@mastra/mcp-docs-server 1.2.21-alpha.3 → 1.2.21-alpha.5

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.
Files changed (33) hide show
  1. package/.docs/docs/deployment/cloud-providers.md +1 -0
  2. package/.docs/docs/deployment/overview.md +1 -0
  3. package/.docs/integrations/deploy/neon.md +217 -0
  4. package/.docs/integrations.md +1 -0
  5. package/.docs/models/environment-variables.md +1 -0
  6. package/.docs/models/gateways/netlify.md +2 -3
  7. package/.docs/models/gateways/openrouter.md +2 -3
  8. package/.docs/models/gateways/vercel.md +3 -1
  9. package/.docs/models/index.md +1 -1
  10. package/.docs/models/providers/digitalocean.md +12 -11
  11. package/.docs/models/providers/edenai.md +6 -3
  12. package/.docs/models/providers/fireworks-ai.md +1 -7
  13. package/.docs/models/providers/inceptron.md +1 -1
  14. package/.docs/models/providers/kenari.md +23 -2
  15. package/.docs/models/providers/kilo.md +7 -8
  16. package/.docs/models/providers/llmgateway-providers.md +2 -1
  17. package/.docs/models/providers/modal.md +7 -5
  18. package/.docs/models/providers/nano-gpt.md +6 -7
  19. package/.docs/models/providers/neuralwatt.md +26 -31
  20. package/.docs/models/providers/nvidia.md +2 -1
  21. package/.docs/models/providers/ofox.md +2 -1
  22. package/.docs/models/providers/ollama-cloud.md +2 -1
  23. package/.docs/models/providers/orcarouter.md +58 -23
  24. package/.docs/models/providers/requesty.md +123 -122
  25. package/.docs/models/providers/runinfra.md +4 -2
  26. package/.docs/models/providers/scnet-token-plan.md +2 -1
  27. package/.docs/models/providers/togetherai.md +3 -2
  28. package/.docs/models/providers/tokengo.md +87 -0
  29. package/.docs/models/providers/vivgrid.md +2 -1
  30. package/.docs/models/providers/wandb.md +3 -2
  31. package/.docs/models/providers.md +1 -0
  32. package/CHANGELOG.md +14 -0
  33. package/package.json +4 -4
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
6
6
 
7
- Access 366 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
7
+ Access 365 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
 
