@mastra/mcp-docs-server 1.2.27-alpha.22 → 1.2.27-alpha.24
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/models/environment-variables.md +1 -0
- package/.docs/models/gateways/merge-gateway.md +2 -1
- package/.docs/models/gateways/netlify.md +2 -1
- package/.docs/models/gateways/openrouter.md +5 -2
- package/.docs/models/gateways/vercel.md +2 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/deepinfra.md +1 -1
- package/.docs/models/providers/edenai.md +2 -2
- package/.docs/models/providers/empiriolabs.md +5 -2
- package/.docs/models/providers/huggingface.md +2 -1
- package/.docs/models/providers/kilo.md +13 -10
- package/.docs/models/providers/llmgateway-providers.md +3 -1
- package/.docs/models/providers/llmgateway.md +3 -2
- package/.docs/models/providers/llmtech.md +7 -7
- package/.docs/models/providers/nano-gpt.md +2 -1
- package/.docs/models/providers/neuralwatt.md +25 -25
- package/.docs/models/providers/opencode-go.md +4 -1
- package/.docs/models/providers/opencode.md +2 -1
- package/.docs/models/providers/opper.md +63 -47
- package/.docs/models/providers/siliconflow-cn.md +1 -4
- package/.docs/models/providers/siliconflow.md +60 -52
- package/.docs/models/providers/stepfun-ai.md +2 -1
- package/.docs/models/providers/stepfun-step-plan.md +2 -1
- package/.docs/models/providers/tempr.md +90 -0
- package/.docs/models/providers/vivgrid.md +4 -2
- package/.docs/models/providers/xai.md +3 -1
- package/.docs/models/providers/zai.md +2 -1
- package/.docs/models/providers/zhipuai.md +2 -1
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/cli/mastra.md +11 -0
- package/.docs/reference/client-js/observability.md +27 -0
- package/.docs/reference/observability/tracing/interfaces.md +33 -0
- package/.docs/reference/observability/tracing/trace-query.md +78 -8
- package/.docs/reference/tools/mcp-server.md +8 -0
- package/package.json +3 -3
|
@@ -174,6 +174,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
174
174
|
| [Subconscious](https://mastra.ai/models/providers/subconscious) | `subconscious/*` | `SUBCONSCIOUS_API_KEY` |
|
|
175
175
|
| [submodel](https://mastra.ai/models/providers/submodel) | `submodel/*` | `SUBMODEL_INSTAGEN_ACCESS_KEY` |
|
|
176
176
|
| [Synthetic](https://mastra.ai/models/providers/synthetic) | `synthetic/*` | `SYNTHETIC_API_KEY` |
|
|
177
|
+
| [Tempr](https://mastra.ai/models/providers/tempr) | `tempr/*` | `TEMPR_API_KEY` |
|
|
177
178
|
| [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan) | `tencent-coding-plan/*` | `TENCENT_CODING_PLAN_API_KEY` |
|
|
178
179
|
| [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan) | `tencent-token-plan/*` | `TENCENT_TOKEN_PLAN_API_KEY` |
|
|
179
180
|
| [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub) | `tencent-tokenhub/*` | `TENCENT_TOKENHUB_API_KEY` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Merge Gateway
|
|
6
6
|
|
|
7
|
-
Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 188 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Merge Gateway documentation](https://docs.merge.dev/merge-gateway).
