@mastra/mcp-docs-server 1.2.25-alpha.3 → 1.2.25-alpha.6

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.
@@ -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 7124 models from 200 providers through a single API.
7
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7132 models from 200 providers through a single API.
8
8
 
9
9
  ## Features
10
10
 
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Cloudflare Workers AI logo](https://models.dev/logos/cloudflare-workers-ai.svg)Cloudflare Workers AI
6
6
 
7
- Access 26 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
7
+ Access 27 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
8
8
 
9
9
  Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
10
10
 
@@ -64,6 +64,7 @@ for await (const chunk of stream) {
64
64
  | `cloudflare-workers-ai/@cf/qwen/qwq-32b` | 24K | | | | | | $0.66 | $1 |
65
65
  | `cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash` | 131K | | | | | | $0.06 | $0.40 |
66
66
  | `cloudflare-workers-ai/@cf/zai-org/glm-5.2` | 262K | | | | | | $1 | $4 |
67
+ | `cloudflare-workers-ai/@cf/zai-org/glm-5.3` | 1.3M | | | | | | $1 | $4 |
67
68
  | `cloudflare-workers-ai/@cf/zai-org/glm-5.3-flash` | 1.3M | | | | | | $0.15 | $0.50 |
68
69
 
69
70
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![CrossModel logo](https://models.dev/logos/crossmodel.svg)CrossModel
6
6
 
7
- Access 58 CrossModel models through Mastra's model router. Authentication is handled automatically using the `CROSSMODEL_API_KEY` environment variable.
7
+ Access 59 CrossModel models through Mastra's model router. Authentication is handled automatically using the `CROSSMODEL_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [CrossModel documentation](https://www.crossmodel.ai/docs).
10
10
 
@@ -46,9 +46,10 @@ for await (const chunk of stream) {
46
46
  | `crossmodel/anthropic/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
47
47
  | `crossmodel/anthropic/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
48
48
  | `crossmodel/anthropic/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
49
- | `crossmodel/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.41 | $1 |
50
- | `crossmodel/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.41 | $1 |
49
+ | `crossmodel/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.27 | $1 |
50
+ | `crossmodel/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.27 | $1 |
51
51
  | `crossmodel/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
52
+ | `crossmodel/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.27 | $1 |
52
53
  | `crossmodel/gemini/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
53
54
  | `crossmodel/gemini/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
54
55
  | `crossmodel/gemini/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
@@ -79,7 +79,7 @@ for await (const chunk of stream) {
79
79
  | `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
80
80
  | `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
81
81
  | `digitalocean/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
82
- | `digitalocean/kimi-k3` | 1.0M | | | | | | $3 | $14 |
82
+ | `digitalocean/kimi-k3` | 1.0M | | | | | | $3 | $13 |
83
83
  | `digitalocean/llama-4-maverick` | 128K | | | | | | $0.20 | $0.70 |
84
84
  | `digitalocean/llama3-8b-instruct` | 131K | | | | | | $0.20 | $0.20 |
85
85
  | `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Eden AI logo](https://models.dev/logos/edenai.svg)Eden AI
6
6
 
7
- Access 258 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
7
+ Access 259 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
 
@@ -169,6 +169,7 @@ for await (const chunk of stream) {
169
169
  | `edenai/moonshot/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
170
170
  | `edenai/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
171
171
  | `edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
172
+ | `edenai/nebius/deepseek-ai/DeepSeek-V4-Pro-0813` | 979K | | | | | | $1 | $4 |
172
173
  | `edenai/nebius/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.13 | $0.40 |
173
174
  | `edenai/nebius/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.30 | $0.90 |
174
175
  | `edenai/nebius/nvidia/Nemotron-3-Ultra-550b-a55b` | 1.0M | | | | | | $1 | $3 |
@@ -216,8 +217,8 @@ for await (const chunk of stream) {
216
217
  | `edenai/perplexityai/sonar-deep-research` | 128K | | | | | | $2 | $8 |
217
218
  | `edenai/perplexityai/sonar-pro` | 200K | | | | | | $3 | $15 |
218
219
  | `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
219
- | `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.18 | $0.53 |
220
- | `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $0.58 | $2 |
220
+ | `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.35 | $1 |
221
+ | `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
221
222
  | `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
222
223
  | `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
223
224
  | `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![GreenPT logo](https://models.dev/logos/greenpt.svg)GreenPT
6
6
 