@@ -105,7 +105,7 @@ for await (const chunk of stream) {
105
105
  | `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
106
106
  | `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
107
107
  | `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
108
- | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
108
+ | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.44 | $1 |
109
109
  | `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
110
110
  | `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
111
111
  | `kilo/dots-studio/dots-3-note-preview:free` | 512K | | | | | | — | — |
@@ -142,6 +142,7 @@ for await (const chunk of stream) {
142
142
  | `kilo/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
143
143
  | `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
144
144
  | `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
145
+ | `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
145
146
  | `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
146
147
  | `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
147
148
  | `kilo/kilo-auto/free` | 256K | | | | | | — | — |
@@ -159,7 +160,7 @@ for await (const chunk of stream) {
159
160
  | `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
160
161
  | `kilo/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.05 | $0.33 |
161
162
  | `kilo/meta-llama/llama-3.3-70b-instruct` | 128K | | | | | | $0.10 | $0.32 |
162
- | `kilo/meta-llama/llama-4-maverick` | 1.0M | | | | | | $0.20 | $0.70 |
163
+ | `kilo/meta-llama/llama-4-maverick` | 1.0M | | | | | | $0.20 | $0.80 |
163
164
  | `kilo/meta-llama/llama-4-scout` | 131K | | | | | | $0.10 | $0.30 |
164
165
  | `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
165
166
  | `kilo/meta/muse-glimmer-30b` | 131K | | | | | | $0.30 | $1 |
@@ -182,7 +183,6 @@ for await (const chunk of stream) {
182
183
  | `kilo/mistralai/devstral-2512` | 262K | | | | | | $0.44 | $2 |
183
184
  | `kilo/mistralai/ministral-14b-2512` | 262K | | | | | | $0.20 | $0.20 |
184
185
  | `kilo/mistralai/ministral-3b-2512` | 131K | | | | | | $0.10 | $0.10 |
185
- | `kilo/mistralai/ministral-8b` | 128K | | | | | | $0.11 | $0.11 |
186
186
  | `kilo/mistralai/ministral-8b-2512` | 262K | | | | | | $0.15 | $0.15 |
187
187
  | `kilo/mistralai/mistral-large` | 128K | | | | | | $2 | $6 |
188
188
  | `kilo/mistralai/mistral-large-2407` | 131K | | | | | | $2 | $6 |
@@ -217,7 +217,7 @@ for await (const chunk of stream) {
217
217
  | `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
218
218
  | `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.09 | $0.40 |
219
219
  | `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
220
- | `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 512K | | | | | | $0.50 | $2 |
220
+ | `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 262K | | | | | | $0.50 | $2 |
221
221
  | `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
222
222
  | `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
223
223
  | `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.08 | $0.20 |
@@ -343,7 +343,7 @@ for await (const chunk of stream) {
343
343
  | `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
344
344
  | `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
345
345
  | `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
346
- | `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
346
+ | `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.42 | $3 |
347
347
  | `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
348
348
  | `kilo/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
349
349
  | `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
@@ -371,7 +371,6 @@ for await (const chunk of stream) {
371
371
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
372
372
  | `kilo/tencent/hy3:free` | 262K | | | | | | — | — |
373
373
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
374
- | `kilo/thedrummer/rocinante-12b` | 66K | | | | | | $0.25 | $0.50 |
375
374
  | `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
376
375
  | `kilo/thedrummer/unslopnemo-12b` | 33K | | | | | | $0.40 | $0.40 |
377
376
  | `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
@@ -402,7 +401,7 @@ for await (const chunk of stream) {
402
401
  | `kilo/z-ai/glm-5.1` | 203K | | | | | | $1 | $4 |
403
402
  | `kilo/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
404
403
  | `kilo/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
405
- | `kilo/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
404
+ | `kilo/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
406
405
  | `kilo/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
407
406
 
408
407
  ## Advanced configuration
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
6
6
 
7
- Access 381 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 382 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
 
@@ -223,6 +223,7 @@ for await (const chunk of stream) {
223
223
  | `llmgateway-providers/iceberg/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
224
224
  | `llmgateway-providers/iceberg/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
225
225
  | `llmgateway-providers/iceberg/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
226
+ | `llmgateway-providers/iceberg/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
226
227
  | `llmgateway-providers/inference.net/llama-3.2-11b-instruct` | 128K | | | | | | $0.07 | $0.33 |
227
228
  | `llmgateway-providers/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
228
229
  | `llmgateway-providers/meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Modal logo](https://models.dev/logos/modal.svg)Modal
6
6
 
7
- Access 2 Modal models through Mastra's model router. Authentication is handled automatically using the `MODAL_PROXY_TOKEN` environment variable.
7
+ Access 4 Modal models through Mastra's model router. Authentication is handled automatically using the `MODAL_PROXY_TOKEN` environment variable.
8
8
 
9
9
  Learn more in the [Modal documentation](https://modal.com/docs/guide/endpoints).
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: "modal/moonshotai/Kimi-K3"
22
+ model: "modal/Qwen/Qwen3.8-2.4T-A95B"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -39,7 +39,9 @@ for await (const chunk of stream) {
39
39
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
40
  | -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
41
  | `modal/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
42
+ | `modal/Qwen/Qwen3.8-2.4T-A95B` | 1.0M | | | | | | $2 | $6 |
42
43
  | `modal/thinkingmachines/Inkling-NVFP4` | 1.0M | | | | | | $1 | $5 |
44
+ | `modal/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.45 | $2 |
43
45
 
