@mastra/mcp-docs-server 1.2.24-alpha.1 → 1.2.24-alpha.4
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/deployment/workers.md +3 -0
- package/.docs/docs/harness/durable-agents.md +2 -0
- package/.docs/docs/server/server-adapters.md +106 -2
- package/.docs/docs/storage.md +1 -0
- package/.docs/docs/workflows/control-flow.md +16 -0
- package/.docs/docs/workflows/overview.md +2 -0
- package/.docs/integrations/databases/mysql.md +147 -0
- package/.docs/integrations/deploy/kubernetes-helm.md +148 -1
- package/.docs/integrations/frameworks/astro.md +3 -3
- package/.docs/integrations/frameworks/electron.md +3 -3
- package/.docs/integrations/frameworks/express.md +3 -3
- package/.docs/integrations/frameworks/hono.md +3 -3
- package/.docs/integrations/frameworks/nestjs.md +3 -3
- package/.docs/integrations/frameworks/next-js.md +89 -10
- package/.docs/integrations/frameworks/nuxt.md +3 -3
- package/.docs/integrations/frameworks/sveltekit.md +3 -3
- package/.docs/integrations/frameworks/tanstack-start.md +167 -0
- package/.docs/integrations/frameworks/vite-react.md +3 -3
- package/.docs/integrations/voice/gladia.md +126 -0
- package/.docs/integrations/voice/modelslab.md +138 -0
- package/.docs/integrations.md +4 -0
- package/.docs/models/environment-variables.md +1 -0
- package/.docs/models/gateways/netlify.md +1 -1
- package/.docs/models/gateways/openrouter.md +2 -1
- package/.docs/models/gateways/vercel.md +2 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/amd.md +7 -5
- package/.docs/models/providers/deepinfra.md +2 -1
- package/.docs/models/providers/edenai.md +7 -4
- package/.docs/models/providers/empiriolabs.md +3 -1
- package/.docs/models/providers/huggingface.md +76 -75
- package/.docs/models/providers/hyper.md +3 -3
- package/.docs/models/providers/kilo.md +9 -8
- package/.docs/models/providers/llmgateway-providers.md +2 -1
- package/.docs/models/providers/llmgateway.md +4 -4
- package/.docs/models/providers/meta.md +4 -2
- package/.docs/models/providers/nan.md +83 -0
- package/.docs/models/providers/nano-gpt.md +5 -1
- package/.docs/models/providers/ofox.md +3 -1
- package/.docs/models/providers/tinfoil.md +1 -1
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/client-js/observability.md +29 -0
- package/.docs/reference/datasets/updateExperiment.md +48 -0
- package/.docs/reference/index.md +4 -0
- package/.docs/reference/observability/tracing/interfaces.md +31 -1
- package/.docs/reference/observability/tracing/trace-query.md +179 -0
- package/.docs/reference/processors/processor-interface.md +52 -0
- package/.docs/reference/rag/metadata-filters.md +1 -0
- package/.docs/reference/server/next-adapter.md +93 -0
- package/.docs/reference/server/routes.md +1 -0
- package/.docs/reference/server/tanstack-start-adapter.md +105 -0
- package/.docs/reference/voice/overview.md +25 -0
- package/.docs/reference/workflows/dynamic-workflow-definition.md +25 -0
- package/.docs/reference/workflows/workflow-methods/branch.md +2 -0
- package/.docs/reference/workflows/workflow-methods/dountil.md +2 -0
- package/.docs/reference/workflows/workflow-methods/dowhile.md +2 -0
- package/.docs/reference/workflows/workflow-methods/foreach.md +1 -1
- package/.docs/reference/workflows/workflow-methods/map.md +2 -0
- package/.docs/reference/workflows/workflow-methods/parallel.md +2 -0
- package/.docs/reference/workflows/workflow-methods/sleep.md +2 -0
- package/.docs/reference/workflows/workflow-methods/sleepUntil.md +2 -0
- package/.docs/reference/workflows/workflow.md +2 -0
- package/package.json +5 -5
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenRouter
|
|
6
6
|
|
|
7
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 358 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -144,6 +144,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
144
144
|
| `inception/mercury-2` |
|
|
145
145
|
| `inception/mercury-2.5-preview` |
|
|
146
146
|
| `inclusionai/ling-3.0-flash` |
|
|
147
|
+
| `inclusionai/ling-3.0-flash-fin` |
|
|
147
148
|
| `inclusionai/ling-3.0-flash-fin:free` |
|
|
148
149
|
