@mastra/mcp-docs-server 1.3.7-alpha.7 → 1.3.7-alpha.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (43) hide show
  1. package/.docs/docs/harness/durable-agents.md +12 -0
  2. package/.docs/docs/observability/metrics/overview.md +1 -1
  3. package/.docs/docs/studio/overview.md +1 -1
  4. package/.docs/integrations/observability/opentelemetry.md +11 -5
  5. package/.docs/integrations/sandboxes/e2b.md +4 -9
  6. package/.docs/models/environment-variables.md +1 -0
  7. package/.docs/models/gateways/custom-gateways.md +22 -0
  8. package/.docs/models/gateways/merge-gateway.md +5 -1
  9. package/.docs/models/gateways/netlify.md +5 -4
  10. package/.docs/models/gateways/openrouter.md +6 -4
  11. package/.docs/models/gateways/vercel.md +7 -2
  12. package/.docs/models/index.md +2 -1
  13. package/.docs/models/providers/aimlapi.md +257 -0
  14. package/.docs/models/providers/ambient.md +3 -1
  15. package/.docs/models/providers/deepinfra.md +3 -2
  16. package/.docs/models/providers/digitalocean.md +1 -1
  17. package/.docs/models/providers/edenai.md +328 -312
  18. package/.docs/models/providers/empiriolabs.md +2 -1
  19. package/.docs/models/providers/google.md +2 -1
  20. package/.docs/models/providers/kilo.md +17 -15
  21. package/.docs/models/providers/llmgateway-providers.md +3 -2
  22. package/.docs/models/providers/llmgateway.md +2 -1
  23. package/.docs/models/providers/meta.md +1 -1
  24. package/.docs/models/providers/nano-gpt.md +8 -2
  25. package/.docs/models/providers/nearai.md +1 -1
  26. package/.docs/models/providers/novita-ai.md +3 -2
  27. package/.docs/models/providers/opencode-go.md +5 -4
  28. package/.docs/models/providers/opencode.md +3 -1
  29. package/.docs/models/providers/prime.md +5 -1
  30. package/.docs/models/providers/requesty.md +5 -1
  31. package/.docs/models/providers/standardcompute.md +2 -2
  32. package/.docs/models/providers.md +1 -0
  33. package/.docs/reference/agent-controller/session.md +8 -5
  34. package/.docs/reference/client-js/agent-controller.md +2 -2
  35. package/.docs/reference/core/mastra-model-gateway.md +2 -0
  36. package/.docs/reference/index.md +1 -0
  37. package/.docs/reference/observability/metrics/automatic-metrics.md +1 -1
  38. package/.docs/reference/observability/tracing/bridges/datadog.md +3 -0
  39. package/.docs/reference/observability/tracing/bridges/otel.md +2 -2
  40. package/.docs/reference/observability/tracing/exporters/datadog.md +3 -0
  41. package/.docs/reference/observability/tracing/exporters/langsmith.md +3 -1
  42. package/.docs/reference/workspace/factory-sandbox.md +173 -0
  43. package/package.json +5 -5
package/.docs/models/providers/empiriolabs.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![EmpirioLabs AI logo](https://models.dev/logos/empiriolabs.svg)EmpirioLabs AI
6
6
 
7
- Access 62 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
7
+ Access 63 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
10
10
 
@@ -42,6 +42,7 @@ for await (const chunk of stream) {
42
42
  | `empiriolabs/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.42 | $1 |
43
43
  | `empiriolabs/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
44
44
  | `empiriolabs/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
45
+ | `empiriolabs/fugu-max` | 1.0M | | | | | | $2 | $6 |
45
46
  | `empiriolabs/fugu-ultra-v1-0` | 1.0M | | | | | | $8 | $45 |
46
47
  | `empiriolabs/fugu-ultra-v1-1` | 1.0M | | | | | | $5 | $30 |
47
48
  | `empiriolabs/fugu-ultra-v2-0` | 1.0M | | | | | | $5 | $30 |
package/.docs/models/providers/google.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Google logo](https://models.dev/logos/google.svg)Google
6
6
 
7
- Access 39 Google models through Mastra's model router. Authentication is handled automatically using one of the following environment variables: `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`.
7
+ Access 40 Google models through Mastra's model router. Authentication is handled automatically using one of the following environment variables: `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`.
8
8
 
9
9
  Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
10
10
 
@@ -63,6 +63,7 @@ for await (const chunk of stream) {
63
63
  | `google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
64
64
  | `google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
65
65
  | `google/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
66
+ | `google/gemini-4-argon` | 1.0M | | | | | | $2 | $10 |
66
67
  | `google/gemini-embedding-001` | 2K | | | | | | $0.15 | — |
67
68
  | `google/gemini-embedding-2` | 8K | | | | | | $0.20 | — |
68
69
  | `google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
package/.docs/models/providers/kilo.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
6
6
 
7
- Access 387 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
7
+ Access 389 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Kilo Gateway documentation](https://kilo.ai).
10
10
 