44
46
  ## Advanced configuration
45
47
 
@@ -51,7 +53,7 @@ const agent = new Agent({
51
53
  name: "custom-agent",
52
54
  model: {
53
55
  url: "https://inference.us-west.modal.direct/v1",
54
- id: "modal/moonshotai/Kimi-K3",
56
+ id: "modal/Qwen/Qwen3.8-2.4T-A95B",
55
57
  apiKey: process.env.MODAL_PROXY_TOKEN,
56
58
  headers: {
57
59
  "X-Custom-Header": "value"
@@ -69,8 +71,8 @@ const agent = new Agent({
69
71
  model: ({ requestContext }) => {
70
72
  const useAdvanced = requestContext.task === "complex";
71
73
  return useAdvanced
72
- ? "modal/thinkingmachines/Inkling-NVFP4"
73
- : "modal/moonshotai/Kimi-K3";
74
+ ? "modal/zai-org/GLM-5.3-Flash"
75
+ : "modal/Qwen/Qwen3.8-2.4T-A95B";
74
76
  }
75
77
  });
76
78
  ```
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 612 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 611 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
 
@@ -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: "nano-gpt/Baichuan-M2"
22
+ model: "nano-gpt/Baichuan4-Air"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -82,7 +82,6 @@ for await (const chunk of stream) {
82
82
  | `nano-gpt/azure-gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
83
83
  | `nano-gpt/azure-o1` | 200K | | | | | | $15 | $60 |
84
84
  | `nano-gpt/azure-o3-mini` | 200K | | | | | | $1 | $4 |
85
- | `nano-gpt/Baichuan-M2` | 33K | | | | | | $16 | $16 |
86
85
  | `nano-gpt/Baichuan4-Air` | 33K | | | | | | $0.16 | $0.16 |
87
86
  | `nano-gpt/Baichuan4-Turbo` | 128K | | | | | | $2 | $2 |
88
87
  | `nano-gpt/baseten/Kimi-K2-Instruct-FP4` | 128K | | | | | | $0.40 | $2 |
@@ -154,7 +153,7 @@ for await (const chunk of stream) {
154
153
  | `nano-gpt/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
155
154
  | `nano-gpt/deepseek/deepseek-v4-flash-0731:thinking` | 1.0M | | | | | | $0.14 | $0.28 |
156
155
  | `nano-gpt/deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.14 | $0.28 |
157
- | `nano-gpt/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
156
+ | `nano-gpt/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.44 | $1 |
158
157
  | `nano-gpt/deepseek/deepseek-v4-flash:thinking` | 1.0M | | | | | | $0.14 | $0.28 |
159
158
  | `nano-gpt/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $2 |
160
159
  | `nano-gpt/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
@@ -440,7 +439,6 @@ for await (const chunk of stream) {
440
439
  | `nano-gpt/phi-4-mini-instruct` | 128K | | | | | | $0.17 | $0.68 |
441
440
  | `nano-gpt/phi-4-multimodal-instruct` | 128K | | | | | | $0.07 | $0.11 |
442
441
  | `nano-gpt/pokee-isaac` | 10.0M | | | | | | $0.15 | $1 |
443
- | `nano-gpt/poolside/laguna-m.1` | 262K | | | | | | $0.20 | $0.40 |
444
442
  | `nano-gpt/poolside/laguna-s-2.1` | 1.0M | | | | | | $0.10 | $0.20 |
445
443
  | `nano-gpt/poolside/laguna-s-2.1:thinking` | 1.0M | | | | | | $0.10 | $0.20 |
446
444
  | `nano-gpt/qvq-max` | 128K | | | | | | $1 | $5 |
@@ -619,6 +617,7 @@ for await (const chunk of stream) {
619
617
  | `nano-gpt/z-ai/glm-4.6:thinking` | 200K | | | | | | $0.35 | $1 |
620
618
  | `nano-gpt/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
621
619
  | `nano-gpt/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
620
+ | `nano-gpt/z-ai/glm-5.3-flash-uncensored` | 262K | | | | | | $0.13 | $0.50 |
622
621
  | `nano-gpt/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
623
622
  | `nano-gpt/z-ai/glm-5v-turbo:thinking` | 203K | | | | | | $1 | $4 |
624
623
  | `nano-gpt/zai-org/glm-4.5` | 128K | | | | | | $0.30 | $1 |
@@ -661,7 +660,7 @@ const agent = new Agent({
661
660
  name: "custom-agent",
662
661
  model: {
663
662
  url: "https://nano-gpt.com/api/v1",
664
- id: "nano-gpt/Baichuan-M2",
663
+ id: "nano-gpt/Baichuan4-Air",
665
664
  apiKey: process.env.NANO_GPT_API_KEY,
666
665
  headers: {
667
666
  "X-Custom-Header": "value"
@@ -680,7 +679,7 @@ const agent = new Agent({
680
679
  const useAdvanced = requestContext.task === "complex";
681
680
  return useAdvanced
682
681
  ? "nano-gpt/zai-org/glm-latest"
683
- : "nano-gpt/Baichuan-M2";
682
+ : "nano-gpt/Baichuan4-Air";
684
683
  }
685
684
  });
686
685
  ```
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Neuralwatt logo](https://models.dev/logos/neuralwatt.svg)Neuralwatt
6
6
 
