@mastra/mcp-docs-server 1.2.22-alpha.1 → 1.2.23-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/integrations/sandboxes/e2b.md +95 -2
- package/.docs/models/environment-variables.md +3 -0
- package/.docs/models/gateways/netlify.md +4 -1
- package/.docs/models/gateways/vercel.md +3 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/alibaba-cn.md +2 -1
- package/.docs/models/providers/alibaba.md +2 -1
- package/.docs/models/providers/amd.md +6 -5
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/cloudflare-workers-ai.md +2 -1
- package/.docs/models/providers/cortecs.md +3 -1
- package/.docs/models/providers/crof.md +25 -24
- package/.docs/models/providers/deepinfra.md +2 -1
- package/.docs/models/providers/digitalocean.md +10 -10
- package/.docs/models/providers/edenai.md +3 -2
- package/.docs/models/providers/hyper.md +3 -3
- package/.docs/models/providers/inceptron.md +2 -2
- package/.docs/models/providers/kilo.md +8 -8
- package/.docs/models/providers/llmgateway-providers.md +8 -5
- package/.docs/models/providers/llmgateway.md +6 -4
- package/.docs/models/providers/nano-gpt.md +32 -17
- package/.docs/models/providers/opencode-go.md +2 -1
- package/.docs/models/providers/opencode.md +2 -1
- package/.docs/models/providers/openreason.md +77 -0
- package/.docs/models/providers/regolo-ai.md +2 -2
- package/.docs/models/providers/tencent-token-plan.md +6 -5
- package/.docs/models/providers/tencent-tokenhub.md +3 -2
- package/.docs/models/providers/vancine.md +82 -0
- package/.docs/models/providers/volcengine-coding-plan.md +82 -0
- package/.docs/models/providers.md +3 -0
- package/.docs/reference/workspace/platform-sandbox.md +86 -3
- package/CHANGELOG.md +14 -0
- package/dist/logger.d.ts.map +1 -1
- package/dist/tools/course.d.ts.map +1 -1
- package/dist/tools/docs.d.ts.map +1 -1
- package/dist/tools/embedded-docs.d.ts.map +1 -1
- package/dist/tools/migration.d.ts.map +1 -1
- package/package.json +7 -7
|
@@ -64,7 +64,7 @@ const agent = new Agent({
|
|
|
64
64
|
|
|
65
65
|
**lifecycle** (`SandboxLifecycle`): Controls what happens when the sandbox timeout is reached. Defaults to pausing the sandbox so the next start resumes it. Pass { onTimeout: 'kill' } to destroy idle sandboxes instead, which suits stateless workspaces whose data is persisted outside the sandbox. An explicit stop() always pauses, regardless of this setting. (Default: `{ onTimeout: 'pause' }`)
|
|
66
66
|
|
|
67
|
-
**template** (`string | TemplateBuilder | function`): Sandbox template specification. Can be a template ID string, a TemplateBuilder,
|
|
67
|
+
**template** (`string | TemplateBuilder | function | NamedTemplateSpec`): Sandbox template specification. Can be a template ID string, a TemplateBuilder, a function that customizes the default template, or a named spec such as the one returned by createRepoTemplate.
|
|
68
68
|
|
|
69
69
|
**env** (`Record<string, string>`): Environment variables to set in the sandbox
|
|
70
70
|
|
|
@@ -177,7 +177,9 @@ The E2B sandbox automatically installs the required FUSE tools when mounting is
|
|
|
177
177
|
|
|
178
178
|
## Custom templates
|
|
179
179
|
|
|
180
|
-
By default, when no template is specified, E2BSandbox automatically builds a template with `s3fs` installed for S3 mounting support. This template is cached and reused across sandbox instances.
|
|
180
|
+
By default, when no template is specified, E2BSandbox automatically builds a template with `s3fs` installed for S3 mounting support, a current Node.js LTS installed over the base image's older runtime, and corepack enabled so `pnpm` and `yarn` resolve to whatever a repository's `packageManager` field pins. This template is cached and reused across sandbox instances.
|
|
181
|
+
|
|
182
|
+
The Node.js version is pinned exactly and is part of the template's identity. Pass `nodeVersion` to `createDefaultMountableTemplate()` to select a different release; changing it builds a new template.
|
|
181
183
|
|
|
182
184
|
For GCS mounting, `gcsfuse` is automatically installed at mount time if not already present. For additional tools or faster cold starts, use custom templates.
|
|
183
185
|
|
|
@@ -255,6 +257,97 @@ const workspace = new Workspace({
|
|
|
255
257
|
|
|
256
258
|
This is optional: `gcsfuse` is installed automatically at mount time if not present.
