED" | "MEDIA_RESOLUTION_LOW" | "MEDIA_RESOLUTION_MEDIUM" | "MEDIA_RESOLUTION_HIGH" | undefined`)
|
|
124
126
|
|
|
125
|
-
**imageConfig** (`{ aspectRatio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | "1:8" | "8:1" | "1:4" | "4:1" | undefined; imageSize?: "1K" | "2K" | "4K" | "512" | undefined;
|
|
127
|
+
**imageConfig** (`{ aspectRatio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | "1:8" | "8:1" | "1:4" | "4:1" | undefined; imageSize?: "1K" | "2K" | "4K" | "512" | undefined; personGeneration?: "PERSON_GENERATION_UNSPECIFIED" | ... 3 more ... | undefined; prominentPeople?: "PROMINENT_PEOPLE_UNSPEC...`)
|
|
126
128
|
|
|
127
129
|
**retrievalConfig** (`{ latLng?: { latitude: number; longitude: number; } | undefined; } | undefined`)
|
|
128
130
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Hugging Face
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 52 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Hugging Face documentation](https://huggingface.co).
|
|
8
8
|
|
|
@@ -77,6 +77,7 @@ for await (const chunk of stream) {
|
|
|
77
77
|
| `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
78
78
|
| `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
79
79
|
| `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
80
|
+
| `huggingface/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.40 | $2 |
|
|
80
81
|
| `huggingface/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
81
82
|
| `huggingface/zai-org/GLM-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
82
83
|
| `huggingface/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.13 | $0.85 |
|
|
@@ -37,11 +37,11 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
38
38
|
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
39
39
|
| `inferx/google/gemma-4-31b-it-fp8` | 262K | | | | | | — | — |
|
|
40
|
-
| `inferx/qwen/qwen3-coder-next-fp8` | 256K | | | | | | — | — |
|
|
41
|
-
| `inferx/qwen/qwen3-coder-next-fp8-1m` | 1.0M | | | | | | — | — |
|
|
42
40
|
| `inferx/qwen/qwen3.5-122b-a10b-nvfp4` | 256K | | | | | | — | — |
|
|
43
41
|
| `inferx/qwen/qwen3.6-27b-fp8` | 262K | | | | | | — | — |
|
|
44
42
|
| `inferx/qwen/qwen3.6-35b-a3b-fp8` | 262K | | | | | | — | — |
|
|
43
|
+
| `inferx/qwen3-coder-next-fp8` | 256K | | | | | | — | — |
|
|
44
|
+
| `inferx/qwen3-coder-next-fp8-1m` | 1.0M | | | | | | — | — |
|
|
45
45
|
|
|
46
46
|
## Advanced configuration
|
|
47
47
|
|
|
@@ -71,7 +71,7 @@ const agent = new Agent({
|
|
|
71
71
|
model: ({ requestContext }) => {
|
|
72
72
|
const useAdvanced = requestContext.task === "complex";
|
|
73
73
|
return useAdvanced
|
|
74
|
-
? "inferx/
|
|
74
|
+
? "inferx/qwen3-coder-next-fp8-1m"
|
|
75
75
|
: "inferx/google/gemma-4-31b-it-fp8";
|
|
76
76
|
}
|
|
77
77
|
});
|