7
- Access 37 GreenPT models through Mastra's model router. Authentication is handled automatically using the `GREENPT_API_KEY` environment variable.
7
+ Access 39 GreenPT models through Mastra's model router. Authentication is handled automatically using the `GREENPT_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [GreenPT documentation](https://docs.greenpt.ai).
10
10
 
@@ -52,6 +52,8 @@ for await (const chunk of stream) {
52
52
  | `greenpt/glm-5.2-ponytail` | 1.0M | | | | | | $1 | $5 |
53
53
  | `greenpt/glm-5.2-ponytail-lite` | 1.0M | | | | | | $1 | $5 |
54
54
  | `greenpt/glm-5.2-ponytail-ultra` | 1.0M | | | | | | $1 | $5 |
55
+ | `greenpt/glm-5.3` | 1.0M | | | | | | $1 | $5 |
56
+ | `greenpt/glm-5.3-flash` | 1.0M | | | | | | $0.13 | $0.51 |
55
57
  | `greenpt/gpt-oss-120b` | 131K | | | | | | $0.23 | $0.80 |
56
58
  | `greenpt/green-l` | 128K | | | | | | $0.28 | $0.91 |
57
59
  | `greenpt/green-l-raw` | 128K | | | | | | $0.28 | $0.91 |
@@ -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 367 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
 
@@ -91,7 +91,7 @@ for await (const chunk of stream) {
91
91
  | `kilo/cohere/command-r-plus-08-2024` | 128K | | | | | | $3 | $10 |
92
92
  | `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
93
93
  | `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
94
- | `kilo/deepseek/deepseek-chat` | 164K | | | | | | $0.32 | $0.89 |
94
+ | `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.26 | $1 |
95
95
  | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.29 | $1 |
96
96
  | `kilo/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.27 | $1 |
97
97
  | `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
@@ -105,6 +105,7 @@ for await (const chunk of stream) {
105
105
  | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.44 | $1 |
106
106
  | `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
107
107
  | `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
108
+ | `kilo/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
108
109
  | `kilo/dots-studio/dots-3-note-preview:free` | 512K | | | | | | — | — |
109
110
  | `kilo/google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
110
111
  | `kilo/google/gemini-2.5-flash-image` | 33K | | | | | | $0.15 | $1 |
@@ -175,7 +176,7 @@ for await (const chunk of stream) {
175
176
  | `kilo/minimax/minimax-m2` | 205K | | | | | | $0.30 | $1 |
176
177
  | `kilo/minimax/minimax-m2-her` | 66K | | | | | | $0.30 | $1 |
177
178
  | `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
178
- | `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
179
+ | `kilo/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
179
180
  | `kilo/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
180
181
  | `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
181
182
  | `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
@@ -307,7 +308,7 @@ for await (const chunk of stream) {
307
308
  | `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
308
309
  | `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
309
310
  | `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
310
- | `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.13 | $0.52 |
311
+ | `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.13 | $0.52 |
311
312
  | `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
312
313
  | `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
313
314
  | `kilo/qwen/qwen3-8b` | 131K | | | | | | $0.12 | $0.46 |
@@ -368,13 +369,13 @@ for await (const chunk of stream) {
368
369
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
369
370
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
370
371
  | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
371
- | `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
372
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
372
373
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
373
374
  | `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
374
375
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
375
376
  | `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
376
377
  | `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
377
- | `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
378
+ | `kilo/thinkingmachines/inkling` | 1.0M | | | | | | $0.95 | $4 |
378
379
  | `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
379
380
  | `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
380
381
  | `kilo/thinkingmachines/inkling:free` | 1.0M | | | | | | — | — |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
6
6
 