|
|
257
259
|
|
|
260
|
+
### Repository templates
|
|
261
|
+
|
|
262
|
+
`createRepoTemplate` produces a template spec that clones a repository and runs its setup command at build time, so sandboxes start with a warm checkout and installed dependencies instead of paying for a cold clone on every session:
|
|
263
|
+
|
|
264
|
+
```typescript
|
|
265
|
+
import { E2BSandbox, createRepoTemplate } from '@mastra/e2b'
|
|
266
|
+
|
|
267
|
+
const sandbox = new E2BSandbox({
|
|
268
|
+
id: sessionId,
|
|
269
|
+
template: createRepoTemplate({
|
|
270
|
+
getRepositoryAccess: async () => ({
|
|
271
|
+
cloneUrl: 'https://github.com/octocat/hello-world.git',
|
|
272
|
+
}),
|
|
273
|
+
setupCommand: 'pnpm install',
|
|
274
|
+
}),
|
|
275
|
+
})
|
|
276
|
+
```
|
|
277
|
+
|
|
278
|
+
`getRepositoryAccess` supplies the clone URL and, for private repositories, a credential. It's the only source of the clone URL, so what gets cloned and what the template is identified by can't drift apart. When it's `undefined`, `createRepoTemplate` returns `undefined` — which is how a session with no repository asks for the provider's default template without a conditional at the call site.
|
|
279
|
+
|
|
280
|
+
There is exactly one template per repository and setup command: the template name carries the repo slug plus a short hash of the inputs, and the commit sha rides as a tag on that name (`mastra-repo-<owner>-<repo>-<hash>:sha-<sha>`). The spec pins itself to the repository's current default-branch head at resolution time: right before the template lookup it runs `git ls-remote` (no clone, \~100ms) and keys the tag on that sha. When the default branch moves, the next new sandbox rebuilds the same template in place under a new tag, and old sha tags remain as prunable build history instead of piling up as stale templates. If the head can't be resolved, the ref degrades to the stable `current` tag and the build clones whatever the default branch is at build time.
|
|
281
|
+
|
|
282
|
+
Resolution is lazy and only ever blocks on a template's very first build. Every successful build also moves a stable `current` tag, so when the head moves, the next sandbox boots immediately from the previous build while the fresh sha ref builds in the background on E2B's side (its runtime setup `git fetch` fast-forwards the slightly stale checkout — freshness never depends on the template). A changed setup command hashes to a new template name.
|
|
283
|
+
|
|
284
|
+
Templates build at E2B's default machine size (2 vCPU, 1024 MB) unless the spec asks for more. Pass `cpuCount` and `memoryMB` to size the machine the template's sandboxes run on:
|
|
285
|
+
|
|
286
|
+
```typescript
|
|
287
|
+
const sandbox = new E2BSandbox({
|
|
288
|
+
id: sessionId,
|
|
289
|
+
template: createRepoTemplate({
|
|
290
|
+
getRepositoryAccess: async () => ({
|
|
291
|
+
cloneUrl: 'https://github.com/octocat/hello-world.git',
|
|
292
|
+
}),
|
|
293
|
+
setupCommand: 'pnpm install',
|
|
294
|
+
cpuCount: 4,
|
|
295
|
+
memoryMB: 2048,
|
|
296
|
+
}),
|
|
297
|
+
})
|
|
298
|
+
```
|
|
299
|
+
|
|
300
|
+
Resources are part of the template's identity: they hash into the template name alongside the repository and setup command, so resizing builds a new template instead of silently reusing one built at the old size. When a repo template's build fails and the sandbox falls back to the default mountable template, the fallback builds at the requested size too, so setup never lands in a smaller machine than it asked for. Account tier limits apply to the values E2B accepts.
|
|
301
|
+
|
|
302
|
+
To warm templates proactively instead of waiting for the first session after a merge, call `refreshRepoTemplate` with the same options from a scheduled job or a merge-to-main event handler. It performs the same resolution as sandbox start — resolves the current head, reuses the build when it already exists, and otherwise builds it (moving `current`) — and reports `{ ref, action, sha }`:
|
|
303
|
+
|
|
304
|
+
```typescript
|
|
305
|
+
import { refreshRepoTemplate } from '@mastra/e2b'
|
|
306
|
+
|
|
307
|
+
const result = await refreshRepoTemplate({
|
|
308
|
+
getRepositoryAccess: async () => ({
|
|
309
|
+
cloneUrl: 'https://github.com/octocat/hello-world.git',
|
|
310
|
+
}),
|
|
311
|
+
setupCommand: 'pnpm install',
|
|
312
|
+
})
|
|
313
|
+
// { ref: 'mastra-repo-octocat-hello-world-…:sha-…', action: 'built' | 'reused', sha: '…' }
|
|
314
|
+
```
|
|
315
|
+
|
|
316
|
+
The template layers on top of the default mountable base (E2B's `base` image, so git and common tooling are present, plus `s3fs`/FUSE for mount support). The clone lands in the build user's home directory at `$HOME/<repo>`, derived from the clone URL. Build steps and runtime commands both run as the sandbox's non-root `user` in its home, so no directory prep is needed, runtime file ownership stays correct, and a runtime `$HOME` probe finds the checkout exactly where the template left it.