@@ -42,20 +42,20 @@ for await (const chunk of stream) {
42
42
  | `kilo/~anthropic/claude-haiku-latest` | 1.0M | | | | | | $0.10 | $0.50 |
43
43
  | `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $4 | $20 |
44
44
  | `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
45
- | `kilo/~deepseek/deepseek-flash-latest` | 1.0M | | | | | | $0.03 | $1 |
46
- | `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.25 | $0.75 |
47
- | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.01 | $0.77 |
45
+ | `kilo/~deepseek/deepseek-flash-latest` | 1.0M | | | | | | $0.04 | $0.77 |
46
+ | `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.15 | $0.44 |
47
+ | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.01 | $0.58 |
48
48
  | `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
49
49
  | `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
50
- | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $0.73 | $10 |
50
+ | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $0.72 | $24 |
51
51
  | `kilo/~openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
52
52
  | `kilo/~openai/gpt-luna-latest` | 1.1M | | | | | | $0.10 | $0.50 |
53
53
  | `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
54
54
  | `kilo/~openai/gpt-sol-latest` | 1.1M | | | | | | $2 | $10 |
55
55
  | `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
56
56
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
57
- | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.02 | $1 |
58
- | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.06 | $5 |
57
+ | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.03 | $0.90 |
58
+ | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.06 | $4 |
59
59
  | `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
60
60
  | `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
61
61
  | `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -107,7 +107,7 @@ for await (const chunk of stream) {
107
107
  | `kilo/deepseek/deepseek-v3.1-terminus` | 164K | | | | | | $0.27 | $1 |
108
108
  | `kilo/deepseek/deepseek-v3.2` | 164K | | | | | | $0.26 | $0.80 |
109
109
  | `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
110
- | `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.01 | $1 |
110
+ | `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.09 | $0.18 |
111
111
  | `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
112
112
  | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.65 |
113
113
  | `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
@@ -135,10 +135,11 @@ for await (const chunk of stream) {
135
135
  | `kilo/google/gemini-3.6-flash` | 1.0M | | | | | | $0.38 | $2 |
136
136
  | `kilo/google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
137
137
  | `kilo/google/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
138
+ | `kilo/google/gemini-4-argon` | 1.0M | | | | | | $2 | $10 |
138
139
  | `kilo/google/gemini-nano-banana-2.1` | 66K | | | | | | $2 | $8 |
139
140
  | `kilo/google/gemma-2-27b-it` | 8K | | | | | | $0.65 | $0.65 |
140
141
  | `kilo/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
141
- | `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
142
+ | `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.07 | $0.28 |
142
143
  | `kilo/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
143
144
  | `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.04 | $0.22 |
144
145
  | `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.09 | $0.34 |
@@ -150,10 +151,8 @@ for await (const chunk of stream) {
150
151
  | `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
151
152
  | `kilo/inception/mercury-2.5` | 260K | | | | | | $0.20 | $0.75 |
152
153
  | `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
153
- | `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.07 | $0.22 |
154
- | `kilo/inclusionai/ling-3.0-flash-sante` | 262K | | | | | | $0.07 | $0.22 |
155
- | `kilo/inclusionai/ling-3.0-flash-vl` | 262K | | | | | | $0.07 | $0.22 |
156
- | `kilo/inclusionai/ling-3.1-flash` | 262K | | | | | | — | — |
154
+ | `kilo/inclusionai/ling-3.0-flash-vl` | 131K | | | | | | $0.06 | $0.18 |
155
+ | `kilo/inclusionai/ling-3.1-flash` | 262K | | | | | | $0.30 | $0.90 |
157
156
  | `kilo/inference-net/schematron-v2-small` | 128K | | | | | | $0.05 | $0.23 |
158
157
  | `kilo/inference-net/schematron-v2-turbo` | 128K | | | | | | $0.03 | $0.15 |
159
158
  | `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
@@ -162,6 +161,7 @@ for await (const chunk of stream) {
162
161
  | `kilo/kilo-auto/frontier` | 1.0M | | | | | | $5 | $25 |
163
162
  | `kilo/kilo-auto/small` | 262K | | | | | | $0.05 | $0.40 |
164
163
  | `kilo/liquid/lfm-2.5-2.6b:free` | 66K | | | | | | — | — |
164
+ | `kilo/liquid/lfm-2.5-24b-a2b` | 128K | | | | | | $0.05 | $0.70 |
165
165
  | `kilo/mancer/weaver` | 8K | | | | | | $0.40 | $0.75 |
166
166
  | `kilo/meituan/longcat-2.0` | 1.0M | | | | | | $0.75 | $3 |
167
167
  | `kilo/meta-llama/llama-3.1-70b-instruct` | 131K | | | | | | $0.40 | $0.40 |
@@ -187,7 +187,7 @@ for await (const chunk of stream) {
187
187
  | `kilo/minimax/minimax-m2-her` | 66K | | | | | | $0.30 | $1 |
188
188
  | `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
189
189
  | `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
190
- | `kilo/minimax/minimax-m2.7` | 197K | | | | | | $0.30 | $1 |
190
+ | `kilo/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
191
191
  | `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
192
192
  | `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
193
193
  | `kilo/mistralai/devstral-2512` | 262K | | | | | | $0.40 | $2 |
@@ -337,7 +337,7 @@ for await (const chunk of stream) {
337
337
  | `kilo/qwen/qwen3-vl-8b-instruct` | 262K | | | | | | $0.25 | $0.75 |
338
338
  | `kilo/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.26 | $2 |
339
339
  | `kilo/qwen/qwen3.5-27b` | 262K | | | | | | $0.20 | $2 |
340
- | `kilo/qwen/qwen3.5-35b-a3b` | 262K | | | | | | $0.16 | $1 |
340
+ | `kilo/qwen/qwen3.5-35b-a3b` | 256K | | | | | | $0.16 | $1 |
341
341
  | `kilo/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.39 | $2 |
342
342
  | `kilo/qwen/qwen3.5-9b` | 256K | | | | | | $0.10 | $0.15 |
343
343
  | `kilo/qwen/qwen3.5-flash-02-23` | 1.0M | | | | | | $0.07 | $0.26 |
@@ -367,6 +367,8 @@ for await (const chunk of stream) {
367
367
  | `kilo/sao10k/l3-lunaris-8b` | 8K | | | | | | $0.04 | $0.05 |
368
368
  | `kilo/sao10k/l3.1-euryale-70b` | 131K | | | | | | $0.85 | $0.85 |
369
369
  | `kilo/sao10k/l3.3-euryale-70b` | 131K | | | | | | $0.65 | $0.75 |
370
+ | `kilo/scaledown/extract` | 1.0M | | | | | | $0.05 | — |
371
+ | `kilo/scaledown/summarize` | 1.0M | | | | | | $0.05 | — |
370
372
  | `kilo/stealth/claude-opus-4.6` | 1.0M | | | | | | $4 | $20 |
371
373
  | `kilo/stealth/claude-opus-4.7` | 1.0M | | | | | | $4 | $20 |
372
374
  | `kilo/stealth/claude-opus-4.8` | 1.0M | | | | | | $4 | $20 |
package/.docs/models/providers/llmgateway-providers.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
6
6
 