7
- Access 372 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 371 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
 
@@ -183,9 +183,8 @@ for await (const chunk of stream) {
183
183
  | `llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct` | 262K | | | | | | $0.20 | $0.88 |
184
184
  | `llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct` | 262K | | | | | | $0.15 | $0.60 |
185
185
  | `llmgateway-providers/deepinfra/qwen3.5-9b` | 262K | | | | | | $0.10 | $0.15 |
186
- | `llmgateway-providers/deepseek/deepseek-v4-flash` | 1.1M | | | | | | $0.14 | $0.28 |
187
- | `llmgateway-providers/deepseek/deepseek-v4-flash-vision-exp` | 1.1M | | | | | | $0.14 | $0.28 |
188
186
  | `llmgateway-providers/deepseek/deepseek-v4-pro` | 1.1M | | | | | | $0.43 | $0.87 |
187
+ | `llmgateway-providers/deepseek/deepseek-v4.1-flash` | 1.1M | | | | | | $0.15 | $0.60 |
189
188
  | `llmgateway-providers/embercloud/glm-4.5` | 131K | | | | | | $0.60 | $2 |
190
189
  | `llmgateway-providers/embercloud/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
191
190
  | `llmgateway-providers/embercloud/glm-4.7` | 200K | | | | | | $0.38 | $2 |
@@ -57,8 +57,8 @@ for await (const chunk of stream) {
57
57
  | `llmgateway/custom` | 128K | | | | | | — | — |
58
58
  | `llmgateway/deepseek-v3.2` | 164K | | | | | | $0.26 | $0.38 |
59
59
  | `llmgateway/deepseek-v4-flash` | 1.1M | | | | | | $0.05 | $0.10 |
60
- | `llmgateway/deepseek-v4-flash-vision-exp` | 1.1M | | | | | | $0.14 | $0.28 |
61
60
  | `llmgateway/deepseek-v4-pro` | 1.1M | | | | | | $0.43 | $0.87 |
61
+ | `llmgateway/deepseek-v4.1-flash` | 1.1M | | | | | | $0.15 | $0.60 |
62
62
  | `llmgateway/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
63
63
  | `llmgateway/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
64
64
  | `llmgateway/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 589 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 587 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
 