|
|
317
|
+
|
|
318
|
+
Failure handling is designed so a broken template never wedges a session:
|
|
319
|
+
|
|
320
|
+
- A failed build falls back to the default mountable template; the session's runtime cold clone into `$HOME` keeps working.
|
|
321
|
+
- E2B keeps a failed build's ref visible to `Template.exists`, so a broken ref could otherwise be reused forever. When creating a sandbox from a named ref fails, the cached resolution is dropped and creation retries down the fallback ladder.
|
|
322
|
+
|
|
323
|
+
Private repositories build warm templates when `getRepositoryAccess` returns an `authorization` alongside the clone URL — a fresh, short-lived credential (such as a GitHub App installation token) minted per template resolution. The credential authenticates the head lookup and the build's clone through an in-shell `http.extraheader` — it enters the template definition's environment (visible to build steps but not persisted into runtime sandbox environments) and never touches the image filesystem, so no captured layer can contain it. It's set as `GH_TOKEN`, the same variable a session installs before running setup, so a command that shells out to `gh` or authenticated https behaves the same in the build as it does in a session.
|
|
324
|
+
|
|
325
|
+
Only pass short-lived credentials — the value stays in the template definition until the next rebuild, so its expiry is what bounds the exposure. Note that the cloned repository contents become part of a team-visible template image. When the access call returns no credential the clone is tokenless: public repositories build fine, and a private repository's build degrades to the fallback, where the session's own runtime setup (with runtime-injected auth) does the clone.
|
|
326
|
+
|
|
327
|
+
Setup commands that need their own credentials — a registry token, a private index URL — take them through `buildEnv`, which accepts a record or an async resolver. Those values are part of the template's identity, so changing one produces a new template.
|
|
328
|
+
|
|
329
|
+
`repoTemplateRef` computes the tagged ref for a spec without building anything — useful for pruning old sha tags with the E2B CLI.
|
|
330
|
+
|
|
331
|
+
### Per-session sandboxes
|
|
332
|
+
|
|
333
|
+
Hosts that construct one sandbox per session, such as Mastra Factory's `sandbox` config, combine the pieces above in a small callback: sandbox identity is the session id (id-keyed getOrCreate — the sandbox pauses on E2B's idle timeout and resumes by id), and the repo template comes from `createRepoTemplate`. The host's session context carries everything the template needs, so it can be passed straight through:
|
|
334
|
+
|
|
335
|
+
```typescript
|
|
336
|
+
import { MastraFactory } from '@mastra/factory'
|
|
337
|
+
import { E2BSandbox, createRepoTemplate } from '@mastra/e2b'
|
|
338
|
+
|
|
339
|
+
new MastraFactory({
|
|
340
|
+
sandbox: ctx =>
|
|
341
|
+
new E2BSandbox({
|
|
342
|
+
id: ctx.sessionId,
|
|
343
|
+
// Undefined for a session with no repository.
|
|
344
|
+
template: createRepoTemplate(ctx),
|
|
345
|
+
}),
|
|
346
|
+
})
|
|
347
|
+
```
|
|
348
|
+
|
|
349
|
+
Factory attaches its own session setup to the sandbox it gets back, so the callback doesn't wire up a start hook.
