@mastra/mcp-docs-server 1.2.25 → 1.2.26-alpha.11

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 (79) hide show
  1. package/.docs/docs/agents/overview.md +1 -1
  2. package/.docs/docs/agents/processors.md +21 -0
  3. package/.docs/docs/connections/connect-mcp-client.md +211 -0
  4. package/.docs/docs/deployment/mastra-server.md +8 -2
  5. package/.docs/docs/deployment/monorepo.md +12 -0
  6. package/.docs/docs/evals/datasets.md +5 -1
  7. package/.docs/docs/guides/context-engineering.md +1 -1
  8. package/.docs/docs/harness/background-tasks.md +30 -24
  9. package/.docs/docs/harness/signals.md +39 -0
  10. package/.docs/docs/index.md +1 -1
  11. package/.docs/docs/memory/message-history.md +6 -2
  12. package/.docs/docs/subagents.md +25 -0
  13. package/.docs/integrations/agentic-ui/ai-sdk-ui.md +7 -0
  14. package/.docs/integrations/file-storage/amazon-s3.md +7 -1
  15. package/.docs/integrations/file-storage/archil.md +3 -3
  16. package/.docs/integrations/frameworks/electron.md +1 -1
  17. package/.docs/integrations/observability/langfuse.md +11 -1
  18. package/.docs/integrations/sandboxes/cloudflare-sandbox.md +2 -0
  19. package/.docs/integrations/sandboxes/daytona.md +33 -0
  20. package/.docs/integrations/sandboxes/docker.md +13 -0
  21. package/.docs/integrations/voice/livekit.md +26 -2
  22. package/.docs/models/gateways/merge-gateway.md +7 -1
  23. package/.docs/models/gateways/netlify.md +5 -1
  24. package/.docs/models/gateways/openrouter.md +11 -2
  25. package/.docs/models/gateways/vercel.md +1 -1
  26. package/.docs/models/index.md +1 -1
  27. package/.docs/models/providers/above.md +2 -3
  28. package/.docs/models/providers/agentrouter.md +8 -6
  29. package/.docs/models/providers/alibaba-token-plan-cn.md +0 -1
  30. package/.docs/models/providers/alibaba-token-plan.md +0 -1
  31. package/.docs/models/providers/baseten.md +2 -1
  32. package/.docs/models/providers/bothub.md +10 -4
  33. package/.docs/models/providers/cline-pass.md +18 -17
  34. package/.docs/models/providers/cortecs.md +3 -3
  35. package/.docs/models/providers/deepinfra.md +7 -5
  36. package/.docs/models/providers/deepseek.md +7 -6
  37. package/.docs/models/providers/digitalocean.md +1 -1
  38. package/.docs/models/providers/edenai.md +27 -4
  39. package/.docs/models/providers/empiriolabs.md +3 -1
  40. package/.docs/models/providers/fireworks-ai.md +3 -1
  41. package/.docs/models/providers/greenpt.md +2 -1
  42. package/.docs/models/providers/huggingface.md +5 -1
  43. package/.docs/models/providers/hyper.md +6 -5
  44. package/.docs/models/providers/inception.md +2 -1
  45. package/.docs/models/providers/kilo.md +24 -16
  46. package/.docs/models/providers/llmgateway-providers.md +34 -2
  47. package/.docs/models/providers/llmgateway.md +9 -3
  48. package/.docs/models/providers/nan.md +1 -1
  49. package/.docs/models/providers/nano-gpt.md +20 -13
  50. package/.docs/models/providers/nvidia.md +3 -2
  51. package/.docs/models/providers/ofox.md +31 -3
  52. package/.docs/models/providers/ollama-cloud.md +3 -1
  53. package/.docs/models/providers/opencode-go.md +4 -4
  54. package/.docs/models/providers/pioneer.md +11 -2
  55. package/.docs/models/providers/requesty.md +4 -4
  56. package/.docs/models/providers/scnet-token-plan.md +4 -6
  57. package/.docs/models/providers/togetherai.md +2 -1
  58. package/.docs/models/providers/volcengine-coding-plan.md +3 -1
  59. package/.docs/reference/agents/agent.md +47 -1
  60. package/.docs/reference/agents/generate.md +2 -0
  61. package/.docs/reference/ai-sdk/to-ai-sdk-messages.md +16 -0
  62. package/.docs/reference/cli/mastra.md +28 -0
  63. package/.docs/reference/client-js/datasets.md +1 -1
  64. package/.docs/reference/configuration.md +2 -2
  65. package/.docs/reference/datasets/purgeItem.md +3 -3
  66. package/.docs/reference/index.md +3 -0
  67. package/.docs/reference/memory/cloneThread.md +2 -0
  68. package/.docs/reference/memory/copyThread.md +65 -0
  69. package/.docs/reference/memory/memory-class.md +2 -1
  70. package/.docs/reference/memory/recall.md +51 -0
  71. package/.docs/reference/memory/updateThreadResourceId.md +46 -0
  72. package/.docs/reference/processors/agents-md-injector.md +55 -0
  73. package/.docs/reference/processors/processor-interface.md +2 -0
  74. package/.docs/reference/pubsub/redis-streams.md +6 -0
  75. package/.docs/reference/pubsub/valkey-streams.md +6 -0
  76. package/.docs/reference/streaming/agents/stream.md +30 -0
  77. package/.docs/reference/tools/mcp-server.md +28 -0
  78. package/.docs/reference/workspace/filesystem.md +72 -0
  79. package/package.json +5 -5
package/.docs/models/providers/deepseek.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![DeepSeek logo](https://models.dev/logos/deepseek.svg)DeepSeek
6
6
 
7
- Access 3 DeepSeek models through Mastra's model router. Authentication is handled automatically using the `DEEPSEEK_API_KEY` environment variable.