| `kwaipilot/kat-coder-pro-v2` |
|
|
149
150
|
| `kwaipilot/kat-coder-pro-v2.5` |
|
|
@@ -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 369 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
|
|
|
@@ -403,6 +403,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
403
403
|
| `zai/glm-5.2` |
|
|
404
404
|
| `zai/glm-5.2-fast` |
|
|
405
405
|
| `zai/glm-5.3` |
|
|
406
|
+
| `zai/glm-5.3-fast` |
|
|
406
407
|
| `zai/glm-5.3-flash` |
|
|
407
408
|
| `zai/glm-5.3-promo-50` |
|
|
408
409
|
| `zai/glm-5v-turbo` |
|
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 7059 models from 200 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# AMD
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 4 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
|
|
|
@@ -36,10 +36,12 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `amd/DeepSeek-V4-Flash`
|
|
42
|
-
| `amd/
|
|
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/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
43
|
+
| `amd/MiniCPM5-1B` | 131K | | | | | | $0.12 | $0.74 |
|
|
44
|
+
| `amd/Qwen3.8-Flash-Next` | 262K | | | | | | $0.15 | $0.47 |
|
|
43
45
|
|
|
44
46
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
45
47
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Deep Infra
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 63 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
|
|
|
@@ -46,6 +46,7 @@ for await (const chunk of stream) {
|
|
|
46
46
|
| `deepinfra/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.26 | $0.38 |
|
|
47
47
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.09 | $0.18 |
|
|
48
48
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
49
|
+
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
49
50
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
50
51
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
51
52
|
| `deepinfra/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.07 | $0.34 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Eden AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 246 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
|
|
|
@@ -107,7 +107,6 @@ for await (const chunk of stream) {
|
|
|
107
107
|
| `edenai/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
108
108
|
| `edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
109
109
|
| `edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
110
|
-
| `edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
111
110
|
| `edenai/fireworks_ai/accounts/fireworks/models/muse-glimmer-30b` | 131K | | | | | | $0.35 | $2 |
|
|
112
111
|
| `edenai/fireworks_ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
113
112
|
| `edenai/flexai/deepseek-v4-flash-0731` | 786K | | | | | | $0.03 | $0.10 |
|
|
@@ -131,6 +130,7 @@ for await (const chunk of stream) {
|
|
|
131
130
|
| `edenai/google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
132
131
|
| `edenai/google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
133
132
|
| `edenai/google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
133
|
+
| `edenai/google/gemini-3.8-flash` | 1.0M | | | | | | $2 | $8 |
|
|
134
134
|
| `edenai/google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
135
135
|
| `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
136
136
|
| `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
@@ -225,11 +225,11 @@ for await (const chunk of stream) {
|
|
|
225
225
|
| `edenai/qwen/qwen3-vl-235b-a22b-thinking` | 131K | | | | | | $0.40 | $4 |
|
|
226
226
|
| `edenai/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
227
227
|
| `edenai/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.50 | $3 |
|
|
228
|
-
| `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.
|
|
228
|
+
| `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
229
229
|
| `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
230
230
|
| `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
231
231
|
| `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
|
|
232
|
-
| `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.