|
|
350
|
+
|
|
258
351
|
## Using with Code Mode
|
|
259
352
|
|
|
260
353
|
[Code Mode](https://mastra.ai/docs/agents/code-mode) lets an agent write a single TypeScript program that orchestrates its tools. Because E2B runs that program in a remote micro-VM, it needs a transport that writes the program into the sandbox filesystem rather than the host. `@mastra/e2b` provides `E2BCodeModeTransport` for this. Pass it as the second argument to `createCodeMode`:
|
|
@@ -127,6 +127,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
127
127
|
| [OpenAI](https://mastra.ai/models/providers/openai) | `openai/*` | `OPENAI_API_KEY` |
|
|
128
128
|
| [OpenCode Go](https://mastra.ai/models/providers/opencode-go) | `opencode-go/*` | `OPENCODE_API_KEY` |
|
|
129
129
|
| [OpenCode Zen](https://mastra.ai/models/providers/opencode) | `opencode/*` | `OPENCODE_API_KEY` |
|
|
130
|
+
| [OpenReason](https://mastra.ai/models/providers/openreason) | `openreason/*` | `OPENREASON_API_KEY` |
|
|
130
131
|
| [Opper](https://mastra.ai/models/providers/opper) | `opper/*` | `OPPER_API_KEY` |
|
|
131
132
|
| [OrcaRouter](https://mastra.ai/models/providers/orcarouter) | `orcarouter/*` | `ORCAROUTER_API_KEY` |
|
|
132
133
|
| [OVHcloud AI Endpoints](https://mastra.ai/models/providers/ovhcloud) | `ovhcloud/*` | `OVHCLOUD_API_KEY` |
|
|
@@ -174,8 +175,10 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
174
175
|
| [Umans AI Coding Plan](https://mastra.ai/models/providers/umans-ai-coding-plan) | `umans-ai-coding-plan/*` | `UMANS_AI_CODING_PLAN_API_KEY` |
|
|
175
176
|
| [UnoRouter](https://mastra.ai/models/providers/unorouter) | `unorouter/*` | `UNOROUTER_API_KEY` |
|
|
176
177
|
| [Upstage](https://mastra.ai/models/providers/upstage) | `upstage/*` | `UPSTAGE_API_KEY` |
|
|
178
|
+
| [Vancine](https://mastra.ai/models/providers/vancine) | `vancine/*` | `VANCINE_API_KEY` |
|
|
177
179
|
| [Vivgrid](https://mastra.ai/models/providers/vivgrid) | `vivgrid/*` | `VIVGRID_API_KEY` |
|
|
178
180
|
| [Volcengine Ark](https://mastra.ai/models/providers/volcengine) | `volcengine/*` | `ARK_API_KEY` |
|
|
181
|
+
| [Volcengine Ark Coding Plan](https://mastra.ai/models/providers/volcengine-coding-plan) | `volcengine-coding-plan/*` | `ARK_CODING_PLAN_API_KEY` |
|
|
179
182
|
| [Vultr](https://mastra.ai/models/providers/vultr) | `vultr/*` | `VULTR_API_KEY` |
|
|
180
183
|
| [Wafer](https://mastra.ai/models/providers/wafer.ai) | `wafer.ai/*` | `WAFER_API_KEY` |
|
|
181
184
|
| [Weights & Biases](https://mastra.ai/models/providers/wandb) | `wandb/*` | `WANDB_API_KEY` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Netlify
|
|
6
6
|
|
|
7
|
-
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access
|
|
7
|
+
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 241 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
|
|
10
10
|
|
|
@@ -109,6 +109,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
109
109
|
| `openrouter/~deepseek/deepseek-v4-flash-latest` |
|
|
110
110
|
| `openrouter/~moonshotai/kimi-latest` |
|
|
111
111
|
| `openrouter/~x-ai/grok-latest` |
|
|
112
|
+
| `openrouter/~z-ai/glm-latest` |
|
|
112
113
|
| `openrouter/allenai/olmo-3-32b-think` |
|
|
113
114
|
| `openrouter/anthracite-org/magnum-v4-72b` |
|
|
114
115
|
| `openrouter/arcee-ai/trinity-large-thinking` |
|
|
@@ -180,6 +181,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
180
181
|
| `openrouter/mistralai/mistral-small-2603` |
|
|
181
182
|
| `openrouter/mistralai/mistral-small-3.2-24b-instruct` |
|
|
182
183
|
| `openrouter/mistralai/mixtral-8x22b-instruct` |
|
|
184
|
+
| `openrouter/mistralai/voxtral-small-24b-2507` |
|
|
183
185
|
| `openrouter/moonshotai/kimi-k2` |
|
|
184
186
|
| `openrouter/moonshotai/kimi-k2-0905` |
|
|
185
187
|
| `openrouter/moonshotai/kimi-k2-thinking` |
|
|
@@ -276,4 +278,5 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
276
278
|
| `openrouter/z-ai/glm-5.1` |
|
|
277
279
|
| `openrouter/z-ai/glm-5.2` |
|
|
278
280
|
| `openrouter/z-ai/glm-5.2:free` |
|
|
281
|
+
| `openrouter/z-ai/glm-5.3` |
|
|
279
282
|
| `openrouter/z-ai/glm-5.3-flash` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Vercel
|
|
6
6
|
|
|
7
|
-
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 360 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
|
|
10
10
|
|
|
@@ -79,6 +79,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
79
79
|
| `alibaba/wan-v2.7-r2v` |
|
|
80
80
|
| `alibaba/wan-v2.7-t2v` |
|
|
81
81
|
| `alibaba/wan-v3.0-video` |
|
|
82
|
+
| `alibaba/wan-v3.0-video-prime` |
|
|
82
83
|
| `amazon/nova-2-lite` |
|
|
83
84
|
| `amazon/nova-lite` |
|
|
84
85
|
| `amazon/nova-micro` |
|
|
@@ -365,6 +366,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
365
366
|
| `tencent/hy-mt2-plus` |
|
|
366
367
|
| `tencent/hy-mt2-pro` |
|
|
367
368
|
| `tencent/hy3` |
|
|
369
|
+
| `tencent/hy4-preview` |
|
|
368
370
|
| `thinkingmachines/inkling` |
|
|
369
371
|
| `thinkingmachines/inkling-small` |
|
|
370
372
|
| `voyage/rerank-2.5` |
|
package/.docs/models/index.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Model Providers
|
|
6
6
|
|
|
7
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
7
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7047 models from 194 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Alibaba (China)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 87 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Alibaba (China) documentation](https://www.alibabacloud.com/help/en/model-studio/models).