7
+ Access 4 DeepSeek models through Mastra's model router. Authentication is handled automatically using the `DEEPSEEK_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [DeepSeek documentation](https://api-docs.deepseek.com/quick_start/pricing).
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: "deepseek/deepseek-v4-flash"
22
+ model: "deepseek/deepseek-flash"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -36,8 +36,9 @@ for await (const chunk of stream) {
36
36
 
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
- | `deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
40
- | `deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.14 | $0.28 |
39
+ | `deepseek/deepseek-flash` | 1.0M | | | | | | $0.15 | $0.60 |
40
+ | `deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.60 |
41
+ | `deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.15 | $0.60 |
41
42
  | `deepseek/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
42
43
 
43
44
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
@@ -52,7 +53,7 @@ const agent = new Agent({
52
53
  name: "custom-agent",
53
54
  model: {
54
55
  url: "https://api.deepseek.com",
55
- id: "deepseek/deepseek-v4-flash",
56
+ id: "deepseek/deepseek-flash",
56
57
  apiKey: process.env.DEEPSEEK_API_KEY,
57
58
  headers: {
58
59
  "X-Custom-Header": "value"
@@ -71,7 +72,7 @@ const agent = new Agent({
71
72
  const useAdvanced = requestContext.task === "complex";
72
73
  return useAdvanced
73
74
  ? "deepseek/deepseek-v4-pro"
74
- : "deepseek/deepseek-v4-flash";
75
+ : "deepseek/deepseek-flash";
75
76
  }
76
77
  });
77
78
  ```
package/.docs/models/providers/digitalocean.md CHANGED
@@ -74,7 +74,7 @@ for await (const chunk of stream) {
74
74
  | `digitalocean/glm-5` | 64K | | | | | | $1 | $3 |
75
75
  | `digitalocean/glm-5.1` | 164K | | | | | | $1 | $4 |
76
76
  | `digitalocean/glm-5.2` | 262K | | | | | | $0.70 | $2 |
77
- | `digitalocean/glm-5.3` | 1.0M | | | | | | $1 | $4 |
77
+ | `digitalocean/glm-5.3` | 1.0M | | | | | | $0.95 | $3 |
78
78
  | `digitalocean/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
79
79
  | `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
80
80
  | `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
package/.docs/models/providers/edenai.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Eden AI logo](https://models.dev/logos/edenai.svg)Eden AI
6
6
 
7
- Access 259 Eden AI models through Mastra's model router. Authentication is handled automatically using the `EDENAI_API_KEY` environment variable.