|
|
232
|
+
| `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
|
|
233
233
|
| `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
|
|
234
234
|
| `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
|
|
235
235
|
| `edenai/tensorx/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
|
|
@@ -262,6 +262,9 @@ for await (const chunk of stream) {
|
|
|
262
262
|
| `edenai/vertex/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
263
263
|
| `edenai/vertex/gemini-3.7-flash@eu` | 1.0M | | | | | | $0.75 | $4 |
|
|
264
264
|
| `edenai/vertex/gemini-3.7-flash@us` | 1.0M | | | | | | $0.75 | $4 |
|
|
265
|
+
| `edenai/vertex/gemini-3.8-flash` | 1.0M | | | | | | $2 | $8 |
|
|
266
|
+
| `edenai/vertex/gemini-3.8-flash@eu` | 1.0M | | | | | | $2 | $8 |
|
|
267
|
+
| `edenai/vertex/gemini-3.8-flash@us` | 1.0M | | | | | | $2 | $8 |
|
|
265
268
|
| `edenai/vertex/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
266
269
|
| `edenai/vertex/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
267
270
|
| `edenai/xai/grok-4.20-0309-non-reasoning` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# EmpirioLabs AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 58 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
|
|
10
10
|
|
|
@@ -66,6 +66,7 @@ for await (const chunk of stream) {
|
|
|
66
66
|
| `empiriolabs/muse-glimmer-30b` | 131K | | | | | | $0.20 | $0.80 |
|
|
67
67
|
| `empiriolabs/muse-spark-1-1` | 1.0M | | | | | | $1 | $4 |
|
|
68
68
|
| `empiriolabs/muse-spark-1-2` | 1.0M | | | | | | $1 | $4 |
|
|
69
|
+
| `empiriolabs/muse-spark-1-3` | 1.0M | | | | | | $1 | $4 |
|
|
69
70
|
| `empiriolabs/qwen3-5-122b-a10b` | 256K | | | | | | $0.12 | $0.92 |
|
|
70
71
|
| `empiriolabs/qwen3-5-27b` | 256K | | | | | | $0.09 | $0.69 |
|
|
71
72
|
| `empiriolabs/qwen3-5-35b-a3b` | 256K | | | | | | $0.06 | $0.46 |
|
|
@@ -85,6 +86,7 @@ for await (const chunk of stream) {
|
|
|
85
86
|
| `empiriolabs/qwen3-8-27b` | 262K | | | | | | $0.17 | $0.50 |
|
|
86
87
|
| `empiriolabs/qwen3-8-flash` | 1.0M | | | | | | $0.16 | $0.47 |
|
|
87
88
|
| `empiriolabs/qwen3-8-max` | 1.0M | | | | | | $2 | $6 |
|
|
89
|
+
| `empiriolabs/qwen3-8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
88
90
|
| `empiriolabs/qwen3-max` | 256K | | | | | | $1 | $6 |
|
|
89
91
|
| `empiriolabs/seed-2-0-code` | 256K | | | | | | $0.40 | $2 |
|
|
90
92
|
| `empiriolabs/seed-2-0-lite` | 256K | | | | | | $0.31 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Hugging Face
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 73 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Hugging Face documentation](https://huggingface.co).
|
|
10
10
|
|
|
@@ -36,80 +36,81 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `huggingface/deepseek-ai/DeepSeek-R1`
|
|
42
|
-
| `huggingface/deepseek-ai/DeepSeek-R1-0528`
|
|
43
|
-
| `huggingface/deepseek-ai/DeepSeek-V3`
|
|
44
|
-
| `huggingface/deepseek-ai/DeepSeek-V3-0324`
|
|
45
|
-
| `huggingface/deepseek-ai/DeepSeek-V3.1`
|
|
46
|
-
| `huggingface/deepseek-ai/DeepSeek-V3.2`
|
|
47
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Flash`
|
|
48
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-0731`
|
|
49
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-
|
|
50
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Pro
|
|
51
|
-
| `huggingface/
|
|
52
|
-
| `huggingface/google/gemma-4-
|
|
53
|
-
| `huggingface/
|
|
54
|
-
| `huggingface/meta-llama/Llama-3.
|
|
55
|
-
| `huggingface/
|
|
56
|
-
| `huggingface/MiniMaxAI/MiniMax-M2
|
|
57
|
-
| `huggingface/MiniMaxAI/MiniMax-M2.
|
|
58
|
-
| `huggingface/MiniMaxAI/MiniMax-M2.
|
|
59
|
-
| `huggingface/MiniMaxAI/MiniMax-
|
|
60
|
-
| `huggingface/
|
|
61
|
-
| `huggingface/moonshotai/Kimi-K2-Instruct
|
|
62
|
-
| `huggingface/moonshotai/Kimi-K2-
|
|
63
|
-
| `huggingface/moonshotai/Kimi-K2
|
|
64
|
-
| `huggingface/moonshotai/Kimi-K2.
|
|
65
|
-
| `huggingface/moonshotai/Kimi-K2.