@@ -50,7 +50,7 @@ for await (const chunk of stream) {
50
50
  | `nano-gpt/alibaba/qwen3.6-27b` | 260K | | | | | | $0.20 | $2 |
51
51
  | `nano-gpt/alibaba/qwen3.6-27b:thinking` | 260K | | | | | | $0.20 | $2 |
52
52
  | `nano-gpt/alibaba/qwen3.6-flash` | 992K | | | | | | $0.19 | $1 |
53
- | `nano-gpt/alibaba/qwen3.8-flash` | 992K | | | | | | $0.16 | $0.47 |
53
+ | `nano-gpt/alibaba/qwen3.8-flash` | 992K | | | | | | $0.14 | $0.42 |
54
54
  | `nano-gpt/alibaba/qwen3.8-max-0902` | 992K | | | | | | $2 | $6 |
55
55
  | `nano-gpt/amazon/nova-2-lite-v1` | 1.0M | | | | | | $0.51 | $4 |
56
56
  | `nano-gpt/amazon/nova-lite-v1` | 300K | | | | | | $0.06 | $0.24 |
@@ -203,8 +203,8 @@ for await (const chunk of stream) {
203
203
  | `nano-gpt/gemini-3-pro-image-preview` | 66K | | | | | | $2 | $12 |
204
204
  | `nano-gpt/gemini-exp-1206` | 2.1M | | | | | | $1 | $5 |
205
205
  | `nano-gpt/gemma-4-12b-it` | 262K | | | | | | $0.05 | $0.25 |
206
- | `nano-gpt/gemma-4-12b-it-semancer` | 131K | | | | | | $0.05 | $0.25 |
207
- | `nano-gpt/gemma-4-12b-it-station-keeper` | 131K | | | | | | $0.05 | $0.25 |
206
+ | `nano-gpt/gemma-4-12b-it-semancer` | 262K | | | | | | $0.05 | $0.25 |
207
+ | `nano-gpt/gemma-4-12b-it-station-keeper` | 262K | | | | | | $0.05 | $0.25 |
208
208
  | `nano-gpt/gemma-4-26b-a4b-it-chimerax` | 262K | | | | | | $0.12 | $0.38 |
209
209
  | `nano-gpt/gemma-4-26b-a4b-it-darksoul` | 262K | | | | | | $0.12 | $0.38 |
210
210
  | `nano-gpt/gemma-4-26b-a4b-it-luminous` | 262K | | | | | | $0.12 | $0.38 |
@@ -272,8 +272,10 @@ for await (const chunk of stream) {
272
272
  | `nano-gpt/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
273
273
  | `nano-gpt/inception/mercury-2.5-preview` | 260K | | | | | | $0.04 | $0.15 |
274
274
  | `nano-gpt/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.07 | $0.22 |
275
+ | `nano-gpt/inclusionai/ling-3.0-flash-vl` | 262K | | | | | | $0.06 | $0.18 |
275
276
  | `nano-gpt/inclusionai/ling-3.0-flash:thinking` | 262K | | | | | | $0.07 | $0.22 |
276
277
  | `nano-gpt/inflatebot/MN-12B-Mag-Mell-R1` | 16K | | | | | | $0.49 | $0.49 |
278
+ | `nano-gpt/k2-horizon-7b` | 131K | | | | | | $0.05 | $0.20 |
277
279
  | `nano-gpt/kimi-k2-instruct-fast` | 131K | | | | | | $0.40 | $2 |
278
280
  | `nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3` | 33K | | | | | | $0.70 | $0.70 |
279
281
  | `nano-gpt/liquid/lfm-2.5-2.6b` | 128K | | | | | | $0.10 | $0.20 |
@@ -414,8 +416,6 @@ for await (const chunk of stream) {
414
416
  | `nano-gpt/openai/o4-mini-high` | 200K | | | | | | $1 | $4 |
415
417
  | `nano-gpt/ornith-ai/ornith-1.5-35b-a3b` | 262K | | | | | | $0.10 | $0.40 |
416
418
  | `nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking` | 262K | | | | | | $0.10 | $0.40 |
417
- | `nano-gpt/ornith-ai/ornith-1.5-9b` | 262K | | | | | | $0.10 | $0.20 |
418
- | `nano-gpt/ornith-ai/ornith-1.5-9b:thinking` | 262K | | | | | | $0.10 | $0.20 |
419
419
  | `nano-gpt/pamanseau/OpenReasoning-Nemotron-32B` | 33K | | | | | | $0.10 | $0.40 |
420
420
  | `nano-gpt/perceptron/perceptron-mk1` | 33K | | | | | | $0.15 | $2 |
421
421
  | `nano-gpt/perplexity-academic-researcher` | 128K | | | | | | $2 | $8 |
@@ -453,8 +453,6 @@ for await (const chunk of stream) {
453
453
  | `nano-gpt/qwen/qwen3.5-plus` | 984K | | | | | | $0.40 | $2 |
454
454
  | `nano-gpt/qwen/qwen3.5-plus-thinking` | 984K | | | | | | $0.40 | $2 |
455
455
  | `nano-gpt/qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.11 | $0.80 |
456
- | `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored` | 262K | | | | | | $0.15 | $0.95 |
457
- | `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored:thinking` | 262K | | | | | | $0.15 | $0.95 |
458
456
  | `nano-gpt/qwen/Qwen3.6-35B-A3B:thinking` | 262K | | | | | | $0.11 | $0.80 |
459
457
  | `nano-gpt/qwen/qwen3.8-2.4t-a95b` | 991K | | | | | | $2 | $6 |
460
458
  | `nano-gpt/qwen/qwen3.8-27b-fable` | 262K | | | | | | $0.25 | $2 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NEAR AI Cloud logo](https://models.dev/logos/nearai.svg)NEAR AI Cloud
6
6
 
