@mastra/mcp-docs-server 1.2.23 → 1.2.24-alpha.10
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/channels.md +23 -0
- 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/subagents.md +1 -1
- package/.docs/docs/workflows/control-flow.md +16 -0
- package/.docs/docs/workflows/overview.md +2 -0
- package/.docs/integrations/databases/clickhouse.md +6 -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/livekit.md +88 -9
- 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/merge-gateway.md +2 -1
- package/.docs/models/gateways/netlify.md +8 -3
- package/.docs/models/gateways/openrouter.md +7 -3
- package/.docs/models/gateways/vercel.md +6 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/amd.md +7 -5
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/cline-pass.md +2 -1
- package/.docs/models/providers/cortecs.md +3 -5
- package/.docs/models/providers/crossmodel.md +4 -2
- package/.docs/models/providers/crusoe.md +7 -4
- package/.docs/models/providers/deepinfra.md +2 -1
- package/.docs/models/providers/edenai.md +15 -9
- package/.docs/models/providers/empiriolabs.md +3 -1
- package/.docs/models/providers/fireworks-ai.md +2 -1
- package/.docs/models/providers/huggingface.md +76 -75
- package/.docs/models/providers/hyper.md +4 -4
- package/.docs/models/providers/kilo.md +17 -13
- package/.docs/models/providers/llmgateway-providers.md +12 -2
- package/.docs/models/providers/llmgateway.md +10 -6
- package/.docs/models/providers/meta.md +4 -2
- package/.docs/models/providers/nan.md +83 -0
- package/.docs/models/providers/nano-gpt.md +47 -45
- package/.docs/models/providers/ofox.md +3 -1
- package/.docs/models/providers/openai.md +2 -1
- package/.docs/models/providers/opencode-go.md +2 -1
- package/.docs/models/providers/opencode.md +6 -1
- package/.docs/models/providers/scnet-token-plan.md +4 -1
- package/.docs/models/providers/tinfoil.md +1 -1
- package/.docs/models/providers/wandb.md +3 -2
- package/.docs/models/providers/xai.md +3 -3
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/client-js/mastra-client.md +3 -1
- package/.docs/reference/client-js/observability.md +43 -0
- package/.docs/reference/datasets/updateExperiment.md +48 -0
- package/.docs/reference/index.md +4 -0
- package/.docs/reference/observability/tracing/interfaces.md +47 -1
- package/.docs/reference/observability/tracing/processors/sensitive-data-filter.md +2 -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
|
# 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
|
# Fireworks AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 20 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
|
|
10
10
|
|
|
@@ -54,6 +54,7 @@ for await (const chunk of stream) {
|
|
|
54
54
|
| `fireworks-ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4` | 262K | | | | | | $0.60 | $2 |
|
|
55
55
|
| `fireworks-ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
|
|
56
56
|
| `fireworks-ai/accounts/fireworks/models/qwen3p7-plus` | 262K | | | | | | $0.40 | $2 |
|
|
57
|
+
| `fireworks-ai/accounts/fireworks/models/qwen3p8-2p4t-a95b` | 262K | | | | | | $2 | $6 |
|
|
57
58
|
| `fireworks-ai/accounts/fireworks/models/qwen3p8-max` | 262K | | | | | | $2 | $6 |
|
|
58
59
|
| `fireworks-ai/accounts/fireworks/routers/glm-5p2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
59
60
|
| `fireworks-ai/accounts/fireworks/routers/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
|
|
@@ -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
|
|
|
@@ -42,21 +42,21 @@ 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 | | | | | | $0.86 | $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 |
|
|
50
50
|
| `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
|
|
51
51
|
| `hyper/gpt-oss-120b` | 128K | | | | | | $0.19 | $0.70 |
|
|
52
52
|
| `hyper/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
53
|
-
| `hyper/kimi-k2.5` | 262K | | | | | | $0.
|
|
53
|
+
| `hyper/kimi-k2.5` | 262K | | | | | | $0.51 | $3 |
|
|
54
54
|
| `hyper/kimi-k2.6` | 262K | | | | | | $1 | $4 |
|
|
55
55
|
| `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
|
|
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 | | | | | | $0.48 | $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 369 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
|
|
|
@@ -42,7 +42,7 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
|
|
43
43
|
| `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
|
|
44
44
|
| `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
|
|
45
|
-
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.