|
|
66
|
-
| `huggingface/moonshotai/Kimi-
|
|
67
|
-
| `huggingface/
|
|
68
|
-
| `huggingface/openai/gpt-oss-
|
|
69
|
-
| `huggingface/
|
|
70
|
-
| `huggingface/Qwen/
|
|
71
|
-
| `huggingface/Qwen/Qwen3-235B-A22B
|
|
72
|
-
| `huggingface/Qwen/Qwen3-235B-A22B-
|
|
73
|
-
| `huggingface/Qwen/Qwen3-
|
|
74
|
-
| `huggingface/Qwen/Qwen3-
|
|
75
|
-
| `huggingface/Qwen/Qwen3-
|
|
76
|
-
| `huggingface/Qwen/Qwen3-Coder-
|
|
77
|
-
| `huggingface/Qwen/Qwen3-Coder-
|
|
78
|
-
| `huggingface/Qwen/Qwen3-
|
|
79
|
-
| `huggingface/Qwen/Qwen3-Embedding-
|
|
80
|
-
| `huggingface/Qwen/Qwen3-
|
|
81
|
-
| `huggingface/Qwen/Qwen3-Next-80B-A3B-
|
|
82
|
-
| `huggingface/Qwen/Qwen3-
|
|
83
|
-
| `huggingface/Qwen/Qwen3-VL-235B-A22B-
|
|
84
|
-
| `huggingface/Qwen/Qwen3
|
|
85
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
86
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
87
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
88
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
89
|
-
| `huggingface/Qwen/Qwen3.
|
|
90
|
-
| `huggingface/Qwen/Qwen3.6-
|
|
91
|
-
| `huggingface/Qwen/Qwen3.
|
|
92
|
-
| `huggingface/Qwen/Qwen3.8-
|
|
93
|
-
| `huggingface/
|
|
94
|
-
| `huggingface/stepfun-ai/Step-3.
|
|
95
|
-
| `huggingface/
|
|
96
|
-
| `huggingface/
|
|
97
|
-
| `huggingface/thinkingmachines/Inkling
|
|
98
|
-
| `huggingface/
|
|
99
|
-
| `huggingface/XiaomiMiMo/MiMo-V2
|
|
100
|
-
| `huggingface/XiaomiMiMo/MiMo-V2.5
|
|
101
|
-
| `huggingface/
|
|
102
|
-
| `huggingface/zai-org/GLM-4.5
|
|
103
|
-
| `huggingface/zai-org/GLM-4.
|
|
104
|
-
| `huggingface/zai-org/GLM-4.
|
|
105
|
-
| `huggingface/zai-org/GLM-4.
|
|
106
|
-
| `huggingface/zai-org/GLM-4.
|
|
107
|
-
| `huggingface/zai-org/GLM-4.7
|
|
108
|
-
| `huggingface/zai-org/GLM-
|
|
109
|
-
| `huggingface/zai-org/GLM-5
|
|
110
|
-
| `huggingface/zai-org/GLM-5.
|
|
111
|
-
| `huggingface/zai-org/GLM-5.
|
|
112
|
-
| `huggingface/zai-org/GLM-5.3
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `huggingface/deepseek-ai/DeepSeek-R1` | 64K | | | | | | $0.70 | $3 |
|
|
42
|
+
| `huggingface/deepseek-ai/DeepSeek-R1-0528` | 164K | | | | | | $3 | $5 |
|
|
43
|
+
| `huggingface/deepseek-ai/DeepSeek-V3` | 64K | | | | | | $0.40 | $1 |
|
|
44
|
+
| `huggingface/deepseek-ai/DeepSeek-V3-0324` | 164K | | | | | | $0.27 | $1 |
|
|
45
|
+
| `huggingface/deepseek-ai/DeepSeek-V3.1` | 131K | | | | | | $0.27 | $1 |
|
|
46
|
+
| `huggingface/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.28 | $0.40 |
|
|
47
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
48
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
49
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
50
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
51
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
52
|
+
| `huggingface/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
53
|
+
| `huggingface/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
54
|
+
| `huggingface/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.06 | $0.06 |
|
|
55
|
+
| `huggingface/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.59 | $0.79 |
|
|
56
|
+
| `huggingface/MiniMaxAI/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
|
|
57
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
58
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
59
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.7` | 205K | | | | | | $0.30 | $1 |
|
|
60
|
+
| `huggingface/MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.30 | $1 |
|
|
61
|
+
| `huggingface/moonshotai/Kimi-K2-Instruct` | 131K | | | | | | $1 | $3 |
|
|
62
|
+
| `huggingface/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $1 | $3 |
|
|
63
|
+
| `huggingface/moonshotai/Kimi-K2-Thinking` | 262K | | | | | | $0.60 | $3 |
|
|
64
|
+
| `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
65
|
+
| `huggingface/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
66
|
+
| `huggingface/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