|
|
10
10
|
|
|
@@ -116,6 +116,7 @@ for await (const chunk of stream) {
|
|
|
116
116
|
| `alibaba-cn/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.12 |
|
|
117
117
|
| `alibaba-cn/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
118
118
|
| `alibaba-cn/qwen3.7-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
119
|
+
| `alibaba-cn/qwen3.8-flash` | 1.0M | | | | | | $0.12 | $0.40 |
|
|
119
120
|
| `alibaba-cn/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
|
|
120
121
|
| `alibaba-cn/qwq-32b` | 131K | | | | | | $0.29 | $0.86 |
|
|
121
122
|
| `alibaba-cn/qwq-plus` | 131K | | | | | | $0.23 | $0.57 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Alibaba
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 55 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Alibaba documentation](https://www.alibabacloud.com/help/en/model-studio/models).
|
|
10
10
|
|
|
@@ -90,6 +90,7 @@ for await (const chunk of stream) {
|
|
|
90
90
|
| `alibaba/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
91
91
|
| `alibaba/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
92
92
|
| `alibaba/qwen3.7-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
93
|
+
| `alibaba/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
93
94
|
| `alibaba/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
94
95
|
| `alibaba/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
95
96
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# AMD
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 2 AMD models through Mastra's model router. Authentication is handled automatically using the `AMD_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [AMD documentation](https://developer.amd.com.cn/radeon/tokenfactory).
|
|
10
10
|
|
|
@@ -36,9 +36,10 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `amd/DeepSeek-V4-Flash`
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `amd/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
42
|
+
| `amd/Qwen3.8-Flash-Next` | 262K | | | | | | $0.15 | $0.47 |
|
|
42
43
|
|
|
43
44
|
## Advanced configuration
|
|
44
45
|
|
|
@@ -68,7 +69,7 @@ const agent = new Agent({
|
|
|
68
69
|
model: ({ requestContext }) => {
|
|
69
70
|
const useAdvanced = requestContext.task === "complex";
|
|
70
71
|
return useAdvanced
|
|
71
|
-
? "amd/
|
|
72
|
+
? "amd/Qwen3.8-Flash-Next"
|
|
72
73
|
: "amd/DeepSeek-V4-Flash";
|
|
73
74
|
}
|
|
74
75
|
});
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Baseten
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 21 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Baseten documentation](https://docs.baseten.co).
|
|
10
10
|
|
|
@@ -55,6 +55,7 @@ for await (const chunk of stream) {
|
|
|
55
55
|
| `baseten/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
56
56
|
| `baseten/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
57
57
|
| `baseten/zai-org/GLM-5.2-Fast` | 1.0M | | | | | | $2 | $7 |
|
|
58
|
+
| `baseten/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
58
59
|
| `baseten/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
59
60
|
|
|
60
61
|
## Advanced configuration
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Cloudflare Workers AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 27 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.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
|
|
10
10
|
|
|
@@ -64,6 +64,7 @@ for await (const chunk of stream) {
|
|
|
64
64
|
| `cloudflare-workers-ai/@cf/qwen/qwq-32b` | 24K | | | | | | $0.66 | $1 |
|
|
65
65
|
| `cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash` | 131K | | | | | | $0.06 | $0.40 |
|
|
66
66
|
| `cloudflare-workers-ai/@cf/zai-org/glm-5.2` | 262K | | | | | | $1 | $4 |
|
|
67
|
+
| `cloudflare-workers-ai/@cf/zai-org/glm-5.3` | 1.3M | | | | | | $1 | $4 |
|
|
67
68
|
| `cloudflare-workers-ai/@cf/zai-org/glm-5.3-flash` | 1.3M | | | | | | $0.15 | $0.50 |
|
|
68
69
|
|
|
69
70
|
## Advanced configuration
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Cortecs
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 110 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Cortecs documentation](https://cortecs.ai).