7
+ Access 282 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
 
@@ -44,10 +44,22 @@ for await (const chunk of stream) {
44
44
  | `edenai/amazon/amazon.nova-micro-v1:0@us` | 128K | | | | | | $0.04 | $0.14 |
45
45
  | `edenai/amazon/amazon.nova-pro-v1:0` | 300K | | | | | | $0.80 | $3 |
46
46
  | `edenai/amazon/amazon.nova-pro-v1:0@us` | 300K | | | | | | $0.80 | $3 |
47
+ | `edenai/amazon/google.gemma-3-12b-it` | 128K | | | | | | $0.09 | $0.29 |
48
+ | `edenai/amazon/google.gemma-3-12b-it@us` | 128K | | | | | | $0.09 | $0.29 |
49
+ | `edenai/amazon/google.gemma-3-27b-it` | 128K | | | | | | $0.23 | $0.38 |
50
+ | `edenai/amazon/google.gemma-3-27b-it@us` | 128K | | | | | | $0.23 | $0.38 |
51
+ | `edenai/amazon/google.gemma-3-4b-it` | 128K | | | | | | $0.04 | $0.08 |
52
+ | `edenai/amazon/google.gemma-3-4b-it@us` | 128K | | | | | | $0.04 | $0.08 |
47
53
  | `edenai/amazon/mistral.pixtral-large-2502-v1:0` | 128K | | | | | | $2 | $6 |
48
54
  | `edenai/amazon/mistral.pixtral-large-2502-v1:0@us` | 128K | | | | | | $2 | $6 |
55
+ | `edenai/amazon/mistral.voxtral-mini-3b-2507` | 128K | | | | | | $0.04 | $0.04 |
56
+ | `edenai/amazon/mistral.voxtral-mini-3b-2507@us` | 128K | | | | | | $0.04 | $0.04 |
57
+ | `edenai/amazon/mistral.voxtral-small-24b-2507` | 128K | | | | | | $0.10 | $0.30 |
58
+ | `edenai/amazon/mistral.voxtral-small-24b-2507@us` | 128K | | | | | | $0.10 | $0.30 |
49
59
  | `edenai/amazon/moonshot.kimi-k2-thinking` | 128K | | | | | | $0.60 | $3 |
50
60
  | `edenai/amazon/moonshotai.kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
61
+ | `edenai/amazon/openai.gpt-oss-safeguard-20b` | 128K | | | | | | $0.07 | $0.20 |
62
+ | `edenai/amazon/openai.gpt-oss-safeguard-20b@us` | 128K | | | | | | $0.07 | $0.20 |
51
63
  | `edenai/amazon/zai.glm-4.7-flash` | 200K | | | | | | $0.07 | $0.40 |
52
64
  | `edenai/amazon/zai.glm-4.7-flash@us` | 200K | | | | | | $0.07 | $0.40 |
53
65
  | `edenai/anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
@@ -94,6 +106,10 @@ for await (const chunk of stream) {
94
106
  | `edenai/deepinfra/deepseek-ai/DeepSeek-V3-0324` | 164K | | | | | | $0.24 | $0.90 |
95
107
  | `edenai/deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.06 | $0.18 |
96
108
  | `edenai/deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $3 |
109
+ | `edenai/deepinfra/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.20 | $0.60 |
110
+ | `edenai/deepinfra/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
111
+ | `edenai/deepinfra/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
112
+ | `edenai/deepinfra/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
97
113
  | `edenai/deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct` | 131K | | | | | | $0.34 | $0.34 |
98
114
  | `edenai/deepinfra/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.10 | $0.32 |
99
115
  | `edenai/deepinfra/meta-llama/Llama-Guard-3-8B` | 131K | | | | | | $0.06 | $0.06 |
@@ -145,8 +161,10 @@ for await (const chunk of stream) {
145
161
  | `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
146
162
  | `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
147
163
  | `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
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 |
164
+ | `edenai/groq/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
165
+ | `edenai/infomaniak/mistralai/Ministral-3-14B-Instruct-2512` | 100K | | | | | | $0.35 | $0.46 |
166
+ | `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
167
+ | `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
150
168
  | `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
151
169
  | `edenai/minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
152
170
  | `edenai/minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
@@ -170,6 +188,7 @@ for await (const chunk of stream) {
170
188
  | `edenai/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
171
189
  | `edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
172
190
  | `edenai/nebius/deepseek-ai/DeepSeek-V4-Pro-0813` | 979K | | | | | | $1 | $4 |
191
+ | `edenai/nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
173
192
  | `edenai/nebius/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.13 | $0.40 |
174
193
  | `edenai/nebius/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.30 | $0.90 |
175
194
  | `edenai/nebius/nvidia/Nemotron-3-Ultra-550b-a55b` | 1.0M | | | | | | $1 | $3 |
@@ -219,6 +238,7 @@ for await (const chunk of stream) {
219
238
  | `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
220
239
  | `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.35 | $1 |
221
240
  | `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
241
+ | `edenai/qwen/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
222
242
  | `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
223
243
  | `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
224
244
  | `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
@@ -241,14 +261,17 @@ for await (const chunk of stream) {
241
261