|
|
10
10
|
|
|
@@ -211,6 +211,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
211
211
|
| `xai/grok-4.3` |
|
|
212
212
|
| `xai/grok-4.5` |
|
|
213
213
|
| `xai/grok-4.6` |
|
|
214
|
+
| `xai/grok-4.7` |
|
|
214
215
|
| `xai/grok-build-0.1` |
|
|
215
216
|
| `zai/glm-4.5` |
|
|
216
217
|
| `zai/glm-4.5-air` |
|
|
@@ -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 261 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
|
|
|
@@ -281,6 +281,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
281
281
|
| `openrouter/x-ai/grok-4.3` |
|
|
282
282
|
| `openrouter/x-ai/grok-4.5` |
|
|
283
283
|
| `openrouter/x-ai/grok-4.6` |
|
|
284
|
+
| `openrouter/x-ai/grok-4.7` |
|
|
284
285
|
| `openrouter/x-ai/grok-build-0.1` |
|
|
285
286
|
| `openrouter/xiaomi/mimo-v2.5` |
|
|
286
287
|
| `openrouter/xiaomi/mimo-v2.5-pro` |
|
|
@@ -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 374 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -70,7 +70,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
70
70
|
| `anthropic/claude-fable-5` |
|
|
71
71
|
| `anthropic/claude-fable-5.1` |
|
|
72
72
|
| `anthropic/claude-haiku-4.5` |
|
|
73
|
-
| `anthropic/claude-opus-4` |
|
|
74
73
|
| `anthropic/claude-opus-4.1` |
|
|
75
74
|
| `anthropic/claude-opus-4.5` |
|
|
76
75
|
| `anthropic/claude-opus-4.6` |
|
|
@@ -390,9 +389,13 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
390
389
|
| `x-ai/grok-4.3` |
|
|
391
390
|
| `x-ai/grok-4.5` |
|
|
392
391
|
| `x-ai/grok-4.6` |
|
|
392
|
+
| `x-ai/grok-4.7` |
|
|
393
393
|
| `x-ai/grok-build-0.1` |
|
|
394
394
|
| `xiaomi/mimo-v2.5` |
|
|
395
395
|
| `xiaomi/mimo-v2.5-pro` |
|
|
396
|
+
| `xiaomi/mimo-v2.6-flash` |
|
|
397
|
+
| `xiaomi/mimo-v2.6-pro` |
|
|
398
|
+
| `xiaomi/mimo-v2.6-pro-ultraspeed` |
|
|
396
399
|
| `z-ai/glm-4.5` |
|
|
397
400
|
| `z-ai/glm-4.5-air` |
|
|
398
401
|
| `z-ai/glm-4.5v` |
|
|
@@ -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 376 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
|
|
|
@@ -363,6 +363,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
363
363
|
| `spacexai/grok-4.3` |
|
|
364
364
|
| `spacexai/grok-4.5` |
|
|
365
365
|
| `spacexai/grok-4.6` |
|
|
366
|
+
| `spacexai/grok-4.7` |
|
|
366
367
|
| `spacexai/grok-build-0.1` |
|
|
367
368
|
| `spacexai/grok-imagine-image` |
|
|
368
369
|
| `spacexai/grok-imagine-image-2.0` |
|
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 7437 models from 210 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -86,7 +86,7 @@ for await (const chunk of stream) {
|
|
|
86
86
|
| `deepinfra/Qwen/Qwen3.8-Flash` | 1.0M | | | | | | $0.11 | $0.38 |
|
|
87
87
|
| `deepinfra/Qwen/Qwen3.8-Max` | 256K | | | | | | $2 | $5 |
|
|
88
88
|
| `deepinfra/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
89
|
-
| `deepinfra/tencent/Hy3` | 262K | | | | | | $0.
|
|
89
|
+
| `deepinfra/tencent/Hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
90
90
|
| `deepinfra/thinkingmachines/Inkling` | 524K | | | | | | $0.95 | $4 |
|
|
91
91
|
| `deepinfra/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.45 | $1 |
|
|
92
92
|
| `deepinfra/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.14 | $0.28 |
|
|
@@ -162,8 +162,8 @@ for await (const chunk of stream) {
|
|
|
162
162
|
| `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
163
163
|
| `edenai/groq/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
164
164
|
| `edenai/infomaniak/mistralai/Ministral-3-14B-Instruct-2512` | 100K | | | | | | $0.34 | $0.46 |
|
|
165
|
-
| `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.
|
|
166
|
-
| `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.