7
- Access 37 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
7
+ Access 32 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [NEAR AI Cloud documentation](https://docs.near.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: "nearai/Qwen/Qwen3-30B-A3B-Instruct-2507"
22
+ model: "nearai/Qwen/Qwen3-Embedding-0.6B"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -41,16 +41,14 @@ for await (const chunk of stream) {
41
41
  | `nearai/anthropic/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
42
42
  | `nearai/anthropic/claude-opus-4-6` | 200K | | | | | | $5 | $25 |
43
43
  | `nearai/anthropic/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
44
- | `nearai/anthropic/claude-sonnet-4-5` | 200K | | | | | | $3 | $16 |
44
+ | `nearai/anthropic/claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
45
45
  | `nearai/anthropic/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
46
46
  | `nearai/black-forest-labs/FLUX.2-klein-4B` | 128K | | | | | | $1 | $1 |
47
47
  | `nearai/google/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
48
48
  | `nearai/google/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
49
49
  | `nearai/google/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
50
- | `nearai/google/gemini-3-pro` | 1.0M | | | | | | $1 | $15 |
51
50
  | `nearai/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
52
51
  | `nearai/google/gemini-3.5-flash` | 1.0M | | | | | | $2 | $9 |
53
- | `nearai/google/gemma-4-31B-it` | 262K | | | | | | $0.13 | $0.40 |
54
52
  | `nearai/openai/gpt-4.1` | 1.0M | | | | | | $2 | $8 |
55
53
  | `nearai/openai/gpt-4.1-mini` | 1.0M | | | | | | $0.40 | $2 |
56
54
  | `nearai/openai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
@@ -58,23 +56,20 @@ for await (const chunk of stream) {
58
56
  | `nearai/openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
59
57
  | `nearai/openai/gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
60
58
  | `nearai/openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
61
- | `nearai/openai/gpt-5.2` | 400K | | | | | | $2 | $16 |
59
+ | `nearai/openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
62
60
  | `nearai/openai/gpt-5.4` | 1.1M | | | | | | $3 | $15 |
63
61
  | `nearai/openai/gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
64
62
  | `nearai/openai/gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
65
63
  | `nearai/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
66
- | `nearai/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.55 |
67
64
  | `nearai/openai/o3` | 200K | | | | | | $2 | $8 |
68
65
  | `nearai/openai/o3-mini` | 200K | | | | | | $1 | $4 |
69
66
  | `nearai/openai/o4-mini` | 200K | | | | | | $1 | $4 |
70
- | `nearai/openai/whisper-large-v3` | 448 | | | | | | $0.01 | — |
71
- | `nearai/Qwen/Qwen3-30B-A3B-Instruct-2507` | 262K | | | | | | $0.15 | $0.55 |
72
- | `nearai/Qwen/Qwen3-Embedding-0.6B` | 41K | | | | | | $0.01 | — |
67
+ | `nearai/openai/whisper-large-v3` | 448 | | | | | | $0.01 | $0.01 |
68
+ | `nearai/Qwen/Qwen3-Embedding-0.6B` | 33K | | | | | | $0.01 | $0.01 |
73
69
  | `nearai/Qwen/Qwen3-Reranker-0.6B` | 41K | | | | | | $0.01 | $0.01 |
74
- | `nearai/Qwen/Qwen3-VL-30B-A3B-Instruct` | 256K | | | | | | $0.15 | $0.55 |
75
- | `nearai/Qwen/Qwen3.5-122B-A10B` | 131K | | | | | | $0.40 | $3 |
70
+ | `nearai/Qwen/Qwen3-VL-30B-A3B-Instruct` | 16K | | | | | | $0.15 | $0.55 |
76
71
  | `nearai/Qwen/Qwen3.6-35B-A3B-FP8` | 262K | | | | | | $0.17 | $1 |
77
- | `nearai/zai-org/GLM-5.1-FP8` | 203K | | | | | | $0.85 | $3 |
72
+ | `nearai/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
78
73
 
