@mastra/mcp-docs-server 1.2.26-alpha.7 → 1.2.26-alpha.9
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/gateways/netlify.md +3 -1
- package/.docs/models/gateways/openrouter.md +3 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/agentrouter.md +8 -6
- package/.docs/models/providers/digitalocean.md +1 -1
- package/.docs/models/providers/edenai.md +9 -3
- package/.docs/models/providers/kilo.md +11 -9
- package/.docs/models/providers/llmgateway-providers.md +25 -1
- package/.docs/models/providers/llmgateway.md +6 -2
- package/.docs/models/providers/nvidia.md +3 -2
- package/.docs/models/providers/ollama-cloud.md +2 -1
- package/.docs/models/providers/requesty.md +4 -5
- package/.docs/models/providers/togetherai.md +2 -1
- package/.docs/reference/cli/mastra.md +28 -0
- package/package.json +5 -5
|
@@ -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 255 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
|
|
|
@@ -163,6 +163,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
163
163
|
| `openrouter/inclusionai/ling-3.0-flash-sante:free` |
|
|
164
164
|
| `openrouter/inclusionai/ling-3.0-flash-vl` |
|
|
165
165
|
| `openrouter/inclusionai/ling-3.0-flash-vl:free` |
|
|
166
|
+
| `openrouter/inference-net/schematron-v2-small` |
|
|
167
|
+
| `openrouter/inference-net/schematron-v2-turbo` |
|
|
166
168
|
| `openrouter/mancer/weaver` |
|
|
167
169
|
| `openrouter/meta-llama/llama-3.1-70b-instruct` |
|
|
168
170
|
| `openrouter/meta-llama/llama-3.1-8b-instruct` |
|
|
@@ -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 367 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -152,6 +152,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
152
152
|
| `inclusionai/ling-3.0-flash-sante:free` |
|
|
153
153
|
| `inclusionai/ling-3.0-flash-vl` |
|
|
154
154
|
| `inclusionai/ling-3.0-flash-vl:free` |
|
|
155
|
+
| `inference-net/schematron-v2-small` |
|
|
156
|
+
| `inference-net/schematron-v2-turbo` |
|
|
155
157
|
| `kwaipilot/kat-coder-pro-v2` |
|
|
156
158
|
| `kwaipilot/kat-coder-pro-v2.5` |
|
|
157
159
|
| `liquid/lfm-2.5-2.6b:free` |
|
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 7289 models from 200 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# AgentRouter
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 5 AgentRouter models through Mastra's model router. Authentication is handled automatically using the `AGENTROUTER_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [AgentRouter documentation](https://agentrouter.org/docs/opencode.html).
|
|
10
10
|
|
|
@@ -36,11 +36,13 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `agentrouter/claude-opus-4-8`
|
|
42
|
-
| `agentrouter/claude-opus-5`
|
|
43
|
-
| `agentrouter/
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `agentrouter/claude-opus-4-8` | 1.0M | | | | | | — | — |
|
|
42
|
+
| `agentrouter/claude-opus-5` | 1.0M | | | | | | — | — |
|
|
43
|
+
| `agentrouter/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
44
|
+
| `agentrouter/glm-5.3` | 1.0M | | | | | | — | — |
|
|
45
|
+
| `agentrouter/gpt-5.6-sol` | 1.1M | | | | | | — | — |
|
|
44
46
|
|
|
45
47
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
46
48
|
|
|
@@ -74,7 +74,7 @@ for await (const chunk of stream) {
|
|
|
74
74
|
| `digitalocean/glm-5` | 64K | | | | | | $1 | $3 |
|
|
75
75
|
| `digitalocean/glm-5.1` | 164K | | | | | | $1 | $4 |
|
|
76
76
|
| `digitalocean/glm-5.2` | 262K | | | | | | $0.70 | $2 |
|
|
77
|
-
| `digitalocean/glm-5.3` | 1.0M | | | | | | $
|
|
77
|
+
| `digitalocean/glm-5.3` | 1.0M | | | | | | $0.95 | $3 |