|
|
165
|
+
| `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
|
|
166
|
+
| `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
|
|
167
167
|
| `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
|
|
168
168
|
| `edenai/minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
169
169
|
| `edenai/minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# EmpirioLabs AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 65 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
|
|
|
@@ -62,6 +62,8 @@ for await (const chunk of stream) {
|
|
|
62
62
|
| `empiriolabs/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
63
63
|
| `empiriolabs/mimo-v2-5` | 1.0M | | | | | | $0.70 | $1 |
|
|
64
64
|
| `empiriolabs/mimo-v2-5-pro` | 1.0M | | | | | | $2 | $4 |
|
|
65
|
+
| `empiriolabs/mimo-v2-6-flash` | 1.0M | | | | | | $0.70 | $1 |
|
|
66
|
+
| `empiriolabs/mimo-v2-6-pro` | 1.0M | | | | | | $2 | $4 |
|
|
65
67
|
| `empiriolabs/minimax-m2-7` | 200K | | | | | | $0.15 | $0.60 |
|
|
66
68
|
| `empiriolabs/minimax-m2-7-highspeed` | 200K | | | | | | $0.30 | $1 |
|
|
67
69
|
| `empiriolabs/minimax-m3` | 1.0M | | | | | | $0.23 | $0.90 |
|
|
@@ -100,6 +102,7 @@ for await (const chunk of stream) {
|
|
|
100
102
|
| `empiriolabs/step-3-5-flash` | 256K | | | | | | $0.10 | $0.30 |
|
|
101
103
|
| `empiriolabs/step-3-5-flash-2603` | 256K | | | | | | $0.10 | $0.30 |
|
|
102
104
|
| `empiriolabs/step-3-7-flash` | 256K | | | | | | $0.20 | $1 |
|
|
105
|
+
| `empiriolabs/step-5-preview` | 1.0M | | | | | | $1 | $3 |
|
|
103
106
|
|
|
104
107
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
105
108
|
|
|
@@ -131,7 +134,7 @@ const agent = new Agent({
|
|
|
131
134
|
model: ({ requestContext }) => {
|
|
132
135
|
const useAdvanced = requestContext.task === "complex";
|
|
133
136
|
return useAdvanced
|
|
134
|
-
? "empiriolabs/step-
|
|
137
|
+
? "empiriolabs/step-5-preview"
|
|
135
138
|
: "empiriolabs/deepseek-v3-2";
|
|
136
139
|
}
|
|
137
140
|
});
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Hugging Face
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 78 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
|
|
|
@@ -98,6 +98,7 @@ for await (const chunk of stream) {
|
|
|
98
98
|
| `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
99
99
|
| `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
100
100
|
| `huggingface/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
101
|
+
| `huggingface/tencent/Hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
101
102
|
| `huggingface/thinkingmachines/Inkling` | 1.0M | | | | | | $1 | $4 |
|
|
102
103
|
| `huggingface/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.50 | $1 |
|
|
103
104
|
| `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 381 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
|
|
|
@@ -43,17 +43,17 @@ for await (const chunk of stream) {
|
|
|
43
43
|
| `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
|
|
44
44
|
| `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
|
|
45
45
|
| `kilo/~deepseek/deepseek-flash-latest` | 1.0M | | | | | | $0.12 | $0.48 |
|
|
46
|
-
| `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.
|
|
47
|
-
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.