|
|
45
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.10 |
|
|
46
46
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
47
47
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
48
48
|
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $3 | $13 |
|
|
@@ -91,9 +91,9 @@ 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
|
-
| `kilo/deepseek/deepseek-chat-v3.1` |
|
|
96
|
+
| `kilo/deepseek/deepseek-chat-v3.1` | 161K | | | | | | $0.27 | $1 |
|
|
97
97
|
| `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
|
|
98
98
|
| `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
|
|
99
99
|
| `kilo/deepseek/deepseek-r1-distill-llama-70b` | 8K | | | | | | $0.80 | $0.80 |
|
|
@@ -137,12 +137,13 @@ for await (const chunk of stream) {
|
|
|
137
137
|
| `kilo/google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
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
|
-
| `kilo/ibm-granite/granite-4.
|
|
141
|
-
| `kilo/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
|
|
140
|
+
| `kilo/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.06 | $0.25 |
|
|
142
141
|
| `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
|
|
143
142
|
| `kilo/inception/mercury-2.5-preview` | 260K | | | | | | $0.20 | $0.75 |
|
|
144
143
|
| `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
|
|
144
|
+
| `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.06 | $0.18 |
|
|
145
145
|
| `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
|
|
146
|
+
| `kilo/inclusionai/ling-3.0-flash-sante:free` | 262K | | | | | | — | — |
|
|
146
147
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
147
148
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
148
149
|
| `kilo/kilo-auto/free` | 256K | | | | | | — | — |
|
|
@@ -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 |
|
|
@@ -217,8 +218,9 @@ for await (const chunk of stream) {
|
|
|
217
218
|
| `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
|
|
218
219
|
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.09 | $0.40 |
|
|
219
220
|
| `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
|
|
220
|
-
| `kilo/nvidia/nemotron-3-ultra-550b-a55b` |
|
|
221
|
+
| `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 256K | | | | | | $0.50 | $2 |
|
|
221
222
|
| `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
|
|
223
|
+
| `kilo/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.20 | $0.20 |
|
|
222
224
|
| `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
|
|
223
225
|
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.08 | $0.20 |
|
|
224
226
|
| `kilo/nvidia/nemotron-3.5-lightning:free` | 1.0M | | | | | | — | — |
|
|
@@ -267,6 +269,8 @@ for await (const chunk of stream) {
|
|
|
267
269
|
| `kilo/openai/gpt-5.6-sol-pro` | 1.1M | | | | | | $4 | $20 |
|
|
268
270
|
| `kilo/openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
269
271
|
| `kilo/openai/gpt-5.6-terra-pro` | 1.1M | | | | | | $2 | $12 |
|
|
272
|
+
| `kilo/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
273
|
+
| `kilo/openai/gpt-6-astra-pro` | 1.1M | | | | | | $10 | $50 |
|
|
270
274
|
| `kilo/openai/gpt-audio` | 128K | | | | | | $3 | $10 |
|
|
271
275
|
| `kilo/openai/gpt-audio-mini` | 128K | | | | | | $0.60 | $2 |
|
|
272
276
|
| `kilo/openai/gpt-chat-latest` | 400K | | | | | | $5 | $30 |
|
|
@@ -300,7 +304,7 @@ for await (const chunk of stream) {
|
|
|
300
304
|
| `kilo/qwen/qwen-2.5-coder-32b-instruct` | 33K | | | | | | $0.66 | $1 |
|
|
301
305
|
| `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
302
306
|
| `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
303
|
-
| `kilo/qwen/qwen2.5-vl-72b-instruct` |
|
|
307
|
+
| `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
|
|
304
308
|
| `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
|
|
305
309
|
| `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
|
|
306
310
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
@@ -342,10 +346,10 @@ for await (const chunk of stream) {
|
|
|
342
346
|
| `kilo/qwen/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
343
347
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
344
348
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
345
|
-
| `kilo/qwen/qwen3.8-2.4t-a95b` |
|
|
349
|
+
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
346
350
|
| `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
|
|
347
351
|
| `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
348
|
-
| `kilo/qwen/qwen3.8-max`
|
|
352
|
+
| `kilo/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
349
353
|
| `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
|
|
350
354
|
| `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
|
|
351
355
|
| `kilo/relace/relace-apply-3` | 256K | | | | | | $0.85 | $1 |
|
|
@@ -367,7 +371,7 @@ for await (const chunk of stream) {
|
|
|
367
371
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
368
372
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
369
373
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
370
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