67
|
+
| `huggingface/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
|
|
68
|
+
| `huggingface/openai/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
|
|
69
|
+
| `huggingface/openai/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
|
|
70
|
+
| `huggingface/Qwen/Qwen2.5-Coder-32B-Instruct` | 131K | | | | | | $0.06 | $0.20 |
|
|
71
|
+
| `huggingface/Qwen/Qwen3-235B-A22B` | 41K | | | | | | $0.20 | $0.80 |
|
|
72
|
+
| `huggingface/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.85 | $3 |
|
|
73
|
+
| `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.30 | $3 |
|
|
74
|
+
| `huggingface/Qwen/Qwen3-30B-A3B` | 41K | | | | | | $0.12 | $0.50 |
|
|
75
|
+
| `huggingface/Qwen/Qwen3-32B` | 131K | | | | | | $0.29 | $0.59 |
|
|
76
|
+
| `huggingface/Qwen/Qwen3-Coder-30B-A3B-Instruct` | 262K | | | | | | $0.07 | $0.26 |
|
|
77
|
+
| `huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $2 | $2 |
|
|
78
|
+
| `huggingface/Qwen/Qwen3-Coder-Next` | 262K | | | | | | $0.20 | $2 |
|
|
79
|
+
| `huggingface/Qwen/Qwen3-Embedding-4B` | 32K | | | | | | $0.01 | — |
|
|
80
|
+
| `huggingface/Qwen/Qwen3-Embedding-8B` | 32K | | | | | | $0.01 | — |
|
|
81
|
+
| `huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.25 | $1 |
|
|
82
|
+
| `huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking` | 262K | | | | | | $0.30 | $2 |
|
|
83
|
+
| `huggingface/Qwen/Qwen3-VL-235B-A22B-Instruct` | 131K | | | | | | $0.30 | $2 |
|
|
84
|
+
| `huggingface/Qwen/Qwen3-VL-235B-A22B-Thinking` | 131K | | | | | | $0.98 | $4 |
|
|
85
|
+
| `huggingface/Qwen/Qwen3.5-122B-A10B` | 262K | | | | | | $0.40 | $3 |
|
|
86
|
+
| `huggingface/Qwen/Qwen3.5-27B` | 262K | | | | | | $0.30 | $2 |
|
|
87
|
+
| `huggingface/Qwen/Qwen3.5-35B-A3B` | 262K | | | | | | $0.25 | $2 |
|
|
88
|
+
| `huggingface/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
|
|
89
|
+
| `huggingface/Qwen/Qwen3.5-9B` | 262K | | | | | | $0.17 | $0.25 |
|
|
90
|
+
| `huggingface/Qwen/Qwen3.6-27B` | 262K | | | | | | $0.47 | $3 |
|
|
91
|
+
| `huggingface/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.15 | $0.95 |
|
|
92
|
+
| `huggingface/Qwen/Qwen3.8-2.4T-A95B` | 262K | | | | | | $3 | $6 |
|
|
93
|
+
| `huggingface/Qwen/Qwen3.8-27B` | 262K | | | | | | $0.40 | $3 |
|
|
94
|
+
| `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
95
|
+
| `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
96
|
+
| `huggingface/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
97
|
+
| `huggingface/thinkingmachines/Inkling` | 1.0M | | | | | | $1 | $4 |
|
|
98
|
+
| `huggingface/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.50 | $1 |
|
|
99
|
+
| `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
100
|
+
| `huggingface/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.40 | $2 |
|
|
101
|
+
| `huggingface/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
102
|
+
| `huggingface/zai-org/GLM-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
103
|
+
| `huggingface/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.13 | $0.85 |
|
|
104
|
+
| `huggingface/zai-org/GLM-4.5V` | 66K | | | | | | $0.60 | $2 |
|
|
105
|
+
| `huggingface/zai-org/GLM-4.6` | 205K | | | | | | $0.55 | $2 |
|
|
106
|
+
| `huggingface/zai-org/GLM-4.6V-Flash` | 131K | | | | | | $0.30 | $0.90 |
|
|
107
|
+
| `huggingface/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
108
|
+
| `huggingface/zai-org/GLM-4.7-Flash` | 200K | | | | | | — | — |
|
|
109
|
+
| `huggingface/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
110
|
+
| `huggingface/zai-org/GLM-5.1` | 203K | | | | | | $1 | $3 |
|
|
111
|
+
| `huggingface/zai-org/GLM-5.2` | 262K | | | | | | $1 | $4 |
|
|
112
|
+
| `huggingface/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
113
|
+
| `huggingface/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
113
114
|
|
|
114
115
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
115
116
|
|
|
@@ -42,8 +42,8 @@ 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.