|
|
78
78
|
| `digitalocean/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
79
79
|
| `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
|
|
80
80
|
| `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Eden AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 280 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
|
|
|
@@ -52,6 +52,10 @@ for await (const chunk of stream) {
|
|
|
52
52
|
| `edenai/amazon/google.gemma-3-4b-it@us` | 128K | | | | | | $0.04 | $0.08 |
|
|
53
53
|
| `edenai/amazon/mistral.pixtral-large-2502-v1:0` | 128K | | | | | | $2 | $6 |
|
|
54
54
|
| `edenai/amazon/mistral.pixtral-large-2502-v1:0@us` | 128K | | | | | | $2 | $6 |
|
|
55
|
+
| `edenai/amazon/mistral.voxtral-mini-3b-2507` | 128K | | | | | | $0.04 | $0.04 |
|
|
56
|
+
| `edenai/amazon/mistral.voxtral-mini-3b-2507@us` | 128K | | | | | | $0.04 | $0.04 |
|
|
57
|
+
| `edenai/amazon/mistral.voxtral-small-24b-2507` | 128K | | | | | | $0.10 | $0.30 |
|
|
58
|
+
| `edenai/amazon/mistral.voxtral-small-24b-2507@us` | 128K | | | | | | $0.10 | $0.30 |
|
|
55
59
|
| `edenai/amazon/moonshot.kimi-k2-thinking` | 128K | | | | | | $0.60 | $3 |
|
|
56
60
|
| `edenai/amazon/moonshotai.kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
|
|
57
61
|
| `edenai/amazon/openai.gpt-oss-safeguard-20b` | 128K | | | | | | $0.07 | $0.20 |
|
|
@@ -158,6 +162,7 @@ for await (const chunk of stream) {
|
|
|
158
162
|
| `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
159
163
|
| `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
160
164
|
| `edenai/groq/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
165
|
+
| `edenai/infomaniak/mistralai/Ministral-3-14B-Instruct-2512` | 100K | | | | | | $0.35 | $0.46 |
|
|
161
166
|
| `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
|
|
162
167
|
| `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
|
|
163
168
|
| `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
|
|
@@ -231,8 +236,8 @@ for await (const chunk of stream) {
|
|
|
231
236
|
| `edenai/perplexityai/sonar-deep-research` | 128K | | | | | | $2 | $8 |
|
|
232
237
|
| `edenai/perplexityai/sonar-pro` | 200K | | | | | | $3 | $15 |
|
|
233
238
|
| `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
234
|
-
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
235
|
-
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $
|
|
239
|
+
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.35 | $1 |
|
|
240
|
+
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
236
241
|
| `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
|
|
237
242
|
| `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
|
|
238
243
|
| `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
|
|
@@ -264,6 +269,7 @@ for await (const chunk of stream) {
|
|
|
264
269
|
| `edenai/tensorx/moonshotai/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
|
|
265
270
|
| `edenai/together_ai/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
266
271
|
| `edenai/together_ai/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
272
|
+
| `edenai/together_ai/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
267
273
|
| `edenai/together_ai/meta-models/Muse-Glimmer-30B` | 131K | | | | | | $0.35 | $2 |
|
|
268
274
|
| `edenai/together_ai/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
269
275
|
| `edenai/together_ai/openai/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 375 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
|
|
|
@@ -42,10 +42,10 @@ 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.