7
- Access 25 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
7
+ Access 20 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
 
@@ -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: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8"
22
+ model: "neuralwatt/deepseek-v4-flash"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -36,33 +36,28 @@ for await (const chunk of stream) {
36
36
 
37
37
  ## Models
38
38
 
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-pro` | 1.0M | | | | | | $1 | $3 |
44
- | `neuralwatt/gemma-4-31b` | 262K | | | | | | $0.14 | $0.42 |
45
- | `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
46
- | `neuralwatt/glm-5.2-fast` | 1.0M | | | | | | $1 | $5 |
47
- | `neuralwatt/glm-5.2-flex` | 1.0M | | | | | | $0.72 | $2 |
48
- | `neuralwatt/glm-5.2-short` | 200K | | | | | | $1 | $5 |
49
- | `neuralwatt/glm-5.2-short-fast` | 200K | | | | | | $1 | $5 |
50
- | `neuralwatt/glm-5.2-short-fast-flex` | 200K | | | | | | $0.72 | $2 |
51
- | `neuralwatt/glm-5.2-short-flex` | 200K | | | | | | $0.72 | $2 |
52
- | `neuralwatt/kimi-k2.5-fast` | 262K | | | | | | $0.52 | $3 |
53
- | `neuralwatt/kimi-k2.6-fast` | 262K | | | | | | $0.69 | $3 |
54
- | `neuralwatt/kimi-k2.6-flex` | 262K | | | | | | $0.34 | $2 |
55
- | `neuralwatt/kimi-k2.7-code-flex` | 262K | | | | | | $0.47 | $2 |
56
- | `neuralwatt/kimi-k3` | 1.0M | | | | | | $3 | $15 |
57
- | `neuralwatt/kimi-k3-fast` | 1.0M | | | | | | $3 | $15 |
58
- | `neuralwatt/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.52 | $3 |
59
- | `neuralwatt/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.69 | $3 |
60
- | `neuralwatt/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
61
- | `neuralwatt/qwen-3.8-27b` | 262K | | | | | | $0.45 | $3 |
62
- | `neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8` | 262K | | | | | | $0.69 | $4 |
63
- | `neuralwatt/Qwen/Qwen3.6-35B-A3B` | 131K | | | | | | $0.29 | $1 |
64
- | `neuralwatt/qwen3.5-397b-fast` | 262K | | | | | | $0.69 | $4 |
65
- | `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
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-pro` | 1.0M | | | | | | $1 | $3 |
44
+ | `neuralwatt/gemma-4-31b` | 262K | | | | | | $0.14 | $0.42 |
45
+ | `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
46
+ | `neuralwatt/glm-5.2-fast` | 1.0M | | | | | | $1 | $5 |
47
+ | `neuralwatt/glm-5.2-flex` | 1.0M | | | | | | $0.94 | $3 |
48
+ | `neuralwatt/glm-5.2-short` | 200K | | | | | | $1 | $5 |
49
+ | `neuralwatt/glm-5.2-short-fast` | 200K | | | | | | $1 | $5 |
50
+ | `neuralwatt/glm-5.2-short-fast-flex` | 200K | | | | | | $0.94 | $3 |
51
+ | `neuralwatt/glm-5.2-short-flex` | 200K | | | | | | $0.94 | $3 |
52
+ | `neuralwatt/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
53
+ | `neuralwatt/kimi-k2.7-code-fast` | 262K | | | | | | $0.95 | $4 |
54
+ | `neuralwatt/kimi-k2.7-code-flex` | 262K | | | | | | $0.62 | $3 |
55
+ | `neuralwatt/kimi-k3` | 1.0M | | | | | | $3 | $15 |
56
+ | `neuralwatt/kimi-k3-fast` | 1.0M | | | | | | $3 | $15 |
57
+ | `neuralwatt/kimi-k3-flex` | 1.0M | | | | | | $2 | $10 |
58
+ | `neuralwatt/qwen-3.8-27b` | 262K | | | | | | $0.45 | $3 |
59
+ | `neuralwatt/qwen3.6-35b` | 131K | | | | | | $0.29 | $1 |
60
+ | `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
66
61
 