|
|
46
|
-
| `hyper/glm-5` | 203K | | | | | | $0.
|
|
45
|
+
| `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.37 |
|
|
46
|
+
| `hyper/glm-5` | 203K | | | | | | $0.93 | $3 |
|
|
47
47
|
| `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
48
48
|
| `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
|
|
49
49
|
| `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
|
|
@@ -56,7 +56,7 @@ for await (const chunk of stream) {
|
|
|
56
56
|
| `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
|
|
57
57
|
| `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
|
|
58
58
|
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.90 |
|
|
59
|
-
| `hyper/minimax-m2.7` | 262K | | | | | | $0.
|
|
59
|
+
| `hyper/minimax-m2.7` | 262K | | | | | | $0.42 | $2 |
|
|
60
60
|
| `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
|
|
61
61
|
| `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
|
|
62
62
|
| `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 366 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
10
10
|
|
|
@@ -50,7 +50,7 @@ for await (const chunk of stream) {
|
|
|
50
50
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
51
51
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
52
52
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
53
|
-
| `kilo/~z-ai/glm-latest` |
|
|
53
|
+
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $1 | $4 |
|
|
54
54
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
55
55
|
| `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
|
|
56
56
|
| `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
|
|
@@ -91,7 +91,7 @@ for await (const chunk of stream) {
|
|
|
91
91
|
| `kilo/cohere/command-r-plus-08-2024` | 128K | | | | | | $3 | $10 |
|
|
92
92
|
| `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
|
|
93
93
|
| `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
|
|
94
|
-
| `kilo/deepseek/deepseek-chat` |
|
|
94
|
+
| `kilo/deepseek/deepseek-chat` | 164K | | | | | | $0.32 | $0.89 |
|
|
95
95
|
| `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.25 | $1 |
|
|
96
96
|
| `kilo/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.27 | $1 |
|
|
97
97
|
| `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
|
|
@@ -138,10 +138,11 @@ for await (const chunk of stream) {
|
|
|
138
138
|
| `kilo/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.06 | $0.06 |
|
|
139
139
|
| `kilo/ibm-granite/granite-4.0-h-micro` | 131K | | | | | | $0.02 | $0.11 |
|
|
140
140
|
| `kilo/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
|
|
141
|
-
| `kilo/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.
|
|
141
|
+
| `kilo/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.06 | $0.25 |
|
|
142
142
|
| `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
|
|
143
143
|
| `kilo/inception/mercury-2.5-preview` | 260K | | | | | | $0.20 | $0.75 |
|
|
144
144
|
| `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
|
|
145
|
+
| `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.06 | $0.18 |
|
|
145
146
|
| `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
|
|
146
147
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
147
148
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
@@ -157,7 +158,7 @@ for await (const chunk of stream) {
|
|
|
157
158
|
| `kilo/meta-llama/llama-3.1-8b-instruct` | 131K | | | | | | $0.02 | $0.04 |
|
|
158
159
|
| `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
|
|
159
160
|
| `kilo/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.05 | $0.33 |
|
|
160
|
-
| `kilo/meta-llama/llama-3.3-70b-instruct` |
|
|
161
|
+
| `kilo/meta-llama/llama-3.3-70b-instruct` | 131K | | | | | | $0.10 | $0.32 |
|
|
161
162
|
| `kilo/meta-llama/llama-4-maverick` | 128K | | | | | | $0.20 | $0.70 |
|
|
162
163
|
| `kilo/meta-llama/llama-4-scout` | 328K | | | | | | $0.10 | $0.30 |
|
|
163
164
|
| `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
|
|
@@ -300,7 +301,7 @@ for await (const chunk of stream) {
|
|
|
300
301
|
| `kilo/qwen/qwen-2.5-coder-32b-instruct` | 33K | | | | | | $0.66 | $1 |
|
|
301
302
|
| `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
302
303
|
| `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
303
|
-
| `kilo/qwen/qwen2.5-vl-72b-instruct` |
|
|
304
|
+
| `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
|
|
304
305
|
| `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
|
|
305
306
|
| `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
|
|
306
307
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