7
- Access 446 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 447 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
 
@@ -216,7 +216,6 @@ for await (const chunk of stream) {
216
216
  | `llmgateway-providers/entrim/deepseek-v4.1-flash` | 1.0M | | | | | | $0.20 | $0.60 |
217
217
  | `llmgateway-providers/entrim/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.35 |
218
218
  | `llmgateway-providers/fireworks/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
219
- | `llmgateway-providers/fireworks/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
220
219
  | `llmgateway-providers/fireworks/deepseek-v4.1-flash` | 1.0M | | | | | | $0.22 | $0.66 |
221
220
  | `llmgateway-providers/fireworks/glm-5.3` | 1.0M | | | | | | $1 | $4 |
222
221
  | `llmgateway-providers/fireworks/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
@@ -236,6 +235,7 @@ for await (const chunk of stream) {
236
235
  | `llmgateway-providers/google-ai-studio/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
237
236
  | `llmgateway-providers/google-ai-studio/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
238
237
  | `llmgateway-providers/google-ai-studio/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
238
+ | `llmgateway-providers/google-ai-studio/gemini-4-argon` | 1.0M | | | | | | $4 | $20 |
239
239
  | `llmgateway-providers/google-ai-studio/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
240
240
  | `llmgateway-providers/google-vertex/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
241
241
  | `llmgateway-providers/google-vertex/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
@@ -248,6 +248,7 @@ for await (const chunk of stream) {
248
248
  | `llmgateway-providers/google-vertex/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
249
249
  | `llmgateway-providers/google-vertex/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
250
250
  | `llmgateway-providers/google-vertex/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
251
+ | `llmgateway-providers/google-vertex/gemini-4-argon` | 1.0M | | | | | | $4 | $20 |
251
252
  | `llmgateway-providers/groq/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.75 |
252
253
  | `llmgateway-providers/groq/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
253
254
  | `llmgateway-providers/inference.net/glm-5.3` | 1.0M | | | | | | $0.90 | $3 |
package/.docs/models/providers/llmgateway.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![DevPass (LLM Gateway) logo](https://models.dev/logos/llmgateway.svg)DevPass (LLM Gateway)
6
6
 
7
- Access 215 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 216 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
10
10
 
@@ -78,6 +78,7 @@ for await (const chunk of stream) {
78
78
  | `llmgateway/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
79
79
  | `llmgateway/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
80
80
  | `llmgateway/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
81
+ | `llmgateway/gemini-4-argon` | 1.0M | | | | | | $4 | $20 |
81
82
  | `llmgateway/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
82
83
  | `llmgateway/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
83
84
  | `llmgateway/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.25 |
package/.docs/models/providers/meta.md CHANGED
@@ -43,7 +43,7 @@ for await (const chunk of stream) {
43
43
  | `meta/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
44
44
  | `meta/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
45
45
  | `meta/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
46
- | `meta/muse-wonder-1.0` | 1.0M | | | | | | — | — |
46
+ | `meta/muse-wonder-1.0` | 1.0M | | | | | | $4 | $20 |
47
47
 