|
|
45
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.11 |
|
|
46
46
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
47
47
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
48
|
-
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $
|
|
48
|
+
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $11 |
|
|
49
49
|
| `kilo/~openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
|
|
50
50
|
| `kilo/~openai/gpt-luna-latest` | 1.1M | | | | | | $0.20 | $1 |
|
|
51
51
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
@@ -53,7 +53,7 @@ for await (const chunk of stream) {
|
|
|
53
53
|
| `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
|
|
54
54
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
55
55
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
56
|
-
| `kilo/~z-ai/glm-latest` |
|
|
56
|
+
| `kilo/~z-ai/glm-latest` | 262K | | | | | | $0.94 | $3 |
|
|
57
57
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
58
58
|
| `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
|
|
59
59
|
| `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
|
|
@@ -135,7 +135,7 @@ for await (const chunk of stream) {
|
|
|
135
135
|
| `kilo/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
|
|
136
136
|
| `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
137
137
|
| `kilo/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
138
|
-
| `kilo/google/gemma-4-26b-a4b-it` |
|
|
138
|
+
| `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.04 | $0.22 |
|
|
139
139
|
| `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.09 | $0.34 |
|
|
140
140
|
| `kilo/google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
|
|
141
141
|
| `kilo/google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
@@ -150,6 +150,8 @@ for await (const chunk of stream) {
|
|
|
150
150
|
| `kilo/inclusionai/ling-3.0-flash-sante:free` | 262K | | | | | | — | — |
|
|
151
151
|
| `kilo/inclusionai/ling-3.0-flash-vl` | 131K | | | | | | $0.06 | $0.18 |
|
|
152
152
|
| `kilo/inclusionai/ling-3.0-flash-vl:free` | 262K | | | | | | — | — |
|
|
153
|
+
| `kilo/inference-net/schematron-v2-small` | 128K | | | | | | $0.05 | $0.23 |
|
|
154
|
+
| `kilo/inference-net/schematron-v2-turbo` | 128K | | | | | | $0.03 | $0.15 |
|
|
153
155
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
154
156
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
155
157
|
| `kilo/kilo-auto/free` | 256K | | | | | | — | — |
|
|
@@ -313,7 +315,7 @@ for await (const chunk of stream) {
|
|
|
313
315
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
314
316
|
| `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
|
|
315
317
|
| `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
|
|
316
|
-
| `kilo/qwen/qwen3-30b-a3b-instruct-2507` |
|
|
318
|
+
| `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.13 | $0.52 |
|
|
317
319
|
| `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
|
|
318
320
|
| `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
|
|
319
321
|
| `kilo/qwen/qwen3-8b` | 131K | | | | | | $0.12 | $0.46 |
|
|
@@ -350,7 +352,7 @@ for await (const chunk of stream) {
|
|
|
350
352
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
351
353
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
352
354
|
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
353
|
-
| `kilo/qwen/qwen3.8-27b` |
|
|
355
|
+
| `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.42 | $3 |
|
|
354
356
|
| `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
355
357
|
| `kilo/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
356
358
|
| `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
|
|
@@ -376,13 +378,13 @@ for await (const chunk of stream) {
|
|
|
376
378
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
377
379
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
378
380
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
379
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
381
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
380
382
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
381
383
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
382
384
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
383
385
|
| `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
|
|
384
386
|
| `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
|
|
385
|
-
| `kilo/thinkingmachines/inkling` |
|
|
387
|
+
| `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
|
|
386
388
|
| `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
|
|
387
389
|
| `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
|
|
388
390
|
| `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.35 | $0.65 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 401 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