  | `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
242
262
  | `edenai/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
243
263
  | `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
244
- | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.47 | $0.93 |
264
+ | `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
265
+ | `edenai/scaleway/gemma-3-27b-it` | 40K | | | | | | $0.29 | $0.57 |
245
266
  | `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
246
267
  | `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
247
268
  | `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
248
269
  | `edenai/tensorx/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
270
+ | `edenai/tensorx/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.50 | $2 |
249
271
  | `edenai/tensorx/moonshotai/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
250
272
  | `edenai/together_ai/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
251
273
  | `edenai/together_ai/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
274
+ | `edenai/together_ai/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
252
275
  | `edenai/together_ai/meta-models/Muse-Glimmer-30B` | 131K | | | | | | $0.35 | $2 |
253
276
  | `edenai/together_ai/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
254
277
  | `edenai/together_ai/openai/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
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 58 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
7
+ Access 60 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
 
@@ -45,6 +45,8 @@ for await (const chunk of stream) {
45
45
  | `empiriolabs/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
46
46
  | `empiriolabs/fugu-ultra-v1-0` | 1.0M | | | | | | $8 | $45 |
47
47
  | `empiriolabs/fugu-ultra-v1-1` | 1.0M | | | | | | $5 | $30 |
48
+ | `empiriolabs/fugu-ultra-v2-0` | 1.0M | | | | | | $5 | $30 |
49
+ | `empiriolabs/gemma-3-27b` | 128K | | | | | | — | — |
48
50
  | `empiriolabs/gemma-4-26b-a4b` | 262K | | | | | | $0.05 | $0.29 |
49
51
  | `empiriolabs/glm-4-5-flash` | 200K | | | | | | — | — |
50
52
  | `empiriolabs/glm-4-6v-flash` | 128K | | | | | | — | — |
package/.docs/models/providers/fireworks-ai.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Fireworks AI logo](https://models.dev/logos/fireworks-ai.svg)Fireworks AI
6
6
 
7
- Access 21 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
7
+ Access 23 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
10
10
 
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
41
41
  | `fireworks-ai/accounts/fireworks/models/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.22 | $0.66 |
42
42
  | `fireworks-ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
43
43
  | `fireworks-ai/accounts/fireworks/models/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
44
+ | `fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash` | 1.0M | | | | | | $0.22 | $0.66 |
44
45
  | `fireworks-ai/accounts/fireworks/models/glm-5p2` | 1.0M | | | | | | $1 | $4 |
45
46
  | `fireworks-ai/accounts/fireworks/models/glm-5p3` | 1.0M | | | | | | $1 | $4 |
46
47
  | `fireworks-ai/accounts/fireworks/models/glm-5p3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
@@ -50,6 +51,7 @@ for await (const chunk of stream) {
50
51
  | `fireworks-ai/accounts/fireworks/models/kimi-k2p7-code` | 262K | | | | | | $0.95 | $4 |
51
52
  | `fireworks-ai/accounts/fireworks/models/kimi-k3` | 1.0M | | | | | | $3 | $15 |
52
53
  | `fireworks-ai/accounts/fireworks/models/minimax-m3` | 512K | | | | | | $0.30 | $1 |
54
+ | `fireworks-ai/accounts/fireworks/models/mistral-large-3-fp8` | 262K | | | | | | — | — |
53
55
  | `fireworks-ai/accounts/fireworks/models/muse-glimmer-30b` | 131K | | | | | | $0.35 | $2 |
54
56
  | `fireworks-ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4` | 262K | | | | | | $0.60 | $2 |
55
57
  | `fireworks-ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
package/.docs/models/providers/greenpt.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![GreenPT logo](https://models.dev/logos/greenpt.svg)GreenPT
6
6
 
7
- Access 39 GreenPT models through Mastra's model router. Authentication is handled automatically using the `GREENPT_API_KEY` environment variable.
7
+ Access 40 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
 
@@ -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
  | `greenpt/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.16 | $0.40 |
42
+ | `greenpt/deepseek-v4.1-flash` | 1.0M | | | | | | $0.26 | $1 |
42
43
  | `greenpt/devstral-2-123b-instruct-2512` | 200K | | | | | | $0.57 | $3 |
43
44
  | `greenpt/gemma-3-27b-it` | 40K | | | | | | $0.34 | $0.68 |
44
45
  | `greenpt/gemma4` | 262K | | | | | | $0.57 | $2 |
package/.docs/models/providers/huggingface.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
6
6
 
7
- Access 73 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
7
+ Access 77 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
8
8
 
9
9
  Learn more in the [Hugging Face documentation](https://huggingface.co).