48
48
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
49
49
 
package/.docs/models/providers/nano-gpt.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 611 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 617 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
 
@@ -97,6 +97,7 @@ for await (const chunk of stream) {
97
97
  | `nano-gpt/anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
98
98
  | `nano-gpt/arcee-ai/trinity-large-thinking` | 262K | | | | | | $0.25 | $0.90 |
99
99
  | `nano-gpt/asi1-mini` | 128K | | | | | | $1 | $1 |
100
+ | `nano-gpt/ateron/gemma-4-dark-thoughts-v2-31b` | 66K | | | | | | $0.10 | $0.45 |
100
101
  | `nano-gpt/auto-model` | 1.0M | | | | | | — | — |
101
102
  | `nano-gpt/auto-model-basic` | 1.0M | | | | | | $10 | $20 |
102
103
  | `nano-gpt/auto-model-premium` | 1.0M | | | | | | $10 | $20 |
@@ -139,6 +140,7 @@ for await (const chunk of stream) {
139
140
  | `nano-gpt/deepseek/deepseek-v4-flash-0731:thinking` | 1.0M | | | | | | $0.05 | $0.16 |
140
141
  | `nano-gpt/deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.16 |
141
142
  | `nano-gpt/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
143
+ | `nano-gpt/deepseek/deepseek-v4-flash-vision-exp-cybersecurity` | 1.0M | | | | | | $0.15 | $0.60 |
142
144
  | `nano-gpt/deepseek/deepseek-v4-flash:thinking` | 1.0M | | | | | | $0.14 | $0.28 |
143
145
  | `nano-gpt/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $2 |
144
146
  | `nano-gpt/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
@@ -237,6 +239,7 @@ for await (const chunk of stream) {
237
239
  | `nano-gpt/google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
238
240
  | `nano-gpt/google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
239
241
  | `nano-gpt/google/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
242
+ | `nano-gpt/google/gemini-4-argon` | 1.0M | | | | | | $2 | $10 |
240
243
  | `nano-gpt/google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
241
244
  | `nano-gpt/google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.30 | $3 |
242
245
  | `nano-gpt/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
@@ -347,7 +350,10 @@ for await (const chunk of stream) {
347
350
  | `nano-gpt/nanogpt/coding-router:low` | 1.0M | | | | | | $0.14 | $0.28 |
348
351
  | `nano-gpt/nanogpt/coding-router:max` | 1.0M | | | | | | $5 | $30 |
349
352
  | `nano-gpt/nanogpt/coding-router:medium` | 1.0M | | | | | | $0.14 | $0.28 |
353
+ | `nano-gpt/nbeerbower/gemma4-gutenberg-31b` | 66K | | | | | | $0.10 | $0.45 |
350
354
  | `nano-gpt/NeverSleep/Lumimaid-v0.2-70B` | 16K | | | | | | $1 | $2 |
355
+ | `nano-gpt/nimbz/gemma-4-giftige-blume-31b-v2` | 66K | | | | | | $0.10 | $0.45 |
356
+ | `nano-gpt/nimbz/schattenblume-31b` | 66K | | | | | | $0.10 | $0.45 |
351
357
  | `nano-gpt/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16` | 33K | | | | | | $0.49 | $0.49 |
352
358
  | `nano-gpt/NousResearch/hermes-3-llama-3.1-70b` | 66K | | | | | | $0.41 | $0.41 |
353
359
  | `nano-gpt/NousResearch/hermes-4-405b` | 128K | | | | | | $0.30 | $1 |
@@ -565,7 +571,7 @@ for await (const chunk of stream) {
565
571
  | `nano-gpt/TheDrummer/Cydonia-24B-v2` | 33K | | | | | | $0.10 | $0.12 |
566
572
  | `nano-gpt/TheDrummer/Cydonia-24B-v4` | 33K | | | | | | $0.20 | $0.24 |
567
573
  | `nano-gpt/TheDrummer/Cydonia-24B-v4.1` | 131K | | | | | | $0.35 | $0.55 |
568
- | `nano-gpt/TheDrummer/Cydonia-24B-v4.3` | 33K | | | | | | $0.12 | $0.15 |
574
+ | `nano-gpt/TheDrummer/Cydonia-24B-v4.3` | 131K | | | | | | $0.12 | $0.15 |
569
575
  | `nano-gpt/TheDrummer/Magidonia-24B-v4.3` | 33K | | | | | | $0.10 | $0.12 |
570
576
  | `nano-gpt/TheDrummer/Rocinante-12B-v1.1` | 16K | | | | | | $0.41 | $0.59 |
571
577
  | `nano-gpt/TheDrummer/Skyfall-31B-v4.2` | 16K | | | | | | $0.12 | $0.15 |
package/.docs/models/providers/nearai.md CHANGED
@@ -93,7 +93,7 @@ for await (const chunk of stream) {
93
93
  | `nearai/Qwen/Qwen3.8-27B` | 262K | | | | | | $0.04 | $1 |
94
94
  | `nearai/x-ai/grok-4.6` | 500K | | | | | | $2 | $6 |
95
95
  | `nearai/x-ai/grok-4.7` | 500K | | | | | | $2 | $6 |
96
- | `nearai/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
96
+ | `nearai/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.08 | $0.50 |
97
97
 