@@ -342,7 +343,7 @@ for await (const chunk of stream) {
|
|
|
342
343
|
| `kilo/qwen/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
343
344
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
344
345
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
345
|
-
| `kilo/qwen/qwen3.8-2.4t-a95b` |
|
|
346
|
+
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
346
347
|
| `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
|
|
347
348
|
| `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
348
349
|
| `kilo/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
@@ -392,7 +393,7 @@ for await (const chunk of stream) {
|
|
|
392
393
|
| `kilo/z-ai/glm-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
393
394
|
| `kilo/z-ai/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
|
|
394
395
|
| `kilo/z-ai/glm-4.5v` | 66K | | | | | | $0.60 | $2 |
|
|
395
|
-
| `kilo/z-ai/glm-4.6` |
|
|
396
|
+
| `kilo/z-ai/glm-4.6` | 205K | | | | | | $0.55 | $2 |
|
|
396
397
|
| `kilo/z-ai/glm-4.6v` | 131K | | | | | | $0.30 | $0.90 |
|
|
397
398
|
| `kilo/z-ai/glm-4.7` | 203K | | | | | | $0.40 | $2 |
|
|
398
399
|
| `kilo/z-ai/glm-4.7-flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 365 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
10
10
|
|
|
@@ -166,6 +166,7 @@ for await (const chunk of stream) {
|
|
|
166
166
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
167
167
|
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.13 | $0.27 |
|
|
168
168
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
169
|
+
| `llmgateway-providers/consensusprotocol/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
169
170
|
| `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
|
|
170
171
|
| `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
171
172
|
| `llmgateway-providers/deepinfra/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -19,7 +19,7 @@ const agent = new Agent({
|
|
|
19
19
|
id: "my-agent",
|
|
20
20
|
name: "My Agent",
|
|
21
21
|
instructions: "You are a helpful assistant",
|
|
22
|
-
model: "llmgateway/
|
|
22
|
+
model: "llmgateway/Qwen3.8-27B"
|
|
23
23
|
});
|
|
24
24
|
|
|
25
25
|
// Generate a response
|
|
@@ -208,7 +208,7 @@ for await (const chunk of stream) {
|
|
|
208
208
|
| `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
209
209
|
| `llmgateway/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
210
210
|
| `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
211
|
-
| `llmgateway/
|
|
211
|
+
| `llmgateway/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
212
212
|
| `llmgateway/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
213
213
|
| `llmgateway/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
|
|
214
214
|
| `llmgateway/qwen35-397b-a17b` | 262K | | | | | | $0.60 | $4 |
|
|
@@ -232,7 +232,7 @@ const agent = new Agent({
|
|
|
232
232
|
name: "custom-agent",
|
|
233
233
|
model: {
|
|
234
234
|
url: "https://api.llmgateway.io/v1",
|
|
235
|
-
id: "llmgateway/
|
|
235
|
+
id: "llmgateway/Qwen3.8-27B",
|
|
236
236
|
apiKey: process.env.LLMGATEWAY_API_KEY,
|
|
237
237
|
headers: {
|
|
238
238
|
"X-Custom-Header": "value"
|
|
@@ -251,7 +251,7 @@ const agent = new Agent({
|
|
|
251
251
|
const useAdvanced = requestContext.task === "complex";
|
|
252
252
|
return useAdvanced
|
|
253
253
|
? "llmgateway/sonar-reasoning-pro"
|
|
254
|
-
: "llmgateway/
|
|
254
|
+
: "llmgateway/Qwen3.8-27B";
|
|
255
255
|
}
|
|
256
256
|
});
|
|
257
257
|
```
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Meta
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 5 Meta models through Mastra's model router. Authentication is handled automatically using the `META_MODEL_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Meta documentation](https://dev.meta.ai/docs).
|
|
10
10
|
|
|
@@ -41,6 +41,8 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
42
42
|
| `meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
43
43
|
| `meta/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
44
|
+
| `meta/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
|
|
45
|
+
| `meta/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
44
46
|
|
|
45
47
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
46
48
|
|
|
@@ -72,7 +74,7 @@ const agent = new Agent({
|
|
|
72
74
|
model: ({ requestContext }) => {
|
|
73
75
|
const useAdvanced = requestContext.task === "complex";
|
|
74
76
|
return useAdvanced
|
|
75
|
-
? "meta/muse-spark-1.
|
|
77
|
+
? "meta/muse-spark-1.3-contributor"
|
|
76
78
|
: "meta/muse-spark-1.1";
|
|
77
79
|
}
|
|
78
80
|
});
|