10
10
 
@@ -49,6 +49,10 @@ for await (const chunk of stream) {
49
49
  | `huggingface/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
50
50
  | `huggingface/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $0.43 | $0.87 |
51
51
  | `huggingface/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
52
+ | `huggingface/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
53
+ | `huggingface/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
54
+ | `huggingface/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
55
+ | `huggingface/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
52
56
  | `huggingface/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.13 | $0.40 |
53
57
  | `huggingface/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
54
58
  | `huggingface/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.06 | $0.06 |
package/.docs/models/providers/hyper.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Charm Hyper logo](https://models.dev/logos/hyper.svg)Charm Hyper
6
6
 
7
- Access 33 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
7
+ Access 34 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
10
10
 
@@ -42,13 +42,14 @@ for await (const chunk of stream) {
42
42
  | `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
43
43
  | `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
44
44
  | `hyper/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
45
- | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.37 |
45
+ | `hyper/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
46
+ | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.10 | $0.36 |
46
47
  | `hyper/glm-5` | 203K | | | | | | $0.86 | $3 |
47
48
  | `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
48
49
  | `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
49
50
  | `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
50
51
  | `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
51
- | `hyper/gpt-oss-120b` | 128K | | | | | | $0.18 | $0.61 |
52
+ | `hyper/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.66 |
52
53
  | `hyper/inkling` | 1.0M | | | | | | $1 | $4 |
53
54
  | `hyper/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
54
55
  | `hyper/kimi-k2.5` | 262K | | | | | | $0.56 | $3 |
@@ -56,8 +57,8 @@ for await (const chunk of stream) {
56
57
  | `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
57
58
  | `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
58
59
  | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
59
- | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.90 |
60
- | `hyper/minimax-m2.7` | 262K | | | | | | $0.46 | $2 |
60
+ | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.26 | $0.84 |
61
+ | `hyper/minimax-m2.7` | 262K | | | | | | $0.40 | $1 |
61
62
  | `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
62
63
  | `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
63
64
  | `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
package/.docs/models/providers/inception.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Inception logo](https://models.dev/logos/inception.svg)Inception
6
6
 
7
- Access 2 Inception models through Mastra's model router. Authentication is handled automatically using the `INCEPTION_API_KEY` environment variable.
7
+ Access 3 Inception models through Mastra's model router. Authentication is handled automatically using the `INCEPTION_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Inception documentation](https://platform.inceptionlabs.ai/docs).
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
  | `inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
42
+ | `inception/mercury-2.5` | 260K | | | | | | $0.04 | $0.15 |
42
43
  | `inception/mercury-edit-2` | 128K | | | | | | $0.25 | $0.75 |
43
44
 
44
45
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
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 367 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
7
+ Access 375 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Kilo Gateway documentation](https://kilo.ai).
10
10
 
@@ -42,15 +42,18 @@ for await (const chunk of stream) {
42
42
  | `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
43
43
  | `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
44
44
  | `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
45
- | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.16 |
45
+ | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.11 |
46
46
  | `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
47
47
  | `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
48
- | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $12 |
49
- | `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
48
+ | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $11 |
49
+ | `kilo/~openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
50
+ | `kilo/~openai/gpt-luna-latest` | 1.1M | | | | | | $0.20 | $1 |
50
51
  | `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
52
+ | `kilo/~openai/gpt-sol-latest` | 1.1M | | | | | | $2 | $10 |
53
+ | `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
51
54
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
52
55
  | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
53
- | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $1 | $3 |
56
+ | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.92 | $3 |
54
57
  | `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
55
58
  | `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
56
59
  | `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -92,7 +95,7 @@ for await (const chunk of stream) {