98
98
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
99
99
 
package/.docs/models/providers/novita-ai.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Novita AI logo](https://models.dev/logos/novita-ai.svg)Novita AI
6
6
 
7
- Access 84 Novita AI models through Mastra's model router. Authentication is handled automatically using the `NOVITA_API_KEY` environment variable.
7
+ Access 85 Novita AI models through Mastra's model router. Authentication is handled automatically using the `NOVITA_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Novita AI documentation](https://novita.ai/docs/guides/introduction).
10
10
 
@@ -62,7 +62,7 @@ for await (const chunk of stream) {
62
62
  | `novita-ai/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.07 | $0.22 |
63
63
  | `novita-ai/inclusionai/ling-3.0-flash-sante` | 262K | | | | | | $0.07 | $0.22 |
64
64
  | `novita-ai/inclusionai/ling-3.0-flash-vl` | 262K | | | | | | $0.07 | $0.22 |
65
- | `novita-ai/inclusionai/ling-3.1-flash` | 262K | | | | | | — | — |
65
+ | `novita-ai/inclusionai/ling-3.1-flash` | 262K | | | | | | $0.30 | $0.90 |
66
66
  | `novita-ai/meta-llama/llama-3.1-8b-instruct` | 16K | | | | | | $0.02 | $0.05 |
67
67
  | `novita-ai/meta-llama/llama-3.2-1b-instruct` | 131K | | | | | | $0.02 | $0.02 |
68
68
  | `novita-ai/meta-llama/llama-3.3-70b-instruct` | 12K | | | | | | $0.14 | $0.40 |
@@ -104,6 +104,7 @@ for await (const chunk of stream) {
104
104
  | `novita-ai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
105
105
  | `novita-ai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
106
106
  | `novita-ai/stepfun/step-3.7-flash` | 262K | | | | | | $0.20 | $1 |
107
+ | `novita-ai/stepfun/step-5-preview` | 1.0M | | | | | | $1 | $3 |
107
108
  | `novita-ai/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
108
109
  | `novita-ai/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
109
110
  | `novita-ai/xiaomimimo/mimo-v2.5` | 1.0M | | | | | | $0.17 | $0.34 |
package/.docs/models/providers/opencode-go.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![OpenCode Go logo](https://models.dev/logos/opencode-go.svg)OpenCode Go
6
6
 