|
|
|
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
|
|
|
43
43
|
| `llmgateway-providers/alibaba/glm-5` | 203K | | | | | | $0.57 | $3 |
|
|
44
44
|
| `llmgateway-providers/alibaba/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
45
45
|
| `llmgateway-providers/alibaba/kimi-k2.5` | 262K | | | | | | $0.57 | $3 |
|
|
46
|
+
| `llmgateway-providers/alibaba/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
46
47
|
| `llmgateway-providers/alibaba/qwen-coder-plus` | 131K | | | | | | $0.50 | $1 |
|
|
47
48
|
| `llmgateway-providers/alibaba/qwen-flash` | 1.0M | | | | | | $0.05 | $0.40 |
|
|
48
49
|
| `llmgateway-providers/alibaba/qwen-max` | 33K | | | | | | $2 | $6 |
|
|
@@ -99,6 +100,7 @@ for await (const chunk of stream) {
|
|
|
99
100
|
| `llmgateway-providers/aws-mantle/gpt-5.6-luna` | 279K | | | | | | $0.22 | $1 |
|
|
100
101
|
| `llmgateway-providers/aws-mantle/gpt-5.6-sol` | 279K | | | | | | $6 | $33 |
|
|
101
102
|
| `llmgateway-providers/aws-mantle/gpt-5.6-terra` | 279K | | | | | | $2 | $13 |
|
|
103
|
+
| `llmgateway-providers/aws-mantle/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
102
104
|
| `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
|
|
103
105
|
| `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
|
|
104
106
|
| `llmgateway-providers/azure-ai-foundry/grok-4-3` | 20K | | | | | | $1 | $3 |
|
|
@@ -174,6 +176,7 @@ for await (const chunk of stream) {
|
|
|
174
176
|
| `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
|
|
175
177
|
| `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
176
178
|
| `llmgateway-providers/deepinfra/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
|
|
179
|
+
| `llmgateway-providers/deepinfra/deepseek-v4.1-flash` | 1.0M | | | | | | $0.20 | $0.60 |
|
|
177
180
|
| `llmgateway-providers/deepinfra/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
|
|
178
181
|
| `llmgateway-providers/deepinfra/gemma-4-31b-it` | 262K | | | | | | $0.13 | $0.38 |
|
|
179
182
|
| `llmgateway-providers/deepinfra/glm-5.1` | 198K | | | | | | $1 | $4 |
|
|
@@ -198,6 +201,7 @@ for await (const chunk of stream) {
|
|
|
198
201
|
| `llmgateway-providers/embercloud/qwen3-coder-next` | 262K | | | | | | $0.11 | $0.68 |
|
|
199
202
|
| `llmgateway-providers/fireworks/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
200
203
|
| `llmgateway-providers/fireworks/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
204
|
+
| `llmgateway-providers/fireworks/deepseek-v4.1-flash` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
201
205
|
| `llmgateway-providers/fireworks/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
202
206
|
| `llmgateway-providers/fireworks/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
|
|
203
207
|
| `llmgateway-providers/gonka24/deepseek-v4-flash` | 390K | | | | | | $0.05 | $0.10 |
|
|
@@ -257,6 +261,7 @@ for await (const chunk of stream) {
|
|
|
257
261
|
| `llmgateway-providers/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
258
262
|
| `llmgateway-providers/novita/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
|
|
259
263
|
| `llmgateway-providers/novita/deepseek-v4-flash` | 1.1M | | | | | | $0.14 | $0.28 |
|
|
264
|
+
| `llmgateway-providers/novita/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
260
265
|
| `llmgateway-providers/novita/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
|
|
261
266
|
| `llmgateway-providers/novita/gemma-4-26b-a4b-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
262
267
|
| `llmgateway-providers/novita/gemma-4-31b-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
@@ -338,6 +343,7 @@ for await (const chunk of stream) {
|
|
|
338
343
|
| `llmgateway-providers/perplexity/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
339
344
|
| `llmgateway-providers/quartz/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
340
345
|
| `llmgateway-providers/ranoai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
346
|
+
| `llmgateway-providers/runpod/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
341
347
|
| `llmgateway-providers/runware/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.15 |
|
|
342
348
|
| `llmgateway-providers/runware/deepseek-v4-pro` | 1.0M | | | | | | $0.96 | $2 |
|
|
343
349
|
| `llmgateway-providers/runware/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
|
|
@@ -362,8 +368,26 @@ for await (const chunk of stream) {
|
|
|
362
368
|
| `llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct` | 131K | | | | | | $0.53 | $2 |
|
|
363
369
|
| `llmgateway-providers/scx-ai/minimax-m2.7` | 197K | | | | | | $0.48 | $2 |
|
|
364
370
|
| `llmgateway-providers/scx-ai/qwen3-32b` | 33K | | | | | | $0.36 | $0.87 |
|
|
371
|
+