92
95
  | `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
93
96
  | `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
94
97
  | `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.26 | $1 |
95
- | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.29 | $1 |
98
+ | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.25 | $1 |
96
99
  | `kilo/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.27 | $1 |
97
100
  | `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
98
101
  | `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
@@ -145,6 +148,10 @@ for await (const chunk of stream) {
145
148
  | `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.06 | $0.18 |
146
149
  | `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
147
150
  | `kilo/inclusionai/ling-3.0-flash-sante:free` | 262K | | | | | | — | — |
151
+ | `kilo/inclusionai/ling-3.0-flash-vl` | 131K | | | | | | $0.06 | $0.18 |
152
+ | `kilo/inclusionai/ling-3.0-flash-vl:free` | 262K | | | | | | — | — |
153
+ | `kilo/inference-net/schematron-v2-small` | 128K | | | | | | $0.05 | $0.23 |
154
+ | `kilo/inference-net/schematron-v2-turbo` | 128K | | | | | | $0.03 | $0.15 |
148
155
  | `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
149
156
  | `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
150
157
  | `kilo/kilo-auto/free` | 256K | | | | | | — | — |
@@ -176,7 +183,7 @@ for await (const chunk of stream) {
176
183
  | `kilo/minimax/minimax-m2` | 205K | | | | | | $0.30 | $1 |
177
184
  | `kilo/minimax/minimax-m2-her` | 66K | | | | | | $0.30 | $1 |
178
185
  | `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
179
- | `kilo/minimax/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
186
+ | `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
180
187
  | `kilo/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
181
188
  | `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
182
189
  | `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
@@ -214,13 +221,13 @@ for await (const chunk of stream) {
214
221
  | `kilo/nousresearch/hermes-4-405b` | 131K | | | | | | $1 | $3 |
215
222
  | `kilo/nvidia/nemotron-3-nano-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
216
223
  | `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
217
- | `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.09 | $0.40 |
224
+ | `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.08 | $0.45 |
218
225
  | `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
219
- | `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 256K | | | | | | $0.50 | $2 |
226
+ | `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 203K | | | | | | $0.50 | $2 |
220
227
  | `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
221
228
  | `kilo/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.20 | $0.20 |
222
229
  | `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
223
- | `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.08 | $0.20 |
230
+ | `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.07 | $0.18 |
224
231
  | `kilo/nvidia/nemotron-3.5-lightning:free` | 1.0M | | | | | | — | — |
225
232
  | `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
226
233
  | `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
@@ -303,12 +310,12 @@ for await (const chunk of stream) {
303
310
  | `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
304
311
  | `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
305
312
  | `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
306
- | `kilo/qwen/qwen3-14b` | 131K | | | | | | $0.23 | $0.91 |
313
+ | `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
307
314
  | `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
308
315
  | `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
309
316
  | `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
310
317
  | `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
311
- | `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.13 | $0.52 |
318
+ | `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.13 | $0.52 |
312
319
  | `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
313
320
  | `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
314
321
  | `kilo/qwen/qwen3-8b` | 131K | | | | | | $0.12 | $0.46 |
@@ -345,14 +352,16 @@ for await (const chunk of stream) {
345
352
  | `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
346
353
  | `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
347
354
  | `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
348
- | `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
355
+ | `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.42 | $3 |
349
356
  | `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
350
357
  | `kilo/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
351
358
  | `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
352
359
  | `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
353
360
  | `kilo/relace/relace-apply-3` | 256K | | | | | | $0.85 | $1 |
354
361
  | `kilo/relace/relace-search` | 256K | | | | | | $1 | $3 |
362
+ | `kilo/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
355
363
  | `kilo/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
364
+ | `kilo/sakana/fugu-ultra-v2` | 1.0M | | | | | | $5 | $30 |
356
365
  | `kilo/sakana/sakana-namazu` | 262K | | | | | | $0.95 | $4 |
357
366
  | `kilo/sao10k/l3-lunaris-8b` | 8K | | | | | | $0.04 | $0.05 |
358
367
  | `kilo/sao10k/l3.1-euryale-70b` | 131K | | | | | | $0.85 | $0.85 |
@@ -369,16 +378,15 @@ for await (const chunk of stream) {
369
378