7
- Access 36 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
7
+ Access 37 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/v2/docs/console/go/).
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/claude-haiku-5-5"
22
+ model: "opencode-go/cat-jam-free"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -38,6 +38,7 @@ 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/cat-jam-free` | 262K | | | | | | — | — |
41
42
  | `opencode-go/claude-haiku-5-5` | 1.0M | | | | | | $0.10 | $0.50 |
42
43
  | `opencode-go/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.60 |
43
44
  | `opencode-go/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.15 | $0.60 |
@@ -82,7 +83,7 @@ const agent = new Agent({
82
83
  name: "custom-agent",
83
84
  model: {
84
85
  url: "https://opencode.ai/inference/go/v1",
85
- id: "opencode-go/claude-haiku-5-5",
86
+ id: "opencode-go/cat-jam-free",
86
87
  apiKey: process.env.OPENCODE_API_KEY,
87
88
  headers: {
88
89
  "X-Custom-Header": "value"
@@ -101,7 +102,7 @@ const agent = new Agent({
101
102
  const useAdvanced = requestContext.task === "complex";
102
103
  return useAdvanced
103
104
  ? "opencode-go/step-5-preview-free"
104
- : "opencode-go/claude-haiku-5-5";
105
+ : "opencode-go/cat-jam-free";
105
106
  }
106
107
  });
107
108
  ```
package/.docs/models/providers/opencode.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![OpenCode logo](https://models.dev/logos/opencode.svg)OpenCode
6
6
 
7
- Access 120 OpenCode models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
7
+ Access 122 OpenCode 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 documentation](https://opencode.ai/v2/docs/console/models/).
10
10
 
@@ -39,6 +39,7 @@ for await (const chunk of stream) {
39
39
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
40
  | ------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
41
  | `opencode/big-pickle` | 200K | | | | | | — | — |
42
+ | `opencode/cat-jam-free` | 262K | | | | | | — | — |
42
43
  | `opencode/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
43
44
  | `opencode/claude-fable-5-1` | 1.0M | | | | | | $10 | $50 |
44
45
  | `opencode/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
@@ -66,6 +67,7 @@ for await (const chunk of stream) {
66
67
  | `opencode/gemini-3.6-flash` | 1.0M | | | | | | $2 | $8 |
67
68
  | `opencode/gemini-3.7-flash` | 1.0M | | | | | | $2 | $8 |
68
69
  | `opencode/gemini-3.8-flash` | 1.0M | | | | | | $2 | $8 |
70
+ | `opencode/gemini-4-argon` | 1.0M | | | | | | $2 | $10 |
69
71
  | `opencode/glm-5` | 205K | | | | | | $1 | $3 |
70
72
  | `opencode/glm-5.1` | 205K | | | | | | $1 | $4 |
71
73
  | `opencode/glm-5.2` | 1.0M | | | | | | $1 | $4 |
package/.docs/models/providers/prime.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Prime Inference logo](https://models.dev/logos/prime.svg)Prime Inference
6
6
 
7
- Access 60 Prime Inference models through Mastra's model router. Authentication is handled automatically using the `PRIME_API_KEY` environment variable.
7
+ Access 64 Prime Inference models through Mastra's model router. Authentication is handled automatically using the `PRIME_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Prime Inference documentation](https://docs.primeintellect.ai).
10
10
 
@@ -62,6 +62,7 @@ for await (const chunk of stream) {
62
62
  | `prime/mistralai/mistral-large-2512` | 262K | | | | | | $0.50 | $2 |
63
63
  | `prime/mistralai/mistral-nemo` | 131K | | | | | | $0.17 | $0.17 |
64
64
  | `prime/mistralai/mistral-small-2603` | 262K | | | | | | $0.17 | $0.66 |
65
+ | `prime/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | $2 | $7 |
65
66
  | `prime/moonshotai/kimi-k2-0905` | 262K | | | | | | $0.60 | $3 |
66
67
  | `prime/moonshotai/kimi-k3` | 1.0M | | | | | | $3 | $17 |
67
68
  | `prime/openai/gpt-4.1` | 1.0M | | | | | | $2 | $8 |
@@ -82,8 +83,11 @@ for await (const chunk of stream) {
82
83
  | `prime/openai/gpt-5.4-pro` | 1.1M | | | | | | $30 | $180 |
83
84
  | `prime/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
84
85
  | `prime/openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
86
+ | `prime/openai/gpt-5.6-luna-pro` | 1.1M | | | | | | $1 | $6 |
85
87
  | `prime/openai/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
88
+ | `prime/openai/gpt-5.6-sol-pro` | 1.1M | | | | | | $5 | $30 |
86
89
  | `prime/openai/gpt-5.6-terra` | 1.1M | | | | | | $3 | $15 |
90
+ | `prime/openai/gpt-5.6-terra-pro` | 1.1M | | | | | | $3 | $15 |
87
91
  | `prime/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
88
92
  | `prime/openai/gpt-6-luna` | 1.1M | | | | | | $0.10 | $0.50 |
89
93
  | `prime/openai/gpt-6-sol` | 1.1M | | | | | | $2 | $10 |
package/.docs/models/providers/requesty.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Requesty logo](https://models.dev/logos/requesty.svg)Requesty
6
6
 
7
- Access 171 Requesty models through Mastra's model router. Authentication is handled automatically using the `REQUESTY_API_KEY` environment variable.
7
+ Access 175 Requesty models through Mastra's model router. Authentication is handled automatically using the `REQUESTY_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Requesty documentation](https://requesty.ai/solution/llm-routing/models).
10
10
 
@@ -97,6 +97,8 @@ for await (const chunk of stream) {
97
97
  | `requesty/gemini-3.7-flash@eu` | 1.0M | | | | | | $0.82 | $4 |
98
98
  | `requesty/gemini-3.8-flash` | 1.0M | | | | | | $0.75 | $4 |
99
99
  | `requesty/gemini-3.8-flash@eu` | 1.0M | | | | | | $0.82 | $4 |
100
+ | `requesty/gemini-4-argon` | 1.0M | | | | | | $2 | $10 |
101
+ | `requesty/gemini-4-argon@eu` | 1.0M | | | | | | $2 | $11 |
100
102
  | `requesty/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
101
103
  | `requesty/gemma-4-31b-it` | 262K | | | | | | — | — |
102
104
  | `requesty/glm-5.1` | 200K | | | | | | $1 | $4 |
@@ -179,6 +181,8 @@ for await (const chunk of stream) {
179
181
  | `requesty/mistral-small-2603` | 256K | | | | | | $0.17 | $0.66 |
180
182
  | `requesty/mistral-small-2603@eu` | 256K | | | | | | $0.17 | $0.66 |
181
183
  | `requesty/muse-glimmer-30b` | 131K | | | | | | — | — |
184
+ | `requesty/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
185
+ | `requesty/muse-wonder-1.0` | 1.0M | | | | | | $4 | $20 |
182
186
  | `requesty/nemotron-3-nano-omni` | 300K | | | | | | $0.06 | $0.24 |
183
187
  | `requesty/nemotron-3-nano-omni-30b-a3b-reasoning` | 131K | | | | | | — | — |
184
188
  | `requesty/nemotron-3-nano-omni@eu` | 300K | | | | | | $0.06 | $0.24 |
package/.docs/models/providers/standardcompute.md CHANGED
@@ -6,7 +6,7 @@
6
6
 
7
7
  Access 1 Standard Compute model through Mastra's model router. Authentication is handled automatically using the `STANDARDCOMPUTE_API_KEY` environment variable.
8
8
 
9
- Learn more in the [Standard Compute documentation](https://standardcompute.com/models).