| `llmgateway-providers/tencent/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
372
|
+
| `llmgateway-providers/tencent/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
373
|
+
| `llmgateway-providers/tencent/glm-5` | 200K | | | | | | $1 | $3 |
|
|
374
|
+
| `llmgateway-providers/tencent/glm-5-turbo` | 200K | | | | | | $1 | $4 |
|
|
375
|
+
| `llmgateway-providers/tencent/glm-5.1` | 200K | | | | | | $1 | $4 |
|
|
376
|
+
| `llmgateway-providers/tencent/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
377
|
+
| `llmgateway-providers/tencent/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
|
|
378
|
+
| `llmgateway-providers/tencent/hy-mt2-plus` | 8K | | | | | | $0.07 | $0.29 |
|
|
379
|
+
| `llmgateway-providers/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
380
|
+
| `llmgateway-providers/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
381
|
+
| `llmgateway-providers/tencent/kimi-k2.6` | 262K | | | | | | $0.86 | $4 |
|
|
382
|
+
| `llmgateway-providers/tencent/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
383
|
+
| `llmgateway-providers/tencent/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
|
|
384
|
+
| `llmgateway-providers/tencent/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
385
|
+
| `llmgateway-providers/tencent/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
386
|
+
| `llmgateway-providers/tencent/minimax-m2.7` | 200K | | | | | | $0.30 | $1 |
|
|
387
|
+
| `llmgateway-providers/tencent/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
|
|
365
388
|
| `llmgateway-providers/together-ai/deepseek-v4-flash` | 164K | | | | | | $0.14 | $0.28 |
|
|
366
389
|
| `llmgateway-providers/together-ai/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
390
|
+
| `llmgateway-providers/together-ai/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
367
391
|
| `llmgateway-providers/together-ai/gemma-4-31b-it` | 262K | | | | | | $0.39 | $0.97 |
|
|
368
392
|
| `llmgateway-providers/together-ai/glm-4.7` | 203K | | | | | | $0.45 | $2 |
|
|
369
393
|
| `llmgateway-providers/together-ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 192 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
|
|
|
@@ -90,11 +90,13 @@ for await (const chunk of stream) {
|
|
|
90
90
|
| `llmgateway/glm-4.7-flash` | 200K | | | | | | $0.06 | $0.40 |
|
|
91
91
|
| `llmgateway/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.40 |
|
|
92
92
|
| `llmgateway/glm-5` | 203K | | | | | | $0.72 | $2 |
|
|
93
|
+
| `llmgateway/glm-5-turbo` | 200K | | | | | | $1 | $4 |
|
|
93
94
|
| `llmgateway/glm-5.1` | 205K | | | | | | $0.93 | $3 |
|
|
94
95
|
| `llmgateway/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
|
|
95
96
|
| `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
96
97
|
| `llmgateway/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
97
98
|
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.09 | $0.25 |
|
|
99
|
+
| `llmgateway/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
|
|
98
100
|
| `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
99
101
|
| `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
100
102
|
| `llmgateway/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
|
|
@@ -139,7 +141,9 @@ for await (const chunk of stream) {
|
|
|
139
141
|
| `llmgateway/grok-4-5` | 500K | | | | | | $2 | $6 |
|
|
140
142
|
| `llmgateway/grok-4-6` | 500K | | | | | | $2 | $6 |
|
|
141
143
|
| `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
142
|
-
| `llmgateway/
|
|
144
|
+
| `llmgateway/hy-mt2-plus` | 8K | | | | | | $0.07 | $0.29 |
|
|
145
|
+
| `llmgateway/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
146
|
+
| `llmgateway/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
143
147
|
| `llmgateway/kimi-k2` | 256K | | | | | | $0.57 | $2 |
|
|
144
148
|
| `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
145
149
|
| `llmgateway/kimi-k2.5` | 262K | | | | | | $0.41 | $2 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Nvidia
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 104 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
|
|
10
10
|
|
|
@@ -139,6 +139,7 @@ for await (const chunk of stream) {
|
|
|
139
139
|
| `nvidia/thinkingmachines/inkling` | 1.0M | | | | | | — | — |
|
|
140
140
|
| `nvidia/upstage/solar-10.7b-instruct` | 128K | | | | | | — | — |
|
|
141
141
|
| `nvidia/z-ai/glm-5.2` | 1.0M | | | | | | — | — |
|
|
142
|
+
| `nvidia/z-ai/glm-5.3-flash` | 1.0M | | | | | | — | — |
|
|
142
143
|
|
|
143
144
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
144
145
|
|
|
@@ -170,7 +171,7 @@ const agent = new Agent({
|
|
|
170
171
|
model: ({ requestContext }) => {
|
|
171
172
|
const useAdvanced = requestContext.task === "complex";
|
|
172
173
|
return useAdvanced
|
|
173
|
-
? "nvidia/z-ai/glm-5.