|
|
46
|
+
| `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.53 | $2 |
|
|
47
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.40 |
|
|
48
48
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
49
49
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
50
|
-
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $
|
|
50
|
+
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $8 |
|
|
51
51
|
| `kilo/~openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
|
|
52
52
|
| `kilo/~openai/gpt-luna-latest` | 1.1M | | | | | | $0.20 | $1 |
|
|
53
53
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
54
54
|
| `kilo/~openai/gpt-sol-latest` | 1.1M | | | | | | $2 | $10 |
|
|
55
55
|
| `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
|
|
56
|
-
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $
|
|
56
|
+
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $5 |
|
|
57
57
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
58
58
|
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.77 | $2 |
|
|
59
59
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
@@ -70,7 +70,6 @@ for await (const chunk of stream) {
|
|
|
70
70
|
| `kilo/anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
|
|
71
71
|
| `kilo/anthropic/claude-fable-5.1` | 1.0M | | | | | | $10 | $50 |
|
|
72
72
|
| `kilo/anthropic/claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
|
|
73
|
-
| `kilo/anthropic/claude-opus-4` | 200K | | | | | | $15 | $75 |
|
|
74
73
|
| `kilo/anthropic/claude-opus-4.1` | 200K | | | | | | $15 | $75 |
|
|
75
74
|
| `kilo/anthropic/claude-opus-4.5` | 200K | | | | | | $5 | $25 |
|
|
76
75
|
| `kilo/anthropic/claude-opus-4.6` | 1.0M | | | | | | $5 | $25 |
|
|
@@ -168,7 +167,7 @@ for await (const chunk of stream) {
|
|
|
168
167
|
| `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
|
|
169
168
|
| `kilo/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.05 | $0.33 |
|
|
170
169
|
| `kilo/meta-llama/llama-3.3-70b-instruct` | 131K | | | | | | $0.10 | $0.32 |
|
|
171
|
-
| `kilo/meta-llama/llama-4-maverick` |
|
|
170
|
+
| `kilo/meta-llama/llama-4-maverick` | 128K | | | | | | $0.19 | $0.65 |
|
|
172
171
|
| `kilo/meta-llama/llama-4-scout` | 328K | | | | | | $0.10 | $0.30 |
|
|
173
172
|
| `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
|
|
174
173
|
| `kilo/meta/muse-glimmer-30b` | 131K | | | | | | $0.30 | $1 |
|
|
@@ -211,7 +210,7 @@ for await (const chunk of stream) {
|
|
|
211
210
|
| `kilo/moonshotai/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
|
|
212
211
|
| `kilo/moonshotai/kimi-k2.6` | 262K | | | | | | $0.80 | $3 |
|
|
213
212
|
| `kilo/moonshotai/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
214
|
-
| `kilo/moonshotai/kimi-k3` | 1.0M | | | | | | $
|
|
213
|
+
| `kilo/moonshotai/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
215
214
|
| `kilo/morph/morph-v3-fast` | 82K | | | | | | $0.80 | $1 |
|
|
216
215
|
| `kilo/morph/morph-v3-large` | 262K | | | | | | $0.90 | $2 |
|
|
217
216
|
| `kilo/nex-agi/nex-n2.5-mini:free` | 262K | | | | | | — | — |
|
|
@@ -351,7 +350,7 @@ for await (const chunk of stream) {
|
|
|
351
350
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
352
351
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
353
352
|
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
354
|
-
| `kilo/qwen/qwen3.8-27b` |
|
|
353
|
+
| `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
|
|
355
354
|
| `kilo/qwen/qwen3.8-27b:free` | 262K | | | | | | — | — |
|
|
356
355
|
| `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
357
356
|
| `kilo/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
@@ -378,7 +377,7 @@ for await (const chunk of stream) {
|
|
|
378
377
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
379
378
