@mastra/mcp-docs-server 1.2.25-alpha.1 → 1.2.25-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.
@@ -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 7122 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 7130 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 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.
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.
8
8
 
9
9
  Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
10
10
 
@@ -64,7 +64,6 @@ 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 |
68
67
  | `cloudflare-workers-ai/@cf/zai-org/glm-5.3-flash` | 1.3M | | | | | | $0.15 | $0.50 |
69
68
 
70
69
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
@@ -95,7 +95,7 @@ for await (const chunk of stream) {
95
95
  | `crossmodel/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
96
96
  | `crossmodel/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
97
97
  | `crossmodel/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
98
- | `crossmodel/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
98
+ | `crossmodel/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
99
99
 
100
100
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
101
101
 
@@ -145,8 +145,8 @@ for await (const chunk of stream) {
145
145
  | `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
146
146
  | `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
147
147
  | `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
148
- | `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
149
- | `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
148
+ | `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.76 | $0.76 |
149
+ | `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.76 |
150
150
  | `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
151
151
  | `edenai/minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
152
152
  | `edenai/minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
@@ -216,8 +216,8 @@ for await (const chunk of stream) {
216
216
  | `edenai/perplexityai/sonar-deep-research` | 128K | | | | | | $2 | $8 |
217
217
  | `edenai/perplexityai/sonar-pro` | 200K | | | | | | $3 | $15 |
218
218
  | `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
219
- | `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.35 | $1 |
220
- | `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
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 |
221
221
  | `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
222
222
  | `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
223
223
  | `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
@@ -240,7 +240,7 @@ for await (const chunk of stream) {
240
240
  | `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
241
241
  | `edenai/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
242
242
  | `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
243
- | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
243
+ | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.47 | $0.93 |
244
244
  | `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
245
245
  | `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
246
246
  | `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
@@ -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 |
@@ -48,7 +48,7 @@ for await (const chunk of stream) {
48
48
  | `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
49
49
  | `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
50
50
  | `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
51
- | `hyper/gpt-oss-120b` | 128K | | | | | | $0.18 | $0.68 |
51
+ | `hyper/gpt-oss-120b` | 128K | | | | | | $0.18 | $0.61 |
52
52
  | `hyper/inkling` | 1.0M | | | | | | $1 | $4 |
53
53
  | `hyper/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
54
54
  | `hyper/kimi-k2.5` | 262K | | | | | | $0.56 | $3 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
6
6
 
7
- Access 367 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
7
+ Access 366 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
 