374
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
371
375
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
372
376
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
373
377
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
@@ -392,7 +396,7 @@ for await (const chunk of stream) {
|
|
|
392
396
|
| `kilo/z-ai/glm-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
393
397
|
| `kilo/z-ai/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
|
|
394
398
|
| `kilo/z-ai/glm-4.5v` | 66K | | | | | | $0.60 | $2 |
|
|
395
|
-
| `kilo/z-ai/glm-4.6` |
|
|
399
|
+
| `kilo/z-ai/glm-4.6` | 205K | | | | | | $0.55 | $2 |
|
|
396
400
|
| `kilo/z-ai/glm-4.6v` | 131K | | | | | | $0.30 | $0.90 |
|
|
397
401
|
| `kilo/z-ai/glm-4.7` | 203K | | | | | | $0.40 | $2 |
|
|
398
402
|
| `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 374 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
|
|
|
@@ -132,6 +132,7 @@ for await (const chunk of stream) {
|
|
|
132
132
|
| `llmgateway-providers/azure/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
133
133
|
| `llmgateway-providers/azure/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
134
134
|
| `llmgateway-providers/azure/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
135
|
+
| `llmgateway-providers/azure/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
135
136
|
| `llmgateway-providers/azure/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
136
137
|
| `llmgateway-providers/azure/o1` | 200K | | | | | | $15 | $60 |
|
|
137
138
|
| `llmgateway-providers/azure/o3` | 200K | | | | | | $2 | $8 |
|
|
@@ -164,8 +165,10 @@ for await (const chunk of stream) {
|
|
|
164
165
|
| `llmgateway-providers/cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
|
|
165
166
|
| `llmgateway-providers/cerebras/llama-3.3-70b-instruct` | 128K | | | | | | $0.85 | $1 |
|
|
166
167
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
167
|
-
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.
|
|
168
|
+
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.07 | $0.16 |
|
|
169
|
+
| `llmgateway-providers/consensusprotocol/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
|
|
168
170
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
171
|
+
| `llmgateway-providers/consensusprotocol/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
169
172
|
| `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
|
|
170
173
|
| `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
171
174
|
| `llmgateway-providers/deepinfra/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -210,6 +213,7 @@ for await (const chunk of stream) {
|
|
|
210
213
|
| `llmgateway-providers/google-ai-studio/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
211
214
|
| `llmgateway-providers/google-ai-studio/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
212
215
|
| `llmgateway-providers/google-ai-studio/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
216
|
+
| `llmgateway-providers/google-ai-studio/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
213
217
|
| `llmgateway-providers/google-ai-studio/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
214
218
|
| `llmgateway-providers/google-vertex/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
215
219
|
| `llmgateway-providers/google-vertex/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
@@ -225,8 +229,11 @@ for await (const chunk of stream) {
|
|
|
225
229
|
| `llmgateway-providers/groq/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.75 |
|
|
226
230
|
| `llmgateway-providers/groq/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
|
|
227
231
|
| `llmgateway-providers/inference.net/llama-3.2-11b-instruct` | 128K | | | | | | $0.07 | $0.33 |
|
|
232
|
+
| `llmgateway-providers/meta-contributor/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
233
|
+
| `llmgateway-providers/meta-contributor/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
228
234
|
| `llmgateway-providers/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
229
235
|
| `llmgateway-providers/meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
236
|
+
| `llmgateway-providers/meta/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
|
|
230
237
|
| `llmgateway-providers/minimax/minimax-m2` | 197K | | | | | | $0.20 | $1 |
|
|
231
238
|
| `llmgateway-providers/minimax/minimax-m2.1` | 197K | | | | | | $0.27 | $1 |
|
|
232
239
|
| `llmgateway-providers/minimax/minimax-m2.1-lightning` | 197K | | | | | | $0.12 | $0.48 |
|
|
@@ -262,6 +269,7 @@ for await (const chunk of stream) {
|
|
|
262
269
|
| `llmgateway-providers/novita/glm-5.1` | 205K | | | | | | $1 | $4 |
|
|
263
270
|
| `llmgateway-providers/novita/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
264
271
|
| `llmgateway-providers/novita/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
272
|
+
| `llmgateway-providers/novita/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
265
273
|
| `llmgateway-providers/novita/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
266