67
62
  ## Advanced configuration
68
63
 
@@ -74,7 +69,7 @@ const agent = new Agent({
74
69
  name: "custom-agent",
75
70
  model: {
76
71
  url: "https://api.neuralwatt.com/v1",
77
- id: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8",
72
+ id: "neuralwatt/deepseek-v4-flash",
78
73
  apiKey: process.env.NEURALWATT_API_KEY,
79
74
  headers: {
80
75
  "X-Custom-Header": "value"
@@ -93,7 +88,7 @@ const agent = new Agent({
93
88
  const useAdvanced = requestContext.task === "complex";
94
89
  return useAdvanced
95
90
  ? "neuralwatt/qwen3.6-35b-fast"
96
- : "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8";
91
+ : "neuralwatt/deepseek-v4-flash";
97
92
  }
98
93
  });
99
94
  ```
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Nvidia logo](https://models.dev/logos/nvidia.svg)Nvidia
6
6
 
7
- Access 102 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
7
+ Access 103 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
 
@@ -48,6 +48,7 @@ for await (const chunk of stream) {
48
48
  | `nvidia/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
49
49
  | `nvidia/deepseek-ai/deepseek-v4-flash-0731` | 1.0M | | | | | | — | — |
50
50
  | `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
51
+ | `nvidia/deepseek-ai/deepseek-v4-pro-0813` | 1.0M | | | | | | — | — |
51
52
  | `nvidia/google/gemma-2-2b-it` | 128K | | | | | | — | — |
52
53
  | `nvidia/google/gemma-3-12b-it` | 131K | | | | | | — | — |
53
54
  | `nvidia/google/gemma-3-4b-it` | 131K | | | | | | — | — |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Ofox logo](https://models.dev/logos/ofox.svg)Ofox
6
6
 
7
- Access 111 Ofox models through Mastra's model router. Authentication is handled automatically using the `OFOX_API_KEY` environment variable.
7
+ Access 112 Ofox models through Mastra's model router. Authentication is handled automatically using the `OFOX_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Ofox documentation](https://ofox.ai/docs).
10
10
 
@@ -148,6 +148,7 @@ for await (const chunk of stream) {
148
148
  | `ofox/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
149
149
  | `ofox/z-ai/glm-5.2` | 1.0M | | | | | | $0.98 | $3 |
150
150
  | `ofox/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
151
+ | `ofox/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
151
152
  | `ofox/z-ai/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
152
153
 
153
154
  ## Advanced configuration
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Ollama Cloud logo](https://models.dev/logos/ollama-cloud.svg)Ollama Cloud
6
6
 
7
- Access 20 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
7
+ Access 21 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
 
@@ -44,6 +44,7 @@ for await (const chunk of stream) {
44
44
  | `ollama-cloud/gemma4:31b` | 262K | | | | | | — | — |
45
45
  | `ollama-cloud/glm-5.1` | 203K | | | | | | — | — |
46
46
  | `ollama-cloud/glm-5.2` | 976K | | | | | | — | — |
47
+ | `ollama-cloud/glm-5.3-flash` | 1.0M | | | | | | — | — |
47
48
  | `ollama-cloud/gpt-oss:120b` | 131K | | | | | | — | — |
48
49
  | `ollama-cloud/gpt-oss:20b` | 131K | | | | | | — | — |
49
50
  | `ollama-cloud/kimi-k2.5` | 262K | | | | | | — | — |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![OrcaRouter logo](https://models.dev/logos/orcarouter.svg)OrcaRouter
6
6
 
7
- Access 81 OrcaRouter models through Mastra's model router. Authentication is handled automatically using the `ORCAROUTER_API_KEY` environment variable.
7
+ Access 116 OrcaRouter models through Mastra's model router. Authentication is handled automatically using the `ORCAROUTER_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [OrcaRouter documentation](https://docs.orcarouter.ai).