9
+ Learn more in the [Standard Compute documentation](https://docs.standardcompute.com/models).
10
10
 
11
11
  ```bash
12
12
  STANDARDCOMPUTE_API_KEY=your-api-key
@@ -32,7 +32,7 @@ for await (const chunk of stream) {
32
32
  }
33
33
  ```
34
34
 
35
- > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Standard Compute documentation](https://standardcompute.com/models) for details.
35
+ > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Standard Compute documentation](https://docs.standardcompute.com/models) for details.
36
36
 
37
37
  ## Models
38
38
 
package/.docs/models/providers.md CHANGED
@@ -20,6 +20,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
20
20
  - [AgentRouter](https://mastra.ai/models/providers/agentrouter)
21
21
  - [Agnes AI](https://mastra.ai/models/providers/agnes)
22
22
  - [AI-ROUTER](https://mastra.ai/models/providers/ai-router)
23
+ - [AI/ML API](https://mastra.ai/models/providers/aimlapi)
23
24
  - [ai&](https://mastra.ai/models/providers/aiand)
24
25
  - [AI21 Labs](https://mastra.ai/models/providers/ai21)
25
26
  - [ainetcafe](https://mastra.ai/models/providers/ainetcafe)
package/.docs/reference/agent-controller/session.md CHANGED
@@ -110,20 +110,23 @@ The author persists under `content.metadata.signal.author`. Read it with `getMes
110
110
 
111
111
  Queue a message for the next run, or send it immediately while the session is idle. Author metadata persists with the queued message.
112
112
 
113
- #### `steer({ content, requestContext?, author? })`
113
+ #### `steer({ content, files?, requestContext?, author? })`
114
114
 
115
- Queue steering content into an active run.
115
+ Abort the active run, then send `content` as a new message. Pass `files` to attach files in the same shape as `sendMessage()`: `{ data, mediaType, filename? }`, where `data` is raw text or a base64 data URL for text files, and base64 for binary files.
116
116
 
117
117
  ```typescript
118
118
  await session.steer({ content: 'Focus on the failing tests.' })
119
119
  ```
120
120
 
121
- #### `followUp({ content, requestContext? })`
121
+ #### `followUp({ content, files?, requestContext? })`
122
122
 
123
- Queue a follow-up while a run is active, or send it immediately while idle.
123
+ Queue a follow-up while a run is active, or send it immediately while idle. Pass `files` to attach files the same way as `steer()`.
124
124
 
125
125
  ```typescript
126
- await session.followUp({ content: 'Then propose a fix.' })
126
+ await session.followUp({
127
+ content: 'Then compare against this screenshot.',
128
+ files: [{ data: screenshotBase64, mediaType: 'image/png', filename: 'expected.png' }],
129
+ })
127
130
  ```
128
131
 
129
132
  #### `getCurrentRunId()`
package/.docs/reference/client-js/agent-controller.md CHANGED
@@ -121,11 +121,11 @@ Pass `options.requestContext` to merge custom context into the run's request con
121
121
 
122
122
  ### `steer(message, options?)`
123
123
 
124
- Injects a message into the in-flight run without starting a new turn.
124
+ Aborts the in-flight run, then sends the message as a new turn. Pass a string, or `{ content, files }` to attach files in the same shape as `sendMessage()`.
125
125
 
126
126
  ### `followUp(message, options?)`
127
127
 
128
- Queues a follow-up message. If the session is idle it sends immediately. If a run is active it queues for after the run completes.
128
+ Queues a follow-up message. If the session is idle it sends immediately. If a run is active it queues for after the run completes. Pass a string, or `{ content, files }` to attach files in the same shape as `sendMessage()`.
129
129
 
130
130
  ### `abort()`
131
131
 
package/.docs/reference/core/mastra-model-gateway.md CHANGED
@@ -89,6 +89,8 @@ Fetches provider configurations from the gateway.
89
89
 
90
90
  **docUrl** (`string`): Optional documentation URL
91
91
 
92
+ **pricing** (`Record<string, ModelPricing>`): Prices per model ID in USD per 1 million tokens, with the same keys as a models.dev cost (input, output, cache\_read, cache\_write, reasoning, input\_audio, output\_audio). Optional tiers hold long-context rates. @mastra/observability uses them for cost metrics when models.dev has no price for the model.
93
+
92
94
  ### `buildUrl()`
93
95
 
94
96
  Builds the API URL for a specific model/provider combination.
package/.docs/reference/index.md CHANGED
@@ -431,6 +431,7 @@ The Reference section provides documentation of Mastra's API, including paramete
431
431
  - [.start()](https://mastra.ai/reference/workflows/run-methods/start)
432
432
  - [.startAsync()](https://mastra.ai/reference/workflows/run-methods/startAsync)
433
433
  - [.timeTravel()](https://mastra.ai/reference/workflows/run-methods/timeTravel)
434
+ - [FactorySandbox](https://mastra.ai/reference/workspace/factory-sandbox)
434
435
  - [LocalFilesystem](https://mastra.ai/reference/workspace/local-filesystem)
435
436
  - [LocalSandbox](https://mastra.ai/reference/workspace/local-sandbox)
436
437
  - [PlatformFilesystem](https://mastra.ai/reference/workspace/platform-filesystem)
package/.docs/reference/observability/metrics/automatic-metrics.md CHANGED
@@ -72,7 +72,7 @@ A caller-supplied `costContext` takes precedence over provider-reported costs an
72
72
 
73
73
  ### Where prices come from
74
74
 
75
- The pricing registry uses model prices from [models.dev](https://models.dev). `@mastra/observability` includes a snapshot of these prices, and each new release of the package includes recent prices. Stored cost estimates aren't recalculated when prices change.
75
+ The pricing registry uses model prices from [models.dev](https://models.dev). `@mastra/observability` includes a snapshot of these prices, and each new release of the package includes recent prices. Stored cost estimates aren't recalculated when prices change. A [custom gateway](https://mastra.ai/models/gateways/custom-gateways) can return its own `pricing` for models that models.dev doesn't list. These prices only fill in models that models.dev doesn't price.
76
76
 
77
77
  When you run `mastra dev`, Mastra also refreshes prices from models.dev in the background once a day, and when a model has no price. Cost estimates don't wait for a refresh, so the first call to a newly released model can still have no cost. In other environments, such as production, you can turn on the refresh with `MASTRA_AUTO_REFRESH_PRICING=true`.
78
78
 
package/.docs/reference/observability/tracing/bridges/datadog.md CHANGED
@@ -25,6 +25,7 @@ interface DatadogBridgeConfig extends BaseExporterConfig {
25
25
  env?: string
26
26
  agentless?: boolean
27
27
  integrationsEnabled?: boolean
28
+ flushGraceMs?: number
28
29
  requestContextKeys?: string[]
29
30
  }
30
31
  ```
@@ -74,6 +75,8 @@ async flush(): Promise<void>
74
75
 