79
74
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
80
75
 
@@ -88,7 +83,7 @@ const agent = new Agent({
88
83
  name: "custom-agent",
89
84
  model: {
90
85
  url: "https://cloud-api.near.ai/v1",
91
- id: "nearai/Qwen/Qwen3-30B-A3B-Instruct-2507",
86
+ id: "nearai/Qwen/Qwen3-Embedding-0.6B",
92
87
  apiKey: process.env.NEARAI_API_KEY,
93
88
  headers: {
94
89
  "X-Custom-Header": "value"
@@ -107,7 +102,7 @@ const agent = new Agent({
107
102
  const useAdvanced = requestContext.task === "complex";
108
103
  return useAdvanced
109
104
  ? "nearai/zai-org/GLM-5.1-FP8"
110
- : "nearai/Qwen/Qwen3-30B-A3B-Instruct-2507";
105
+ : "nearai/Qwen/Qwen3-Embedding-0.6B";
111
106
  }
112
107
  });
113
108
  ```
@@ -149,9 +149,9 @@ for await (const chunk of stream) {
149
149
  | `ofox/z-ai/glm-5` | 205K | | | | | | $1 | $3 |
150
150
  | `ofox/z-ai/glm-5-turbo` | 200K | | | | | | $1 | $4 |
151
151
  | `ofox/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
152
- | `ofox/z-ai/glm-5.2` | 1.0M | | | | | | $0.98 | $3 |
152
+ | `ofox/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
153
153
  | `ofox/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
154
- | `ofox/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
154
+ | `ofox/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
155
155
  | `ofox/z-ai/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
156
156
 
157
157
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![OpenCode Go logo](https://models.dev/logos/opencode-go.svg)OpenCode Go
6
6
 
7
- Access 35 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
7
+ Access 36 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/zen).
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: "opencode-go/deepseek-v4-flash"
22
+ model: "opencode-go/deepseek-flash"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -38,8 +38,9 @@ for await (const chunk of stream) {
38
38
 
39
39
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
40
  | ------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
- | `opencode-go/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
42
- | `opencode-go/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
41
+ | `opencode-go/deepseek-flash` | 1.0M | | | | | | $0.15 | $0.60 |
42
+ | `opencode-go/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.60 |
43
+ | `opencode-go/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.15 | $0.60 |
43
44
  | `opencode-go/deepseek-v4-pro` | 1.0M | | | | | | $0.66 | $2 |
44
45
  | `opencode-go/glm-5.1` | 203K | | | | | | $1 | $4 |
45
46
  | `opencode-go/glm-5.2` | 1.0M | | | | | | $1 | $4 |
@@ -59,7 +60,6 @@ for await (const chunk of stream) {
59
60
  | `opencode-go/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
60
61
  | `opencode-go/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
61
62
  | `opencode-go/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
62
- | `opencode-go/omen-alpha` | 500K | | | | | | $0.20 | $0.66 |
63
63
  | `opencode-go/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
64
64
  | `opencode-go/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
65
65
  | `opencode-go/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
@@ -78,7 +78,7 @@ const agent = new Agent({
78
78
  name: "custom-agent",
79
79
  model: {
80
80
  url: "https://opencode.ai/zen/go/v1",
81
- id: "opencode-go/deepseek-v4-flash",
81
+ id: "opencode-go/deepseek-flash",
82
82
  apiKey: process.env.OPENCODE_API_KEY,
83
83
  headers: {
84
84
  "X-Custom-Header": "value"
@@ -97,7 +97,7 @@ const agent = new Agent({
97
97
  const useAdvanced = requestContext.task === "complex";
98
98
  return useAdvanced
99
99
  ? "opencode-go/qwen3.8-max"
100
- : "opencode-go/deepseek-v4-flash";
100
+ : "opencode-go/deepseek-flash";
101
101
  }
102
102
  });
103
103
  ```
@@ -82,7 +82,6 @@ for await (const chunk of stream) {
82
82
  | `zenmux/openai/gpt-5` | 400K | | | | | | $1 | $10 |
83
83
  | `zenmux/openai/gpt-5-codex` | 400K | | | | | | $1 | $10 |
84
84
  | `zenmux/openai/gpt-5.1` | 400K | | | | | | $1 | $10 |
85
- | `zenmux/openai/gpt-5.1-chat` | 128K | | | | | | $1 | $10 |
86
85
  | `zenmux/openai/gpt-5.1-codex` | 400K | | | | | | $1 | $10 |
87
86
  | `zenmux/openai/gpt-5.1-codex-mini` | 400K | | | | | | $0.25 | $2 |
88
87
  | `zenmux/openai/gpt-5.2` | 400K | | | | | | $2 | $14 |
@@ -155,6 +155,24 @@ const response = await mastraClient.createFeedback({
155
155
  })
156
156
  ```
157
157
 
158
+ ### Deleting feedback and scores
159
+
160
+ Delete feedback or score records by id. Deletion is idempotent, so missing ids are ignored. Each request accepts at most 1,000 `feedbackIds` or 1,000 `scoreIds`. Optional `organizationId` and `resourceId` fields restrict each deletion to records with matching scope fields:
161
+
162
+ ```typescript
163
+ await mastraClient.deleteFeedback({
164
+ feedbackIds: ['feedback-1', 'feedback-2'],
165
+ organizationId: 'org-1',
166
+ resourceId: 'resource-1',
167
+ })
168
+
169
+ await mastraClient.deleteScores({
170
+ scoreIds: ['score-1', 'score-2'],
171
+ organizationId: 'org-1',
172
+ resourceId: 'resource-1',
173
+ })
174
+ ```
175
+
158
176
  ### Listing feedback
159
177
 
160
178
  Retrieve paginated feedback records with optional filters:
@@ -23,6 +23,24 @@ const { mastra, controller } = await mountAgentControllerOnMastra({
23
23
  const session = await controller.createSession({ resourceId: 'user-123' })
24
24
  ```
25
25
 