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: "orcarouter/anthropic/claude-haiku-4.5"
22
+ model: "orcarouter/anthropic/claude-fable-5"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -38,38 +38,54 @@ for await (const chunk of stream) {
38
38
 
39
39
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
40
  | ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
+ | `orcarouter/anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
41
42
  | `orcarouter/anthropic/claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
42
- | `orcarouter/anthropic/claude-opus-4` | 200K | | | | | | $15 | $75 |
43
- | `orcarouter/anthropic/claude-opus-4.1` | 200K | | | | | | $15 | $75 |
44
43
  | `orcarouter/anthropic/claude-opus-4.5` | 200K | | | | | | $5 | $25 |
45
44
  | `orcarouter/anthropic/claude-opus-4.6` | 1.0M | | | | | | $5 | $25 |
46
45
  | `orcarouter/anthropic/claude-opus-4.7` | 1.0M | | | | | | $5 | $25 |
47
- | `orcarouter/anthropic/claude-sonnet-4` | 200K | | | | | | $3 | $15 |
48
- | `orcarouter/anthropic/claude-sonnet-4.5` | 200K | | | | | | $3 | $15 |
46
+ | `orcarouter/anthropic/claude-opus-4.8` | 1.0M | | | | | | $5 | $25 |
47
+ | `orcarouter/anthropic/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
48
+ | `orcarouter/anthropic/claude-sonnet-4.5` | 1.0M | | | | | | $3 | $15 |
49
49
  | `orcarouter/anthropic/claude-sonnet-4.6` | 1.0M | | | | | | $3 | $15 |
50
- | `orcarouter/deepseek/deepseek-chat` | 1.0M | | | | | | $0.14 | $0.28 |
51
- | `orcarouter/deepseek/deepseek-reasoner` | 1.0M | | | | | | $0.43 | $0.87 |
52
- | `orcarouter/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.19 | $0.37 |
53
- | `orcarouter/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $0.56 | $1 |
50
+ | `orcarouter/anthropic/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
51
+ | `orcarouter/deepseek/deepseek-chat` | 1.0M | | | | | | $0.15 | $0.29 |
52
+ | `orcarouter/deepseek/deepseek-reasoner` | 1.0M | | | | | | $0.15 | $0.29 |
53
+ | `orcarouter/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.29 |
54
+ | `orcarouter/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.15 | $0.29 |
55
+ | `orcarouter/deepseek/deepseek-v4-flash-free` | 1.0M | | | | | | — | — |
56
+ | `orcarouter/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.15 | $0.29 |
57
+ | `orcarouter/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $0.44 | $0.88 |
58
+ | `orcarouter/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $0.44 | $0.88 |
54
59
  | `orcarouter/google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
55
60
  | `orcarouter/google/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
56
- | `orcarouter/google/gemini-2.5-pro` | 1.0M | | | | | | $3 | $15 |
61
+ | `orcarouter/google/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
57
62
  | `orcarouter/google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
58
- | `orcarouter/google/gemini-3-pro-preview` | 1.0M | | | | | | $4 | $18 |
63
+ | `orcarouter/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
59
64
  | `orcarouter/google/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
60
- | `orcarouter/google/gemini-3.1-pro-preview` | 1.0M | | | | | | $4 | $18 |
61
- | `orcarouter/google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $4 | $18 |
62
- | `orcarouter/google/gemini-flash-latest` | 1.0M | | | | | | $2 | $9 |
65
+ | `orcarouter/google/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
66
+ | `orcarouter/google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
67
+ | `orcarouter/google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
68
+ | `orcarouter/google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
69