|
|
10
10
|
|
|
@@ -72,6 +72,7 @@ for await (const chunk of stream) {
|
|
|
72
72
|
| `cortecs/glm-5-turbo` | 203K | | | | | | $1 | $4 |
|
|
73
73
|
| `cortecs/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
74
74
|
| `cortecs/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
75
|
+
| `cortecs/glm-5.3-flash` | 1.0M | | | | | | $0.20 | $0.50 |
|
|
75
76
|
| `cortecs/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
|
|
76
77
|
| `cortecs/gpt-4.1` | 1.0M | | | | | | $2 | $9 |
|
|
77
78
|
| `cortecs/gpt-4.1-mini` | 1.0M | | | | | | $0.43 | $2 |
|
|
@@ -143,6 +144,7 @@ for await (const chunk of stream) {
|
|
|
143
144
|
| `cortecs/qwen3.6-35b-a3b` | 262K | | | | | | $0.17 | $0.56 |
|
|
144
145
|
| `cortecs/qwen3.8-2.4t-a95b` | 262K | | | | | | $3 | $6 |
|
|
145
146
|
| `cortecs/qwen3.8-27b` | 262K | | | | | | $0.33 | $2 |
|
|
147
|
+
| `cortecs/qwen3.8-flash-next` | 262K | | | | | | $0.20 | $0.50 |
|
|
146
148
|
| `cortecs/qwen3guard-gen-0.6b` | 32K | | | | | | — | — |
|
|
147
149
|
| `cortecs/qwen3guard-gen-8b` | 32K | | | | | | — | — |
|
|
148
150
|
| `cortecs/voxtral-small-2507` | 32K | | | | | | $0.11 | $0.33 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# CrofAI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 22 CrofAI models through Mastra's model router. Authentication is handled automatically using the `CROF_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [CrofAI documentation](https://crof.ai/docs).
|
|
10
10
|
|
|
@@ -36,29 +36,30 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `crof/deepseek-v3.2`
|
|
42
|
-
| `crof/deepseek-v4-flash`
|
|
43
|
-
| `crof/deepseek-v4-flash-0731`
|
|
44
|
-
| `crof/deepseek-v4-pro`
|
|
45
|
-
| `crof/deepseek-v4-pro-
|
|
46
|
-
| `crof/gemma-4-31b-it`
|
|
47
|
-
| `crof/glm-5.1`
|
|
48
|
-
| `crof/glm-5.2`
|
|
49
|
-
| `crof/
|
|
50
|
-
| `crof/greg-
|
|
51
|
-
| `crof/greg-2-
|
|
52
|
-
| `crof/greg-
|
|
53
|
-
| `crof/
|
|
54
|
-
| `crof/kimi-k2.
|
|
55
|
-
| `crof/kimi-
|
|
56
|
-
| `crof/kimi-k3
|
|
57
|
-
| `crof/
|
|
58
|
-
| `crof/
|
|
59
|
-
| `crof/qwen3.5-
|
|
60
|
-
| `crof/qwen3.
|
|
61
|
-
| `crof/qwen3.
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ----------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `crof/deepseek-v3.2` | 164K | | | | | | $0.18 | $0.35 |
|
|
42
|
+
| `crof/deepseek-v4-flash` | 1.0M | | | | | | $0.12 | $0.21 |
|
|
43
|
+
| `crof/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.08 | $0.10 |
|
|
44
|
+
| `crof/deepseek-v4-pro` | 1.0M | | | | | | $0.35 | $0.80 |
|
|
45
|
+
| `crof/deepseek-v4-pro-0813` | 1.0M | | | | | | $0.35 | $0.80 |
|
|
46
|
+
| `crof/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
|
|
47
|
+
| `crof/glm-5.1` | 203K | | | | | | $0.45 | $2 |
|
|
48
|
+
| `crof/glm-5.2` | 1.0M | | | | | | $0.30 | $1 |
|
|
49
|
+
| `crof/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.22 |
|
|
50
|
+
| `crof/greg-1-mini` | 229K | | | | | | $0.07 | $0.15 |
|
|
51
|
+
| `crof/greg-2-super` | 229K | | | | | | $2 | $5 |
|
|
52
|
+
| `crof/greg-2-ultra` | 229K | | | | | | $3 | $10 |
|
|
53
|
+
| `crof/greg-rp` | 229K | | | | | | $0.10 | $0.30 |
|
|
54
|
+
| `crof/kimi-k2.6` | 262K | | | | | | $0.50 | $2 |
|
|
55
|
+
| `crof/kimi-k2.7-code` | 262K | | | | | | $0.55 | $2 |
|
|
56
|
+
| `crof/kimi-k3` | 1.0M | | | | | | $2 | $8 |
|
|
57
|
+
| `crof/kimi-k3-eco` | 1.0M | | | | | | $1 | $4 |
|
|
58
|
+
| `crof/mimo-v2.5-pro` | 1.0M | | | | | | $0.40 | $0.80 |
|
|
59
|
+