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
380
379
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
381
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
380
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
|
|
382
381
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
383
382
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
384
383
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
@@ -397,9 +396,13 @@ for await (const chunk of stream) {
|
|
|
397
396
|
| `kilo/x-ai/grok-4.3` | 1.0M | | | | | | $1 | $3 |
|
|
398
397
|
| `kilo/x-ai/grok-4.5` | 500K | | | | | | $2 | $6 |
|
|
399
398
|
| `kilo/x-ai/grok-4.6` | 500K | | | | | | $2 | $6 |
|
|
399
|
+
| `kilo/x-ai/grok-4.7` | 500K | | | | | | $2 | $5 |
|
|
400
400
|
| `kilo/x-ai/grok-build-0.1` | 256K | | | | | | $1 | $2 |
|
|
401
401
|
| `kilo/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
402
402
|
| `kilo/xiaomi/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
403
|
+
| `kilo/xiaomi/mimo-v2.6-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
404
|
+
| `kilo/xiaomi/mimo-v2.6-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
405
|
+
| `kilo/xiaomi/mimo-v2.6-pro-ultraspeed` | 1.0M | | | | | | $4 | $9 |
|
|
403
406
|
| `kilo/z-ai/glm-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
404
407
|
| `kilo/z-ai/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
|
|
405
408
|
| `kilo/z-ai/glm-4.5v` | 66K | | | | | | $0.60 | $2 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 406 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
|
|
|
@@ -210,6 +210,7 @@ for await (const chunk of stream) {
|
|
|
210
210
|
| `llmgateway-providers/fireworks/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
211
211
|
| `llmgateway-providers/fireworks/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
|
|
212
212
|
| `llmgateway-providers/gonka24/deepseek-v4-flash` | 390K | | | | | | $0.05 | $0.10 |
|
|
213
|
+
| `llmgateway-providers/gonka24/glm-5.3-flash` | 200K | | | | | | $0.07 | $0.19 |
|
|
213
214
|
| `llmgateway-providers/gonka24/minimax-m2.7` | 205K | | | | | | $0.08 | $0.32 |
|
|
214
215
|
| `llmgateway-providers/google-ai-studio/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
215
216
|
| `llmgateway-providers/google-ai-studio/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
@@ -423,6 +424,7 @@ for await (const chunk of stream) {
|
|
|
423
424
|
| `llmgateway-providers/xai/grok-4-3` | 1.0M | | | | | | $1 | $3 |
|
|
424
425
|
| `llmgateway-providers/xai/grok-4-5` | 500K | | | | | | $2 | $6 |
|
|
425
426
|
| `llmgateway-providers/xai/grok-4-6` | 500K | | | | | | $2 | $6 |
|
|
427
|
+
| `llmgateway-providers/xai/grok-4-7` | 500K | | | | | | $2 | $6 |
|
|
426
428
|
| `llmgateway-providers/xai/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
427
429
|
| `llmgateway-providers/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
428
430
|
| `llmgateway-providers/xiaomi/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 194 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
|
|
|
@@ -96,7 +96,7 @@ for await (const chunk of stream) {
|
|
|
96
96
|
| `llmgateway/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
|
|
97
97
|
| `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
98
98
|
| `llmgateway/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
99
|
-
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.
|
|
99
|
+
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.19 |
|
|
100
100
|
| `llmgateway/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
|
|
101
101
|
| `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
102
102
|
| `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
@@ -141,6 +141,7 @@ for await (const chunk of stream) {
|
|
|
141
141
|