+ | `orcarouter/google/gemini-3.6-flash` | 1.0M | | | | | | $2 | $8 |
70
+ | `orcarouter/google/gemini-flash-latest` | 1.0M | | | | | | $0.50 | $3 |
63
71
  | `orcarouter/google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.25 | $2 |
72
+ | `orcarouter/google/gemini-robotics-er-1.6-preview` | 131K | | | | | | $1 | $5 |
64
73
  | `orcarouter/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.06 | $0.33 |
65
74
  | `orcarouter/google/gemma-4-31b-it` | 262K | | | | | | $0.13 | $0.38 |
66
75
  | `orcarouter/grok/grok-4.3` | 1.0M | | | | | | $1 | $3 |
76
+ | `orcarouter/grok/grok-4.5` | 500K | | | | | | $2 | $6 |
77
+ | `orcarouter/grok/grok-4.6` | 500K | | | | | | $2 | $6 |
67
78
  | `orcarouter/kimi/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
68
79
  | `orcarouter/kimi/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
80
+ | `orcarouter/kimi/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
81
+ | `orcarouter/kimi/kimi-k3` | 1.0M | | | | | | $3 | $17 |
82
+ | `orcarouter/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
83
+ | `orcarouter/meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
69
84
  | `orcarouter/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
70
85
  | `orcarouter/minimax/minimax-m2.5-highspeed` | 205K | | | | | | $0.60 | $2 |
71
86
  | `orcarouter/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
72
87
  | `orcarouter/minimax/minimax-m2.7-highspeed` | 205K | | | | | | $0.60 | $2 |
88
+ | `orcarouter/minimax/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
73
89
  | `orcarouter/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
74
90
  | `orcarouter/openai/gpt-4` | 8K | | | | | | $30 | $60 |
75
91
  | `orcarouter/openai/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
@@ -83,42 +99,61 @@ for await (const chunk of stream) {
83
99
  | `orcarouter/openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
84
100
  | `orcarouter/openai/gpt-5` | 400K | | | | | | $1 | $10 |
85
101
  | `orcarouter/openai/gpt-5-chat-latest` | 400K | | | | | | $1 | $10 |
86
- | `orcarouter/openai/gpt-5-codex` | 400K | | | | | | $1 | $10 |
87
102
  | `orcarouter/openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
88
103
  | `orcarouter/openai/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
89
104
  | `orcarouter/openai/gpt-5-pro` | 400K | | | | | | $15 | $120 |
90
105
  | `orcarouter/openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
91
106
  | `orcarouter/openai/gpt-5.1-chat-latest` | 128K | | | | | | $1 | $10 |
92
107
  | `orcarouter/openai/gpt-5.1-codex` | 400K | | | | | | $1 | $10 |
93
- | `orcarouter/openai/gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
94
108
  | `orcarouter/openai/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
95
109
  | `orcarouter/openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
96
110
  | `orcarouter/openai/gpt-5.2-chat-latest` | 128K | | | | | | $2 | $14 |
97
111
  | `orcarouter/openai/gpt-5.2-codex` | 400K | | | | | | $2 | $14 |
98
112
  | `orcarouter/openai/gpt-5.2-pro` | 400K | | | | | | $21 | $168 |
99
- | `orcarouter/openai/gpt-5.3-chat-latest` | 128K | | | | | | $2 | $14 |
100
113
  | `orcarouter/openai/gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
101
- | `orcarouter/openai/gpt-5.4` | 1.1M | | | | | | $5 | $23 |
114
+ | `orcarouter/openai/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
102
115
  | `orcarouter/openai/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
103
116
  | `orcarouter/openai/gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
104
- | `orcarouter/openai/gpt-5.4-pro` | 1.1M | | | | | | $60 | $270 |
117
+ | `orcarouter/openai/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
105
118