| `crof/qwen3.5-397b-a17b` | 262K | | | | | | $0.35 | $2 |
|
|
60
|
+
| `crof/qwen3.5-9b` | 262K | | | | | | $0.04 | $0.15 |
|
|
61
|
+
| `crof/qwen3.6-27b` | 262K | | | | | | $0.20 | $2 |
|
|
62
|
+
| `crof/qwen3.8-27b` | 262K | | | | | | $0.20 | $2 |
|
|
62
63
|
|
|
63
64
|
## Advanced configuration
|
|
64
65
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Deep Infra
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 62 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
|
|
10
10
|
|
|
@@ -93,6 +93,7 @@ for await (const chunk of stream) {
|
|
|
93
93
|
| `deepinfra/zai-org/GLM-5` | 203K | | | | | | $0.60 | $2 |
|
|
94
94
|
| `deepinfra/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
95
95
|
| `deepinfra/zai-org/GLM-5.2` | 1.0M | | | | | | $0.75 | $2 |
|
|
96
|
+
| `deepinfra/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
96
97
|
| `deepinfra/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
97
98
|
|
|
98
99
|
## Advanced configuration
|
|
@@ -57,12 +57,12 @@ for await (const chunk of stream) {
|
|
|
57
57
|
| `digitalocean/arcee-trinity-large-thinking` | 128K | | | | | | $0.25 | $0.90 |
|
|
58
58
|
| `digitalocean/bge-m3` | 8K | | | | | | $0.02 | — |
|
|
59
59
|
| `digitalocean/bge-reranker-v2-m3` | 8K | | | | | | $0.01 | — |
|
|
60
|
-
| `digitalocean/deepseek-3.2` | 164K | | | | | | $0.
|
|
61
|
-
| `digitalocean/deepseek-4-flash` | 1.0M | | | | | | $0.
|
|
60
|
+
| `digitalocean/deepseek-3.2` | 164K | | | | | | $0.25 | $0.80 |
|
|
61
|
+
| `digitalocean/deepseek-4-flash` | 1.0M | | | | | | $0.07 | $0.17 |
|
|
62
62
|
| `digitalocean/deepseek-r1-distill-llama-70b` | 33K | | | | | | $0.99 | $0.99 |
|
|
63
63
|
| `digitalocean/deepseek-v3` | 164K | | | | | | — | — |
|
|
64
|
-
| `digitalocean/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
65
|
-
| `digitalocean/deepseek-v4-pro` | 1.0M | | | | | | $
|
|
64
|
+
| `digitalocean/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.08 | $0.25 |
|
|
65
|
+
| `digitalocean/deepseek-v4-pro` | 1.0M | | | | | | $0.87 | $2 |
|
|
66
66
|
| `digitalocean/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
67
67
|
| `digitalocean/e5-large-v2` | 512 | | | | | | $0.02 | — |
|
|
68
68
|
| `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | — | | | | | | — | — |
|
|
@@ -72,16 +72,16 @@ for await (const chunk of stream) {
|
|
|
72
72
|
| `digitalocean/gemma-4-31B-it` | 256K | | | | | | $0.18 | $0.50 |
|
|
73
73
|
| `digitalocean/glm-5` | 64K | | | | | | $1 | $3 |
|
|
74
74
|
| `digitalocean/glm-5.1` | 164K | | | | | | $1 | $4 |
|
|
75
|
-
| `digitalocean/glm-5.2` | 262K | | | | | | $
|
|
75
|
+
| `digitalocean/glm-5.2` | 262K | | | | | | $0.70 | $2 |
|
|
76
76
|
| `digitalocean/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
77
77
|
| `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
|
|
78
78
|
| `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
|
|
79
79
|
| `digitalocean/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
80
|
-
| `digitalocean/kimi-k3` | 1.0M | | | | | | $3 | $
|
|
81
|
-
| `digitalocean/llama-4-maverick` | 128K | | | | | | $0.
|
|
80
|
+
| `digitalocean/kimi-k3` | 1.0M | | | | | | $3 | $14 |
|
|
81
|
+
| `digitalocean/llama-4-maverick` | 128K | | | | | | $0.20 | $0.70 |
|
|
82
82
|
| `digitalocean/llama3-8b-instruct` | 131K | | | | | | $0.20 | $0.20 |
|
|
83
83
|
| `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
|
|
84
|
-
| `digitalocean/mimo-v2.5-pro` | 262K | | | | | | $0.