| `llmgateway/grok-4-3` | 1.0M | | | | | | $1 | $3 |
|
|
142
142
|
| `llmgateway/grok-4-5` | 500K | | | | | | $2 | $6 |
|
|
143
143
|
| `llmgateway/grok-4-6` | 500K | | | | | | $2 | $6 |
|
|
144
|
+
| `llmgateway/grok-4-7` | 500K | | | | | | $2 | $6 |
|
|
144
145
|
| `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
145
146
|
| `llmgateway/hy-mt2-plus` | 8K | | | | | | $0.07 | $0.29 |
|
|
146
147
|
| `llmgateway/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
@@ -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: "llmtech/
|
|
22
|
+
model: "llmtech/nvidia/Qwen3.8-27B-NVFP4"
|
|
23
23
|
});
|
|
24
24
|
|
|
25
25
|
// Generate a response
|
|
@@ -36,9 +36,9 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `llmtech/
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `llmtech/nvidia/Qwen3.8-27B-NVFP4` | 262K | | | | | | $0.25 | $2 |
|
|
42
42
|
|
|
43
43
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
44
44
|
|
|
@@ -52,7 +52,7 @@ const agent = new Agent({
|
|
|
52
52
|
name: "custom-agent",
|
|
53
53
|
model: {
|
|
54
54
|
url: "https://api.llmtech.eu/v1",
|
|
55
|
-
id: "llmtech/
|
|
55
|
+
id: "llmtech/nvidia/Qwen3.8-27B-NVFP4",
|
|
56
56
|
apiKey: process.env.LLMTECH_API_KEY,
|
|
57
57
|
headers: {
|
|
58
58
|
"X-Custom-Header": "value"
|
|
@@ -70,8 +70,8 @@ const agent = new Agent({
|
|
|
70
70
|
model: ({ requestContext }) => {
|
|
71
71
|
const useAdvanced = requestContext.task === "complex";
|
|
72
72
|
return useAdvanced
|
|
73
|
-
? "llmtech/
|
|
74
|
-
: "llmtech/
|
|
73
|
+
? "llmtech/nvidia/Qwen3.8-27B-NVFP4"
|
|
74
|
+
: "llmtech/nvidia/Qwen3.8-27B-NVFP4";
|
|
75
75
|
}
|
|
76
76
|
});
|
|
77
77
|
```
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# NanoGPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 577 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
|
|
10
10
|
|
|
@@ -572,6 +572,7 @@ for await (const chunk of stream) {
|
|
|
572
572
|
| `nano-gpt/x-ai/grok-4.3` | 1.0M | | | | | | $1 | $3 |
|
|
573
573
|
| `nano-gpt/x-ai/grok-4.5` | 500K | | | | | | $2 | $6 |
|
|
574
574
|
| `nano-gpt/x-ai/grok-4.6` | 500K | | | | | | $2 | $6 |
|
|
575
|
+
| `nano-gpt/x-ai/grok-4.7` | 500K | | | | | | $2 | $5 |
|
|
575
576
|
| `nano-gpt/x-ai/grok-build-0.1` | 256K | | | | | | $1 | $2 |
|
|
576
577
|
| `nano-gpt/x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
577
578
|
| `nano-gpt/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Neuralwatt
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 29 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).
|
|
10
10
|
|
|
@@ -36,29 +36,29 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `neuralwatt/deepseek-v4-flash`
|
|
42
|
-
| `neuralwatt/deepseek-v4-flash-flex`
|
|
43
|
-
| `neuralwatt/deepseek-v4-
|
|
44
|
-
| `neuralwatt/
|
|
45
|
-
| `neuralwatt/
|
|
46
|
-
| `neuralwatt/
|
|
47
|
-
| `neuralwatt/glm-5.
|
|
48
|
-
| `neuralwatt/glm-5.
|
|
49
|
-
| `neuralwatt/glm-5.
|
|
50
|
-
| `neuralwatt/glm-5.
|
|
51
|
-
| `neuralwatt/
|
|
52
|
-
| `neuralwatt/
|
|
53
|
-
| `neuralwatt/kimi-k2.7-code`
|
|
54
|
-
| `neuralwatt/kimi-
|
|
55
|
-
| `neuralwatt/kimi-
|
|
56
|
-
| `neuralwatt/kimi-k3`
|
|
57
|
-
| `neuralwatt/
|
|
58
|
-
| `neuralwatt/
|
|
59
|
-
| `neuralwatt/
|
|
60
|
-
| `neuralwatt/qwen3.6-35b`
|
|
61
|
-
| `neuralwatt/qwen3.6-35b-
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `neuralwatt/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
42
|
+
| `neuralwatt/deepseek-v4-flash-flex` | 1.0M | | | | | | $0.09 | $0.18 |
|
|
43
|
+
| `neuralwatt/deepseek-v4-flash-speed` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
44
|
+
| `neuralwatt/deepseek-v4.1-flash` | 1.0M | | | | | | $0.15 | $0.60 |
|
|
45
|
+
| `neuralwatt/deepseek-v4.1-flash-flex` | 1.0M | | | | | | $0.10 | $0.39 |
|
|
46
|