  | `orcarouter/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
106
119
  | `orcarouter/openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
120
+ | `orcarouter/openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
121
+ | `orcarouter/openai/gpt-5.6-sol` | 1.1M | | | | | | $4 | $20 |
122
+ | `orcarouter/openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
123
+ | `orcarouter/openai/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.17 |
107
124
  | `orcarouter/orcarouter/auto` | 128K | | | | | | — | — |
125
+ | `orcarouter/orcarouter/free` | 66K | | | | | | — | — |
126
+ | `orcarouter/orcarouter/fusion` | 1.0M | | | | | | — | — |
127
+ | `orcarouter/orcarouter/fusion-flash` | 200K | | | | | | — | — |
128
+ | `orcarouter/orcarouter/fusion-mini` | 1.0M | | | | | | — | — |
108
129
  | `orcarouter/qwen/qwen3-max` | 262K | | | | | | $0.36 | $1 |
130
+ | `orcarouter/qwen/qwen3-vl-235b-a22b-instruct` | 131K | | | | | | $0.40 | $2 |
131
+ | `orcarouter/qwen/qwen3-vl-235b-a22b-thinking` | 131K | | | | | | $0.40 | $4 |
109
132
  | `orcarouter/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.12 | $0.92 |
110
133
  | `orcarouter/qwen/qwen3.5-27b` | 262K | | | | | | $0.09 | $0.69 |
111
134
  | `orcarouter/qwen/qwen3.5-35b-a3b` | 262K | | | | | | $0.06 | $0.46 |
112
135
  | `orcarouter/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.17 | $1 |
136
+ | `orcarouter/qwen/qwen3.5-flash` | 1.0M | | | | | | $0.10 | $0.40 |
113
137
  | `orcarouter/qwen/qwen3.5-plus` | 1.0M | | | | | | $0.12 | $0.69 |
114
138
  | `orcarouter/qwen/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
139
+ | `orcarouter/qwen/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
115
140
  | `orcarouter/qwen/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
141
+ | `orcarouter/qwen/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
142
+ | `orcarouter/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
143
+ | `orcarouter/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.35 | $1 |
144
+ | `orcarouter/qwen/qwen3.8-27b` | 262K | | | | | | $0.33 | $2 |
145
+ | `orcarouter/qwen/qwen3.8-27b-free` | 66K | | | | | | — | — |
146
+ | `orcarouter/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
147
+ | `orcarouter/tencent/hy3` | 256K | | | | | | $0.18 | $0.59 |
148
+ | `orcarouter/tencent/hy3-free` | 256K | | | | | | — | — |
116
149
  | `orcarouter/z-ai/glm-4.5` | 131K | | | | | | $0.60 | $2 |
117
150
  | `orcarouter/z-ai/glm-4.5-air` | 131K | | | | | | $0.20 | $1 |
118
151
  | `orcarouter/z-ai/glm-4.6` | 205K | | | | | | $0.60 | $2 |
119
152
  | `orcarouter/z-ai/glm-4.7` | 205K | | | | | | $0.60 | $2 |
120
153
  | `orcarouter/z-ai/glm-5` | 205K | | | | | | $1 | $3 |
121
154
  | `orcarouter/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
155
+ | `orcarouter/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
156
+ | `orcarouter/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
122
157
 
123
158
  ## Advanced configuration
124
159
 
@@ -130,7 +165,7 @@ const agent = new Agent({
130
165
  name: "custom-agent",
131
166
  model: {
132
167
  url: "https://api.orcarouter.ai/v1",
133
- id: "orcarouter/anthropic/claude-haiku-4.5",
168
+ id: "orcarouter/anthropic/claude-fable-5",
134
169
  apiKey: process.env.ORCAROUTER_API_KEY,
135
170
  headers: {
136
171
  "X-Custom-Header": "value"
@@ -148,8 +183,8 @@ const agent = new Agent({
148
183
  model: ({ requestContext }) => {
149
184
  const useAdvanced = requestContext.task === "complex";
150
185
  return useAdvanced
151
- ? "orcarouter/z-ai/glm-5.1"
152
- : "orcarouter/anthropic/claude-haiku-4.5";
186
+ ? "orcarouter/z-ai/glm-5.3"
187
+ : "orcarouter/anthropic/claude-fable-5";
153
188
  }
154
189
  });
155
190
  ```