|
|
174
|
+
? "nvidia/z-ai/glm-5.3-flash"
|
|
174
175
|
: "nvidia/abacusai/dracarys-llama-3.1-70b-instruct";
|
|
175
176
|
}
|
|
176
177
|
});
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Ollama Cloud
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 24 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
|
|
10
10
|
|
|
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `ollama-cloud/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
42
42
|
| `ollama-cloud/deepseek-v4-flash:0731` | 1.0M | | | | | | — | — |
|
|
43
43
|
| `ollama-cloud/deepseek-v4-pro` | 1.0M | | | | | | — | — |
|
|
44
|
+
| `ollama-cloud/deepseek-v4-pro:0813` | 1.0M | | | | | | — | — |
|
|
44
45
|
| `ollama-cloud/deepseek-v4.1-flash` | 1.0M | | | | | | — | — |
|
|
45
46
|
| `ollama-cloud/gemma4:31b` | 262K | | | | | | — | — |
|
|
46
47
|
| `ollama-cloud/glm-5.1` | 203K | | | | | | — | — |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Requesty
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 153 Requesty models through Mastra's model router. Authentication is handled automatically using the `REQUESTY_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Requesty documentation](https://requesty.ai/solution/llm-routing/models).
|
|
10
10
|
|
|
@@ -69,7 +69,8 @@ for await (const chunk of stream) {
|
|
|
69
69
|
| `requesty/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
70
70
|
| `requesty/deepseek-v4-pro-0813@eu` | 1.0M | | | | | | $2 | $4 |
|
|
71
71
|
| `requesty/deepseek-v4-pro@eu` | 1.0M | | | | | | $2 | $4 |
|
|
72
|
-
| `requesty/deepseek-v4.1-flash` | 1.0M | | | | | | $0.
|
|
72
|
+
| `requesty/deepseek-v4.1-flash` | 1.0M | | | | | | $0.50 | $2 |
|
|
73
|
+
| `requesty/deepseek-v4.1-flash@eu` | 1.0M | | | | | | $0.50 | $2 |
|
|
73
74
|
| `requesty/devstral-latest` | 256K | | | | | | $0.44 | $2 |
|
|
74
75
|
| `requesty/devstral-latest@eu` | 256K | | | | | | $0.44 | $2 |
|
|
75
76
|
| `requesty/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
@@ -190,8 +191,6 @@ for await (const chunk of stream) {
|
|
|
190
191
|
| `requesty/seed-2.0-mini` | 256K | | | | | | $0.10 | $0.40 |
|
|
191
192
|
| `requesty/seed-2.0-pro` | 256K | | | | | | $0.50 | $3 |
|
|
192
193
|
| `requesty/step-3.7-flash` | 262K | | | | | | $0.20 | $1 |
|
|
193
|
-
| `requesty/thinkingcap-qwen3.6-27b` | 262K | | | | | | $0.40 | $3 |
|
|
194
|
-
| `requesty/thinkingcap-qwen3.6-27b@eu` | 262K | | | | | | $0.40 | $3 |
|
|
195
194
|
|
|
196
195
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
197
196
|
|
|
@@ -223,7 +222,7 @@ const agent = new Agent({
|
|
|
223
222
|
model: ({ requestContext }) => {
|
|
224
223
|
const useAdvanced = requestContext.task === "complex";
|
|
225
224
|
return useAdvanced
|
|
226
|
-
? "requesty/
|
|
225
|
+
? "requesty/step-3.7-flash"
|
|
227
226
|
: "requesty/claude-fable-5";
|
|
228
227
|
}
|
|
229
228
|
});
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Together AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 39 Together AI models through Mastra's model router. Authentication is handled automatically using the `TOGETHER_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Together AI documentation](https://docs.together.ai/docs/serverless-models).