75
76
  Force-flushes any buffered LLM Observability data to Datadog without shutting down the bridge. Useful in serverless environments where you need to ensure data is exported before the runtime terminates.
76
77
 
78
+ The flush is best-effort: dd-trace sends LLM Observability data from a background writer and gives no way to await the request, so `flush()` waits `flushGraceMs` (default 2000 ms) after asking dd-trace to flush, then flushes the APM exporter. Each flush that sent new data costs that full wait, so a serverless handler that awaits `flush()` per request pays it per request. Raise it if spans from short-lived processes are missing in Datadog, or set it to `0` to skip the wait when something else keeps the process alive.
79
+
77
80
  ### `shutdown`
78
81
 
79
82
  ```typescript
package/.docs/reference/observability/tracing/bridges/otel.md CHANGED
@@ -56,7 +56,7 @@ If no `LoggerProvider` is registered globally, emission is a silent no-op.
56
56
  async flush(): Promise<void>
57
57
  ```
58
58
 
59
- Force flushes the global OTEL tracer provider and logger provider if they support `forceFlush`. Useful in serverless environments where you need to drain telemetry before the runtime terminates.
59
+ Force flushes the tracer provider and logger provider if they support `forceFlush`. The global providers are resolved at flush time, so a `LoggerProvider` registered after the bridge was constructed is flushed too. Useful in serverless environments where you need to drain telemetry before the runtime terminates. Your OTEL SDK may still hold a batch it has already started exporting; call `sdk.shutdown()` as well before the process exits; the provider's own `forceFlush()` doesn't wait for that batch either.
60
60
 
61
61
  ### `shutdown`
62
62
 
@@ -64,7 +64,7 @@ Force flushes the global OTEL tracer provider and logger provider if they suppor
64
64
  async shutdown(): Promise<void>
65
65
  ```
66
66
 
67
- Shuts down the bridge and cleans up resources. Ends any spans that weren't properly closed.
67
+ Shuts down the bridge and cleans up resources. Ends any spans that weren't properly closed, then flushes the providers so those spans are exported.
68
68
 
69
69
  ## Usage examples
70
70
 
package/.docs/reference/observability/tracing/exporters/datadog.md CHANGED
@@ -25,6 +25,7 @@ interface DatadogExporterConfig extends BaseExporterConfig {
25
25
  env?: string
26
26
  agentless?: boolean
27
27
  integrationsEnabled?: boolean
28
+ flushGraceMs?: number
28
29
  }
29
30
  ```
30
31
 
@@ -51,6 +52,8 @@ async flush(): Promise<void>
51
52
 
52
53
  Force flushes any buffered spans to Datadog without shutting down the exporter. Useful in serverless environments where you need to ensure spans are exported before the runtime terminates.
53
54
 
55
+ The flush is best-effort: dd-trace sends LLM Observability data from a background writer and gives no way to await the request, so `flush()` waits `flushGraceMs` (default 2000 ms) after asking dd-trace to flush. Each flush that sent new data costs that full wait, so a serverless handler that awaits `flush()` per request pays it per request. Raise it if spans from short-lived processes are missing in Datadog, or set it to `0` to skip the wait when something else keeps the process alive.
56
+
54
57
  ### shutdown
55
58
 
56
59
  ```typescript