274
|
| `llmgateway-providers/novita/kimi-k2` | 131K | | | | | | $0.57 | $2 |
|
|
267
275
|
| `llmgateway-providers/novita/kimi-k2.6` | 262K | | | | | | $0.80 | $3 |
|
|
@@ -321,6 +329,7 @@ for await (const chunk of stream) {
|
|
|
321
329
|
| `llmgateway-providers/openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
322
330
|
| `llmgateway-providers/openai/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
323
331
|
| `llmgateway-providers/openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
332
|
+
| `llmgateway-providers/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
324
333
|
| `llmgateway-providers/openai/o1` | 200K | | | | | | $15 | $60 |
|
|
325
334
|
| `llmgateway-providers/openai/o3` | 200K | | | | | | $2 | $8 |
|
|
326
335
|
| `llmgateway-providers/openai/o3-mini` | 200K | | | | | | $1 | $4 |
|
|
@@ -338,6 +347,7 @@ for await (const chunk of stream) {
|
|
|
338
347
|
| `llmgateway-providers/runware/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
339
348
|
| `llmgateway-providers/runware/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
|
|
340
349
|
| `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
|
|
350
|
+
| `llmgateway-providers/runware/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
341
351
|
| `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
342
352
|
| `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.55 | $2 |
|
|
343
353
|
| `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $6 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 186 DevPass (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 [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
|
|
10
10
|
|
|
@@ -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
|
|
@@ -92,7 +92,7 @@ for await (const chunk of stream) {
|
|
|
92
92
|
| `llmgateway/glm-5.2` | 1.0M | | | | | | $0.55 | $2 |
|
|
93
93
|
| `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $6 |
|
|
94
94
|
| `llmgateway/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
95
|
-
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.
|
|
95
|
+
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
|
|
96
96
|
| `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
97
97
|
| `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
98
98
|
| `llmgateway/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
|
|
@@ -123,6 +123,7 @@ for await (const chunk of stream) {
|
|
|
123
123
|
| `llmgateway/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
124
124
|
| `llmgateway/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
125
125
|
| `llmgateway/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
126
|
+
| `llmgateway/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
126
127
|
| `llmgateway/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
|
|
127
128
|
| `llmgateway/gpt-oss-20b` | 131K | | | | | | $0.04 | $0.19 |
|
|
128
129
|
| `llmgateway/grok-4` | 256K | | | | | | $3 | $15 |
|
|
@@ -172,6 +173,9 @@ for await (const chunk of stream) {
|
|
|
172
173
|
| `llmgateway/mistral-small-2506` | 128K | | | | | | $0.10 | $0.30 |
|
|
173
174
|
| `llmgateway/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
174
175
|
| `llmgateway/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
176
|
+
| `llmgateway/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
177
|
+
| `llmgateway/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
|
|
178
|
+
| `llmgateway/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
175
179
|
| `llmgateway/nemotron-3-ultra-550b` | 1.0M | | | | | | $0.50 | $2 |
|
|
176
180
|
| `llmgateway/o1` | 200K | | | | | | $15 | $60 |
|
|
177
181
|
| `llmgateway/o3` | 200K | | | | | | $2 | $8 |
|
|
@@ -208,7 +212,7 @@ for await (const chunk of stream) {
|
|
|
208
212
|
| `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
209
213
|
| `llmgateway/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
210
214
|
| `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
211
|
-
| `llmgateway/
|
|
215
|
+
| `llmgateway/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
212
216
|
| `llmgateway/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
213
217
|
| `llmgateway/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
|
|
214
218
|
| `llmgateway/qwen35-397b-a17b` | 262K | | | | | | $0.60 | $4 |
|
|
@@ -232,7 +236,7 @@ const agent = new Agent({
|
|
|
232
236
|
name: "custom-agent",
|
|
233
237
|
model: {
|
|
234
238
|
url: "https://api.llmgateway.io/v1",
|
|
235
|
-
id: "llmgateway/
|
|
239
|
+
id: "llmgateway/Qwen3.8-27B",
|
|
236
240
|
apiKey: process.env.LLMGATEWAY_API_KEY,
|
|
237
241
|
headers: {
|
|
238
242
|
"X-Custom-Header": "value"
|
|
@@ -251,7 +255,7 @@ const agent = new Agent({
|
|
|
251
255
|
const useAdvanced = requestContext.task === "complex";
|
|
252
256
|
return useAdvanced
|
|
253
257
|
? "llmgateway/sonar-reasoning-pro"
|
|
254
|
-
: "llmgateway/
|
|
258
|
+
: "llmgateway/Qwen3.8-27B";
|
|
255
259
|
}
|
|
256
260
|
});
|
|
257
261
|
```
|
|
@@ -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
|
});
|