|
|
10
10
|
|
|
@@ -40,6 +40,7 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| `togetherai/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
41
41
|
| `togetherai/deepseek-ai/DeepSeek-V4-Pro` | 512K | | | | | | $2 | $3 |
|
|
42
42
|
| `togetherai/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
43
|
+
| `togetherai/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
43
44
|
| `togetherai/google/gemma-3n-E4B-it` | 33K | | | | | | $0.06 | $0.12 |
|
|
44
45
|
| `togetherai/google/gemma-4-31B-it` | 262K | | | | | | $0.39 | $0.97 |
|
|
45
46
|
| `togetherai/LiquidAI/LFM2-24B-A2B` | 33K | | | | | | $0.03 | $0.12 |
|
|
@@ -1482,6 +1482,34 @@ mastra api trace list '{"page":0,"perPage":20}' --verbose
|
|
|
1482
1482
|
|
|
1483
1483
|
`trace list` returns lightweight root span records by default so you can page through traces without fetching large input, output, attributes, or metadata payloads. Pass `--verbose` to fetch the full root span records.
|
|
1484
1484
|
|
|
1485
|
+
#### `mastra api trace query`
|
|
1486
|
+
|
|
1487
|
+
Queries completed observability traces with recursive predicates over trace and related span or score fields. The inline JSON input is required. Like other observability commands, it targets `https://observability.mastra.ai` by default.
|
|
1488
|
+
|
|
1489
|
+
```bash
|
|
1490
|
+
mastra api trace query <input>
|
|
1491
|
+
mastra api trace query '{"timeRange":{"from":"2026-08-01T00:00:00.000Z","to":"2026-08-08T00:00:00.000Z"}}'
|
|
1492
|
+
```
|
|
1493
|
+
|
|
1494
|
+
Inspect the target server's exact request contract before constructing a query:
|
|
1495
|
+
|
|
1496
|
+
```bash
|
|
1497
|
+
mastra api trace query --schema
|
|
1498
|
+
```
|
|
1499
|
+
|
|
1500
|
+
The response remains nested under `data` to preserve cursor pagination:
|
|
1501
|
+
|
|
1502
|
+
```json
|
|
1503
|
+
{
|
|
1504
|
+
"data": {
|
|
1505
|
+
"traces": [],
|
|
1506
|
+
"page": { "next": "opaque-cursor" }
|
|
1507
|
+
}
|
|
1508
|
+
}
|
|
1509
|
+
```
|
|
1510
|
+
|
|
1511
|
+
Pass a non-null `page.next` value back as `page.after` in the next query. See [Advanced trace queries](https://mastra.ai/reference/observability/tracing/trace-query) for supported fields and operators, recursive predicates, limits, pagination, and errors.
|
|
1512
|
+
|
|
1485
1513
|
#### `mastra api trace get`
|
|
1486
1514
|
|
|
1487
1515
|
Gets a lightweight timeline for one observability trace without fetching full span input, output, attributes, or metadata payloads. Pass `--verbose` to fetch the full trace payload.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/mcp-docs-server",
|
|
3
|
-
"version": "1.2.26-alpha.
|
|
3
|
+
"version": "1.2.26-alpha.9",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -27,8 +27,8 @@
|
|
|
27
27
|
"jsdom": "^26.1.0",
|
|
28
28
|
"local-pkg": "^1.1.2",
|
|
29
29
|
"zod": "^4.4.3",
|
|
30
|
-
"@mastra/
|
|
31
|
-
"@mastra/
|
|
30
|
+
"@mastra/mcp": "^1.17.4-alpha.0",
|
|
31
|
+
"@mastra/core": "1.67.0-alpha.3"
|
|
32
32
|
},
|
|
33
33
|
"devDependencies": {
|
|
34
34
|
"@hono/node-server": "^2.0.0",
|
|
@@ -45,8 +45,8 @@
|
|
|
45
45
|
"typescript": "^7.0.2",
|
|
46
46
|
"vitest": "4.1.10",
|
|
47
47
|
"@internal/types-builder": "0.0.107",
|
|
48
|
-
"@
|
|
49
|
-
"@
|
|
48
|
+
"@internal/lint": "0.0.132",
|
|
49
|
+
"@mastra/core": "1.67.0-alpha.3"
|
|
50
50
|
},
|
|
51
51
|
"homepage": "https://mastra.ai",
|
|
52
52
|
"repository": {
|