@@ -49,7 +49,7 @@ for await (const chunk of stream) {
49
49
  | `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
50
50
  | `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
51
51
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
52
- | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
52
+ | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.23 |
53
53
  | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $1 | $3 |
54
54
  | `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
55
55
  | `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
@@ -211,7 +211,6 @@ for await (const chunk of stream) {
211
211
  | `kilo/nousresearch/hermes-3-llama-3.1-405b` | 131K | | | | | | $1 | $1 |
212
212
  | `kilo/nousresearch/hermes-3-llama-3.1-70b` | 131K | | | | | | $0.70 | $0.70 |
213
213
  | `kilo/nousresearch/hermes-4-405b` | 131K | | | | | | $1 | $3 |
214
- | `kilo/nousresearch/hermes-4-70b` | 131K | | | | | | $0.13 | $0.40 |
215
214
  | `kilo/nvidia/nemotron-3-nano-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
216
215
  | `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
217
216
  | `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.09 | $0.40 |
@@ -369,7 +368,7 @@ for await (const chunk of stream) {
369
368
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
370
369
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
371
370
  | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
372
- | `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
371
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
373
372
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
374
373
  | `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
375
374
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
@@ -347,13 +347,13 @@ for await (const chunk of stream) {
347
347
  | `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
348
348
  | `llmgateway-providers/runware/kimi-k3` | 1.0M | | | | | | $3 | $15 |
349
349
  | `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
350
- | `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.55 | $2 |
351
- | `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $6 |
350
+ | `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
351
+ | `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
352
352
  | `llmgateway-providers/scx-ai-gp/glm-5.3` | 1.0M | | | | | | $1 | $4 |
353
- | `llmgateway-providers/scx-ai-gp/glm-5.3-flash` | 1.0M | | | | | | $0.13 | $0.40 |
354
- | `llmgateway-providers/scx-ai-gp/kimi-k2.7-code` | 262K | | | | | | $0.89 | $4 |
355
- | `llmgateway-providers/scx-ai-gp/kimi-k3` | 1.0M | | | | | | $3 | $14 |
356
- | `llmgateway-providers/scx-ai-gp/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
353
+ | `llmgateway-providers/scx-ai-gp/glm-5.3-flash` | 1.0M | | | | | | $0.09 | $0.25 |
354
+ | `llmgateway-providers/scx-ai-gp/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
355
+ | `llmgateway-providers/scx-ai-gp/kimi-k3` | 1.0M | | | | | | $4 | $18 |
356
+ | `llmgateway-providers/scx-ai-gp/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
357
357
  | `llmgateway-providers/scx-ai/gemma-4-31b-it` | 131K | | | | | | $0.30 | $0.91 |
358
358
  | `llmgateway-providers/scx-ai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.55 |
359
359
  | `llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct` | 131K | | | | | | $0.53 | $2 |
@@ -89,10 +89,10 @@ for await (const chunk of stream) {
89
89
  | `llmgateway/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.40 |
90
90
  | `llmgateway/glm-5` | 203K | | | | | | $0.72 | $2 |
91
91
  | `llmgateway/glm-5.1` | 205K | | | | | | $0.93 | $3 |
92
- | `llmgateway/glm-5.2` | 1.0M | | | | | | $0.55 | $2 |
93
- | `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $6 |
92
+ | `llmgateway/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
93
+ | `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
94
94
  | `llmgateway/glm-5.3` | 1.0M | | | | | | $1 | $4 |
95
- | `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
95
+ | `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.09 | $0.25 |
96
96
  | `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
97
97
  | `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
98
98
  | `llmgateway/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
@@ -142,9 +142,9 @@ for await (const chunk of stream) {
142
142
  | `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
143
143
  | `llmgateway/kimi-k2.5` | 262K | | | | | | $0.41 | $2 |
144
144
  | `llmgateway/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
145
- | `llmgateway/kimi-k2.7-code` | 262K | | | | | | $0.89 | $4 |
145
+ | `llmgateway/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
146
146
  | `llmgateway/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
147
- | `llmgateway/kimi-k3` | 1.0M | | | | | | $3 | $14 |
147
+ | `llmgateway/kimi-k3` | 1.0M | | | | | | $3 | $15 |
148
148
  | `llmgateway/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
149
149
  | `llmgateway/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
150
150
  | `llmgateway/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
@@ -214,7 +214,7 @@ for await (const chunk of stream) {
214
214
  | `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
215
215
  | `llmgateway/Qwen3.8-27B` | 33K | | | | | | $0.20 | $2 |
216
216
  | `llmgateway/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
217
- | `llmgateway/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
217
+ | `llmgateway/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
218
218
  | `llmgateway/qwen35-397b-a17b` | 262K | | | | | | $0.60 | $4 |
219
219
  | `llmgateway/seed-1-6-250615` | 256K | | | | | | $0.25 | $2 |
220
220
  | `llmgateway/seed-1-6-250915` | 256K | | | | | | $0.25 | $2 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 584 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 591 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
 