26
+ ## Commit attribution
27
+
28
+ Use `coAuthor` to set the `Co-Authored-By` trailer in coding-agent commit guidance:
29
+
30
+ ```typescript
31
+ const { mastra, controller } = await mountAgentControllerOnMastra({
32
+ cwd: process.cwd(),
33
+ coAuthor: {
34
+ name: 'my-coding-app',
35
+ email: 'my-coding-app@example.com',
36
+ },
37
+ })
38
+ ```
39
+
40
+ Both fields are optional. An omitted field uses the SDK default: `mastra-platform[bot]` for the name and `284800079+mastra-platform[bot]@users.noreply.github.com` for the email.
41
+
42
+ The `mastracode` terminal app sets its name to `mastracode`, and Factory sets its name to `mastra-platform[bot]`. Both use the same default email, so GitHub resolves their trailers to the same bot account while the raw commit message retains the app name.
43
+
26
44
  Pass an existing `mastra` to mount the controller onto a Mastra instance that already hosts other primitives:
27
45
 
28
46
  ```typescript
@@ -38,6 +56,8 @@ const { controller } = await mountAgentControllerOnMastra({ mastra })
38
56
 
39
57
  **cwd** (`string`): Working directory for project detection. (Default: `process.cwd()`)
40
58
 
59
+ **coAuthor** (`{ name?: string; email?: string }`): Commit co-author identity included in coding-agent commit guidance. Omitted fields use the SDK defaults.
60
+
41
61
  **mastra** (`Mastra`): Existing Mastra instance to mount onto. When omitted, a Mastra is created that owns the controller storage.
42
62
 
43
63
  **controllerId** (`string`): Id under which the controller is registered on the Mastra instance.
@@ -58,7 +58,7 @@ const prompt = buildBasePrompt({
58
58
 
59
59
  **mode** (`string`): Active agent mode (for example, "build" or "plan").
60
60
 
61
- **modelId** (`string`): Identifier of the active model.
61
+ **modelId** (`string`): Identifier of the active model. It is not included in the commit Co-Authored-By line.
62
62
 
63
63
  **activePlan** (`{ title: string; plan: string; approvedAt: string } | null`): The currently approved plan, if any.
64
64
 
@@ -118,6 +118,26 @@ await observability.batchCreateFeedback({
118
118
  })
119
119
  ```
120
120
 