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
370
379
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
371
380
  | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
372
- | `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
381
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
373
382
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
374
383
  | `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
375
384
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
376
385
  | `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
377
386
  | `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
378
- | `kilo/thinkingmachines/inkling` | 1.0M | | | | | | $0.95 | $4 |
387
+ | `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
379
388
  | `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
380
389
  | `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
381
- | `kilo/thinkingmachines/inkling:free` | 1.0M | | | | | | — | — |
382
390
  | `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.35 | $0.65 |
383
391
  | `kilo/upstage/solar-pro-3` | 131K | | | | | | $0.15 | $0.60 |
384
392
  | `kilo/upstage/solar-pro4` | 524K | | | | | | $0.30 | $1 |
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 371 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 403 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
 
@@ -40,9 +40,11 @@ for await (const chunk of stream) {
40
40
  | ------------------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
41
  | `llmgateway-providers/alibaba/deepseek-v4-flash` | 1.0M | | | | | | $0.20 | $0.40 |
42
42
  | `llmgateway-providers/alibaba/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
43
+ | `llmgateway-providers/alibaba/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
43
44
  | `llmgateway-providers/alibaba/glm-5` | 203K | | | | | | $0.57 | $3 |
44
45
  | `llmgateway-providers/alibaba/glm-5.2` | 1.0M | | | | | | $1 | $4 |
45
46
  | `llmgateway-providers/alibaba/kimi-k2.5` | 262K | | | | | | $0.57 | $3 |
47
+ | `llmgateway-providers/alibaba/kimi-k3` | 1.0M | | | | | | $3 | $15 |
46
48
  | `llmgateway-providers/alibaba/qwen-coder-plus` | 131K | | | | | | $0.50 | $1 |
47
49
  | `llmgateway-providers/alibaba/qwen-flash` | 1.0M | | | | | | $0.05 | $0.40 |
48
50
  | `llmgateway-providers/alibaba/qwen-max` | 33K | | | | | | $2 | $6 |
@@ -78,6 +80,7 @@ for await (const chunk of stream) {
78
80
  | `llmgateway-providers/anthropic/claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
79
81
  | `llmgateway-providers/anthropic/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
80
82
  | `llmgateway-providers/aws-bedrock/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
83
+ | `llmgateway-providers/aws-bedrock/claude-fable-5-1` | 1.0M | | | | | | $10 | $50 |
81
84
  | `llmgateway-providers/aws-bedrock/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
82
85
  | `llmgateway-providers/aws-bedrock/claude-haiku-4-5-20251001` | 200K | | | | | | $1 | $5 |
83
86
  | `llmgateway-providers/aws-bedrock/claude-opus-4-1-20250805` | 200K | | | | | | $15 | $75 |
@@ -98,6 +101,7 @@ for await (const chunk of stream) {
98
101
  | `llmgateway-providers/aws-mantle/gpt-5.6-luna` | 279K | | | | | | $0.22 | $1 |
99
102
  | `llmgateway-providers/aws-mantle/gpt-5.6-sol` | 279K | | | | | | $6 | $33 |
100
103
  | `llmgateway-providers/aws-mantle/gpt-5.6-terra` | 279K | | | | | | $2 | $13 |
104
+ | `llmgateway-providers/aws-mantle/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
101
105
  | `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
102
106
  | `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
103
107
  | `llmgateway-providers/azure-ai-foundry/grok-4-3` | 20K | | | | | | $1 | $3 |
@@ -165,13 +169,16 @@ for await (const chunk of stream) {
165
169
  | `llmgateway-providers/cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
166
170
  | `llmgateway-providers/cerebras/llama-3.3-70b-instruct` | 128K | | | | | | $0.85 | $1 |
167
171
  | `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
168
- | `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.05 | $0.10 |
172
+ | `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 1.1M | | | | | | $0.05 | $0.10 |
173
+ | `llmgateway-providers/consensusprotocol/deepseek-v4.1-flash` | 1.0M | | | | | | $0.20 | $1 |
174
+ | `llmgateway-providers/consensusprotocol/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.25 |
169
175
  | `llmgateway-providers/consensusprotocol/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
170
176
  | `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
171
177
  | `llmgateway-providers/consensusprotocol/Qwen3.8-27B` | 33K | | | | | | $0.20 | $2 |
172
178
  | `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
173
179
  | `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
174
180
  | `llmgateway-providers/deepinfra/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
181
+ | `llmgateway-providers/deepinfra/deepseek-v4.1-flash` | 1.0M | | | | | | $0.20 | $0.60 |
175
182
  | `llmgateway-providers/deepinfra/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
176
183
  | `llmgateway-providers/deepinfra/gemma-4-31b-it` | 262K | | | | | | $0.13 | $0.38 |
177
184
  | `llmgateway-providers/deepinfra/glm-5.1` | 198K | | | | | | $1 | $4 |
@@ -196,6 +203,7 @@ for await (const chunk of stream) {
196
203
  | `llmgateway-providers/embercloud/qwen3-coder-next` | 262K | | | | | | $0.11 | $0.68 |
197
204
  | `llmgateway-providers/fireworks/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
198
205
  | `llmgateway-providers/fireworks/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