|
|
84
|
+
| `digitalocean/mimo-v2.5-pro` | 262K | | | | | | $0.40 | $2 |
|
|
85
85
|
| `digitalocean/minimax-m2.5` | 66K | | | | | | $0.30 | $1 |
|
|
86
86
|
| `digitalocean/ministral-3-8b-instruct-2512` | 262K | | | | | | — | — |
|
|
87
87
|
| `digitalocean/mistral-3-14B` | 262K | | | | | | $0.20 | $0.20 |
|
|
@@ -108,12 +108,12 @@ for await (const chunk of stream) {
|
|
|
108
108
|
| `digitalocean/openai-gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
|
|
109
109
|
| `digitalocean/openai-gpt-5.5` | 1.0M | | | | | | $5 | $30 |
|
|
110
110
|
| `digitalocean/openai-gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
111
|
-
| `digitalocean/openai-gpt-5.6-sol` | 1.1M | | | | | | $
|
|
111
|
+
| `digitalocean/openai-gpt-5.6-sol` | 1.1M | | | | | | $4 | $20 |
|
|
112
112
|
| `digitalocean/openai-gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
113
113
|
| `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
|
|
114
114
|
| `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
|
|
115
115
|
| `digitalocean/openai-gpt-image-2` | — | | | | | | $8 | $30 |
|
|
116
|
-
| `digitalocean/openai-gpt-oss-120b` | 128K | | | | | | $0.
|
|
116
|
+
| `digitalocean/openai-gpt-oss-120b` | 128K | | | | | | $0.06 | $0.39 |
|
|
117
117
|
| `digitalocean/openai-gpt-oss-20b` | 128K | | | | | | $0.05 | $0.45 |
|
|
118
118
|
| `digitalocean/openai-o1` | 200K | | | | | | $15 | $60 |
|
|
119
119
|
| `digitalocean/openai-o3` | 200K | | | | | | $2 | $8 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Eden AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 239 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Eden AI documentation](https://docs.edenai.co).
|
|
10
10
|
|
|
@@ -94,6 +94,7 @@ for await (const chunk of stream) {
|
|
|
94
94
|
| `edenai/deepinfra/openai/gpt-oss-20b` | 131K | | | | | | $0.03 | $0.14 |
|
|
95
95
|
| `edenai/deepinfra/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.09 | $0.30 |
|
|
96
96
|
| `edenai/deepinfra/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
97
|
+
| `edenai/deepinfra/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
97
98
|
| `edenai/deepinfra/thinkingmachines/Inkling` | 524K | | | | | | $0.95 | $4 |
|
|
98
99
|
| `edenai/deepinfra/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.45 | $1 |
|
|
99
100
|
| `edenai/deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
@@ -129,7 +130,6 @@ for await (const chunk of stream) {
|
|
|
129
130
|
| `edenai/google/gemini-3.7-flash` | 1.0M | | | | | | $2 | $8 |
|
|
130
131
|
| `edenai/google/gemini-flash-latest` | 1.0M | | | | | | $2 | $8 |
|
|
131
132
|
| `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
132
|
-
| `edenai/google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
|
|
133
133
|
| `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
134
134
|
| `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
135
135
|
| `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.76 | $0.76 |
|
|
@@ -221,6 +221,7 @@ for await (const chunk of stream) {
|
|
|
221
221
|
| `edenai/qwen/qwen3-vl-235b-a22b-thinking` | 131K | | | | | | $0.40 | $4 |
|
|
222
222
|
| `edenai/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
223
223
|
| `edenai/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.50 | $3 |
|
|
224
|
+
| `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.16 | $0.47 |
|
|
224
225
|
| `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
225
226
|
| `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
226
227
|
| `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.47 | $0.93 |
|
|
@@ -42,7 +42,7 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
|
|
43
43
|
| `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
|
|
44
44
|
| `hyper/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
45
|
-
| `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.
|
|
45
|
+
| `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.41 |
|
|
46
46
|
| `hyper/glm-5` | 203K | | | | | | $0.90 | $3 |
|
|
47
47
|
| `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
48
48
|
| `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
|
|
@@ -52,8 +52,8 @@ for await (const chunk of stream) {
|
|
|
52
52
|
| `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
|
|
53
53
|
| `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
|
|
54
54
|
| `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
|
|
55
|
-
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.
|
|
56
|
-
| `hyper/minimax-m2.7` | 262K | | | | | | $0.
|
|
55
|
+
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.28 | $0.93 |
|
|
56
|
+
| `hyper/minimax-m2.7` | 262K | | | | | | $0.40 | $1 |
|
|
57
57
|
| `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
|
|
58
58
|
| `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
|
|
59
59
|
| `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
|
|
@@ -39,9 +39,9 @@ for await (const chunk of stream) {
|
|
|
39
39
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
40
|
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
41
|
| `inceptron/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.13 | $0.28 |
|
|
42
|
-
| `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.
|
|
42
|
+
| `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.53 | $3 |
|
|
43
43
|
| `inceptron/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.66 | $3 |
|
|
44
|
-
| `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $0.
|
|
44
|
+
| `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $0.71 | $2 |
|
|
45
45
|
|
|
46
46
|
## Advanced configuration
|
|
47
47
|
|