121
+ ## Delete feedback
122
+
123
+ ### `deleteFeedback(args)`
124
+
125
+ Deletes up to 1,000 feedback records by id. The operation is idempotent: ids that don't exist are ignored, and an empty `feedbackIds` array is a no-op. When `organizationId` or `resourceId` are provided, they're ANDed into the delete predicate to restrict deletion to records with matching scope fields.
126
+
127
+ ```typescript
128
+ await mastraClient.deleteFeedback({
129
+ feedbackIds: ['feedback-1', 'feedback-2'],
130
+ })
131
+ ```
132
+
133
+ **feedbackIds** (`string[]`): Ids of the feedback records to delete. Accepts at most 1,000 ids.
134
+
135
+ **organizationId** (`string`): Restricts the delete to records with this organization id.
136
+
137
+ **resourceId** (`string`): Restricts the delete to records with this resource id.
138
+
139
+ On ClickHouse, deletion uses lightweight deletes on the main feedback events table to remove rows from reads, including OLAP queries, without guaranteeing immediate physical removal, so open-source deployments must configure an [observability retention period](https://mastra.ai/reference/storage/retention) to physically purge them. ClickHouse doesn't configure a retention TTL for deletion requests in open-source deployments. Delete APIs intentionally leave cursor-only delta rows untouched. These rows contain identifiers rather than feedback payloads and expire within two days.
140
+
121
141
  ## List feedback
122
142
 
123
143
  ### `listFeedback(args?)`
@@ -381,14 +401,16 @@ Use `FeedbackFilter` in `listFeedback()` and OLAP query `filters`.
381
401
 
382
402
  These routes belong to a Mastra runtime and use its configured observability storage. They're separate from the [unversioned Mastra Platform feedback query API](https://mastra.ai/docs/mastra-platform/api), which doesn't provide a feedback creation route.
383
403
 
384
- | Method | Path | Purpose | Permission |
385
- | ------ | ----------------------------------------- | ---------------------------- | -------------------- |
386
- | `GET` | `/api/observability/feedback` | List feedback records | None derived |
387
- | `POST` | `/api/observability/feedback` | Create a feedback record | None derived |
388
- | `POST` | `/api/observability/feedback/aggregate` | Return one aggregate value | `observability:read` |
389
- | `POST` | `/api/observability/feedback/breakdown` | Group feedback by dimensions | `observability:read` |
390
- | `POST` | `/api/observability/feedback/timeseries` | Bucket feedback by interval | `observability:read` |
391
- | `POST` | `/api/observability/feedback/percentiles` | Return percentile series | `observability:read` |
404
+ | Method | Path | Purpose | Permission |
405
+ | -------- | ----------------------------------------- | ----------------------------- | ---------------------- |
406
+ | `GET` | `/api/observability/feedback` | List feedback records | None derived |
407
+ | `POST` | `/api/observability/feedback` | Create a feedback record | None derived |
408
+ | `DELETE` | `/api/observability/feedback` | Delete feedback records by id | `observability:delete` |
409
+ | `DELETE` | `/api/observability/scores` | Delete score records by id | `observability:delete` |
410
+ | `POST` | `/api/observability/feedback/aggregate` | Return one aggregate value | `observability:read` |
411
+ | `POST` | `/api/observability/feedback/breakdown` | Group feedback by dimensions | `observability:read` |
412
+ | `POST` | `/api/observability/feedback/timeseries` | Bucket feedback by interval | `observability:read` |
413
+ | `POST` | `/api/observability/feedback/percentiles` | Return percentile series | `observability:read` |
392
414
 
393
415
  ## Related
394
416