206
+ | `llmgateway-providers/fireworks/deepseek-v4.1-flash` | 1.0M | | | | | | $0.22 | $0.66 |
199
207
  | `llmgateway-providers/fireworks/kimi-k3` | 1.0M | | | | | | $3 | $15 |
200
208
  | `llmgateway-providers/fireworks/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
201
209
  | `llmgateway-providers/gonka24/deepseek-v4-flash` | 390K | | | | | | $0.05 | $0.10 |
@@ -255,6 +263,7 @@ for await (const chunk of stream) {
255
263
  | `llmgateway-providers/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
256
264
  | `llmgateway-providers/novita/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
257
265
  | `llmgateway-providers/novita/deepseek-v4-flash` | 1.1M | | | | | | $0.14 | $0.28 |
266
+ | `llmgateway-providers/novita/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
258
267
  | `llmgateway-providers/novita/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
259
268
  | `llmgateway-providers/novita/gemma-4-26b-a4b-it` | 262K | | | | | | $0.13 | $0.40 |
260
269
  | `llmgateway-providers/novita/gemma-4-31b-it` | 262K | | | | | | $0.14 | $0.40 |
@@ -336,6 +345,7 @@ for await (const chunk of stream) {
336
345
  | `llmgateway-providers/perplexity/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
337
346
  | `llmgateway-providers/quartz/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
338
347
  | `llmgateway-providers/ranoai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
348
+ | `llmgateway-providers/runpod/kimi-k3` | 1.0M | | | | | | $3 | $15 |
339
349
  | `llmgateway-providers/runware/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.15 |
340
350
  | `llmgateway-providers/runware/deepseek-v4-pro` | 1.0M | | | | | | $0.96 | $2 |
341
351
  | `llmgateway-providers/runware/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
@@ -345,7 +355,9 @@ for await (const chunk of stream) {
345
355
  | `llmgateway-providers/runware/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
346
356
  | `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
347
357
  | `llmgateway-providers/runware/kimi-k3` | 1.0M | | | | | | $3 | $15 |
358
+ | `llmgateway-providers/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
348
359
  | `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
360
+ | `llmgateway-providers/sakana/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
349
361
  | `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
350
362
  | `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
351
363
  | `llmgateway-providers/scx-ai-gp/glm-5.3` | 1.0M | | | | | | $1 | $4 |
@@ -358,8 +370,26 @@ for await (const chunk of stream) {
358
370
  | `llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct` | 131K | | | | | | $0.53 | $2 |
359
371
  | `llmgateway-providers/scx-ai/minimax-m2.7` | 197K | | | | | | $0.48 | $2 |
360
372
  | `llmgateway-providers/scx-ai/qwen3-32b` | 33K | | | | | | $0.36 | $0.87 |
373
+ | `llmgateway-providers/tencent/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
374
+ | `llmgateway-providers/tencent/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
375
+ | `llmgateway-providers/tencent/glm-5` | 200K | | | | | | $1 | $3 |
376
+ | `llmgateway-providers/tencent/glm-5-turbo` | 200K | | | | | | $1 | $4 |
377
+ | `llmgateway-providers/tencent/glm-5.1` | 200K | | | | | | $1 | $4 |
378
+ | `llmgateway-providers/tencent/glm-5.2` | 1.0M | | | | | | $1 | $4 |
379
+ | `llmgateway-providers/tencent/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
380
+ | `llmgateway-providers/tencent/hy-mt2-plus` | 8K | | | | | | $0.07 | $0.29 |
381
+ | `llmgateway-providers/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
382
+ | `llmgateway-providers/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
383
+ | `llmgateway-providers/tencent/kimi-k2.6` | 262K | | | | | | $0.86 | $4 |
384
+ | `llmgateway-providers/tencent/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
385
+ | `llmgateway-providers/tencent/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
386
+ | `llmgateway-providers/tencent/kimi-k3` | 1.0M | | | | | | $3 | $15 |
387
+ | `llmgateway-providers/tencent/mimo-v2.5-pro` | 1.0M | | | | | | $0.43 | $0.87 |
388
+ | `llmgateway-providers/tencent/minimax-m2.7` | 200K | | | | | | $0.30 | $1 |
389
+ | `llmgateway-providers/tencent/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
361
390
  | `llmgateway-providers/together-ai/deepseek-v4-flash` | 164K | | | | | | $0.14 | $0.28 |
362
391
  | `llmgateway-providers/together-ai/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
392
+ | `llmgateway-providers/together-ai/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
363
393
  | `llmgateway-providers/together-ai/gemma-4-31b-it` | 262K | | | | | | $0.39 | $0.97 |
364
394
  | `llmgateway-providers/together-ai/glm-4.7` | 203K | | | | | | $0.45 | $2 |
365
395
  | `llmgateway-providers/together-ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
@@ -384,6 +414,8 @@ for await (const chunk of stream) {
384
414
  | `llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.22 | $2 |
385
415
  | `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
386
416
  | `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
417
+ | `llmgateway-providers/vichar-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
418
+ | `llmgateway-providers/vichar-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
387
419
  | `llmgateway-providers/xai/grok-4` | 256K | | | | | | $3 | $15 |
388
420
  | `llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
389
421
  | `llmgateway-providers/xai/grok-4-20-beta-0309-reasoning` | 2.0M | | | | | | $2 | $6 |