+
| `neuralwatt/gemma-4-31b` | 262K | | | | | | $0.14 | $0.42 |
|
|
47
|
+
| `neuralwatt/glm-5.3` | 1.0M | | | | | | $1 | $5 |
|
|
48
|
+
| `neuralwatt/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
49
|
+
| `neuralwatt/glm-5.3-flash-flex` | 1.0M | | | | | | $0.10 | $0.33 |
|
|
50
|
+
| `neuralwatt/glm-5.3-flex` | 1.0M | | | | | | $0.94 | $3 |
|
|
51
|
+
| `neuralwatt/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
52
|
+
| `neuralwatt/kimi-k2.7-code-fast` | 262K | | | | | | $0.95 | $4 |
|
|
53
|
+
| `neuralwatt/kimi-k2.7-code-flex` | 262K | | | | | | $0.62 | $3 |
|
|
54
|
+
| `neuralwatt/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
55
|
+
| `neuralwatt/kimi-k3-fast` | 1.0M | | | | | | $3 | $15 |
|
|
56
|
+
| `neuralwatt/kimi-k3-flex` | 1.0M | | | | | | $2 | $10 |
|
|
57
|
+
| `neuralwatt/qwen-3.8-27b` | 262K | | | | | | $0.45 | $3 |
|
|
58
|
+
| `neuralwatt/qwen-3.8-27b-flex` | 262K | | | | | | $0.29 | $2 |
|
|
59
|
+
| `neuralwatt/qwen3.6-35b` | 131K | | | | | | $0.29 | $1 |
|
|
60
|
+
| `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
|
|
61
|
+
| `neuralwatt/qwen3.6-35b-flex` | 131K | | | | | | $0.19 | $0.75 |
|
|
62
62
|
|
|
63
63
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
64
64
|
|
|
@@ -90,7 +90,7 @@ const agent = new Agent({
|
|
|
90
90
|
model: ({ requestContext }) => {
|
|
91
91
|
const useAdvanced = requestContext.task === "complex";
|
|
92
92
|
return useAdvanced
|
|
93
|
-
? "neuralwatt/qwen3.6-35b-
|
|
93
|
+
? "neuralwatt/qwen3.6-35b-flex"
|
|
94
94
|
: "neuralwatt/deepseek-v4-flash";
|
|
95
95
|
}
|
|
96
96
|
});
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenCode Go
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 39 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/go).
|
|
10
10
|
|
|
@@ -48,6 +48,7 @@ for await (const chunk of stream) {
|
|
|
48
48
|
| `opencode-go/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
49
49
|
| `opencode-go/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
50
50
|
| `opencode-go/grok-4.6` | 500K | | | | | | $2 | $6 |
|
|
51
|
+
| `opencode-go/grok-4.7` | 500K | | | | | | $2 | $6 |
|
|
51
52
|
| `opencode-go/hy3` | 256K | | | | | | $0.14 | $0.58 |
|
|
52
53
|
| `opencode-go/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
53
54
|
| `opencode-go/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
@@ -56,6 +57,8 @@ for await (const chunk of stream) {
|
|
|
56
57
|
| `opencode-go/longcat-2.0` | 1.0M | | | | | | $0.30 | $1 |
|
|
57
58
|
| `opencode-go/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
58
59
|
| `opencode-go/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
60
|
+
| `opencode-go/mimo-v2.6-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
61
|
+
| `opencode-go/mimo-v2.6-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
59
62
|
| `opencode-go/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
|
|
60
63
|
| `opencode-go/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
|
|
61
64
|
| `opencode-go/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenCode Zen
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 105 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
|
|
10
10
|
|
|
@@ -97,6 +97,7 @@ for await (const chunk of stream) {
|
|
|
97
97
|
| `opencode/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
98
98
|
| `opencode/ling-3.0-flash-fin-free` | 262K | | | | | | — | — |
|
|
99
99
|
| `opencode/mimo-v2.5-free` | 200K | | | | | | — | — |
|
|
100
|
+
| `opencode/mimo-v2.6-flash-free` | 200K | | | | | | — | — |
|
|
100
101
|
| `opencode/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
101
102
|
| `opencode/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
|
|
102
103
|
| `opencode/minimax-m3` | 512K | | | | | | $0.30 | $1 |
|