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
42
42
  | `nano-gpt/abliteration-ai/abliterated-model` | 262K | | | | | | $3 | $3 |
43
43
  | `nano-gpt/abliteration-ai/abliterated-model-large` | 1.0M | | | | | | $5 | $5 |
44
44
  | `nano-gpt/abliteration-ai/abliterated-model-large-v2` | 1.0M | | | | | | $5 | $5 |
45
+ | `nano-gpt/agnes-3.0-flash` | 524K | | | | | | $0.05 | $0.15 |
45
46
  | `nano-gpt/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
46
47
  | `nano-gpt/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
47
48
  | `nano-gpt/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -154,6 +155,7 @@ for await (const chunk of stream) {
154
155
  | `nano-gpt/deepseek/deepseek-v4-pro-0813:thinking` | 1.0M | | | | | | $1 | $3 |
155
156
  | `nano-gpt/deepseek/deepseek-v4-pro:thinking` | 1.0M | | | | | | $1 | $2 |
156
157
  | `nano-gpt/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.16 | $0.31 |
158
+ | `nano-gpt/deepseek/deepseek-v4.1-flash:thinking` | 1.0M | | | | | | $0.16 | $0.31 |
157
159
  | `nano-gpt/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond` | 33K | | | | | | $0.49 | $0.49 |
158
160
  | `nano-gpt/doubao-1.5-pro-256k` | 256K | | | | | | $0.80 | $1 |
159
161
  | `nano-gpt/doubao-1.5-pro-32k` | 32K | | | | | | $0.13 | $0.33 |
@@ -201,6 +203,8 @@ for await (const chunk of stream) {
201
203
  | `nano-gpt/gemini-3-pro-image-preview` | 66K | | | | | | $2 | $12 |
202
204
  | `nano-gpt/gemini-exp-1206` | 2.1M | | | | | | $1 | $5 |
203
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 |
204
208
  | `nano-gpt/gemma-4-26b-a4b-it-chimerax` | 262K | | | | | | $0.12 | $0.38 |
205
209
  | `nano-gpt/gemma-4-26b-a4b-it-darksoul` | 262K | | | | | | $0.12 | $0.38 |
206
210
  | `nano-gpt/gemma-4-26b-a4b-it-luminous` | 262K | | | | | | $0.12 | $0.38 |
@@ -268,8 +272,10 @@ for await (const chunk of stream) {
268
272
  | `nano-gpt/ibm-granite/granite-4.2-8b` | 131K | | | | | | $0.10 | $0.15 |
269
273
  | `nano-gpt/inception/mercury-2.5-preview` | 260K | | | | | | $0.04 | $0.15 |
270
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 |
271
276
  | `nano-gpt/inclusionai/ling-3.0-flash:thinking` | 262K | | | | | | $0.07 | $0.22 |
272
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 |
273
279
  | `nano-gpt/kimi-k2-instruct-fast` | 131K | | | | | | $0.40 | $2 |
274
280
  | `nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3` | 33K | | | | | | $0.70 | $0.70 |
275
281
  | `nano-gpt/liquid/lfm-2.5-2.6b` | 128K | | | | | | $0.10 | $0.20 |
@@ -456,6 +462,7 @@ for await (const chunk of stream) {
456
462
  | `nano-gpt/qwen/qwen3.8-27b-fable` | 262K | | | | | | $0.25 | $2 |
457
463
  | `nano-gpt/qwen/qwen3.8-27b-obliterated` | 262K | | | | | | $0.25 | $2 |
458
464
  | `nano-gpt/qwen/qwen3.8-27b-obliterated:thinking` | 262K | | | | | | $0.25 | $2 |
465
+ | `nano-gpt/qwen/qwen3.8-27b-queen` | 262K | | | | | | $0.25 | $2 |
459
466
  | `nano-gpt/qwen/qwen3.8-27b-uncensored` | 262K | | | | | | $0.25 | $2 |
460
467
  | `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking` | 262K | | | | | | $0.25 | $2 |
461
468
  | `nano-gpt/qwen25-vl-72b-instruct` | 32K | | | | | | $0.70 | $0.70 |
@@ -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
  ```
@@ -44,7 +44,7 @@ for await (const chunk of stream) {
44
44
  | `opencode-go/glm-5.1` | 203K | | | | | | $1 | $4 |
45
45
  | `opencode-go/glm-5.2` | 1.0M | | | | | | $1 | $4 |
46
46
  | `opencode-go/glm-5.3` | 1.0M | | | | | | $1 | $4 |
47
- | `opencode-go/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
47
+ | `opencode-go/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
48
48
  | `opencode-go/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
49
49
  | `opencode-go/grok-4.6` | 500K | | | | | | $2 | $6 |
50
50
  | `opencode-go/hy3` | 256K | | | | | | $0.14 | $0.58 |
@@ -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:
@@ -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