@mastra/mcp-docs-server 1.2.26-alpha.1 → 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.
- package/.docs/docs/agents/overview.md +1 -1
- package/.docs/docs/agents/processors.md +21 -0
- package/.docs/docs/connections/connect-mcp-client.md +211 -0
- package/.docs/docs/deployment/mastra-server.md +8 -2
- package/.docs/docs/evals/datasets.md +5 -1
- package/.docs/docs/guides/context-engineering.md +1 -1
- package/.docs/docs/harness/background-tasks.md +30 -24
- package/.docs/docs/harness/signals.md +39 -0
- package/.docs/docs/index.md +1 -1
- package/.docs/docs/memory/message-history.md +6 -2
- package/.docs/docs/subagents.md +25 -0
- package/.docs/integrations/agentic-ui/ai-sdk-ui.md +7 -0
- package/.docs/integrations/file-storage/amazon-s3.md +7 -1
- package/.docs/integrations/file-storage/archil.md +3 -3
- package/.docs/integrations/frameworks/electron.md +1 -1
- package/.docs/integrations/observability/langfuse.md +11 -1
- package/.docs/integrations/sandboxes/cloudflare-sandbox.md +2 -0
- package/.docs/integrations/sandboxes/daytona.md +33 -0
- package/.docs/integrations/sandboxes/docker.md +13 -0
- package/.docs/integrations/voice/livekit.md +26 -2
- package/.docs/models/gateways/merge-gateway.md +6 -1
- package/.docs/models/gateways/netlify.md +4 -1
- package/.docs/models/gateways/openrouter.md +10 -2
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/above.md +1 -1
- package/.docs/models/providers/agentrouter.md +8 -6
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/bothub.md +2 -1
- package/.docs/models/providers/cline-pass.md +18 -17
- package/.docs/models/providers/cortecs.md +3 -3
- package/.docs/models/providers/deepinfra.md +7 -6
- package/.docs/models/providers/digitalocean.md +1 -1
- package/.docs/models/providers/edenai.md +28 -6
- package/.docs/models/providers/empiriolabs.md +3 -1
- package/.docs/models/providers/fireworks-ai.md +2 -1
- package/.docs/models/providers/greenpt.md +2 -1
- package/.docs/models/providers/huggingface.md +4 -1
- package/.docs/models/providers/hyper.md +6 -5
- package/.docs/models/providers/kilo.md +22 -15
- package/.docs/models/providers/llmgateway-providers.md +31 -2
- package/.docs/models/providers/llmgateway.md +8 -2
- package/.docs/models/providers/nan.md +1 -1
- package/.docs/models/providers/nano-gpt.md +13 -4
- package/.docs/models/providers/nvidia.md +3 -2
- package/.docs/models/providers/ofox.md +30 -3
- package/.docs/models/providers/ollama-cloud.md +3 -1
- package/.docs/models/providers/pioneer.md +11 -2
- package/.docs/models/providers/requesty.md +5 -6
- package/.docs/models/providers/togetherai.md +2 -1
- package/.docs/models/providers/volcengine-coding-plan.md +3 -1
- package/.docs/reference/agents/agent.md +47 -1
- package/.docs/reference/agents/generate.md +2 -0
- package/.docs/reference/ai-sdk/to-ai-sdk-messages.md +16 -0
- package/.docs/reference/cli/mastra.md +28 -0
- package/.docs/reference/client-js/datasets.md +1 -1
- package/.docs/reference/configuration.md +2 -2
- package/.docs/reference/datasets/purgeItem.md +3 -3
- package/.docs/reference/index.md +3 -0
- package/.docs/reference/memory/cloneThread.md +2 -0
- package/.docs/reference/memory/copyThread.md +65 -0
- package/.docs/reference/memory/memory-class.md +2 -1
- package/.docs/reference/memory/recall.md +51 -0
- package/.docs/reference/memory/updateThreadResourceId.md +46 -0
- package/.docs/reference/processors/agents-md-injector.md +55 -0
- package/.docs/reference/processors/processor-interface.md +2 -0
- package/.docs/reference/pubsub/redis-streams.md +6 -0
- package/.docs/reference/pubsub/valkey-streams.md +6 -0
- package/.docs/reference/streaming/agents/stream.md +30 -0
- package/.docs/reference/tools/mcp-server.md +28 -0
- package/.docs/reference/workspace/filesystem.md +72 -0
- package/package.json +4 -4
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# EmpirioLabs AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
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 | | | | | | — | — |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Fireworks AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
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 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# GreenPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
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 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Hugging Face
|
|
6
6
|
|
|
7
|
-
Access
|
|
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
|
|
|
@@ -50,6 +50,9 @@ for await (const chunk of stream) {
|
|
|
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
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 |
|
|
53
56
|
| `huggingface/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
54
57
|
| `huggingface/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
55
58
|
| `huggingface/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.06 | $0.06 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Charm Hyper
|
|
6
6
|
|
|
7
|
-
Access
|
|
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/
|
|
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.
|
|
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.
|
|
60
|
-
| `hyper/minimax-m2.7` | 262K | | | | | | $0.
|
|
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 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
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.
|
|
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 | $
|
|
49
|
-
| `kilo/~openai/gpt-latest`
|
|
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 | | | | | | $0.
|
|
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.
|
|
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 |
|
|
@@ -132,7 +135,7 @@ for await (const chunk of stream) {
|
|
|
132
135
|
| `kilo/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
|
|
133
136
|
| `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
134
137
|
| `kilo/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
135
|
-
| `kilo/google/gemma-4-26b-a4b-it` |
|
|
138
|
+
| `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.04 | $0.22 |
|
|
136
139
|
| `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.09 | $0.34 |
|
|
137
140
|
| `kilo/google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
|
|
138
141
|
| `kilo/google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
@@ -145,7 +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 |
|
|
148
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 |
|
|
149
155
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
150
156
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
151
157
|
| `kilo/kilo-auto/free` | 256K | | | | | | — | — |
|
|
@@ -215,13 +221,13 @@ for await (const chunk of stream) {
|
|
|
215
221
|
| `kilo/nousresearch/hermes-4-405b` | 131K | | | | | | $1 | $3 |
|
|
216
222
|
| `kilo/nvidia/nemotron-3-nano-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
|
|
217
223
|
| `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
|
|
218
|
-
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.
|
|
224
|
+
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.08 | $0.45 |
|
|
219
225
|
| `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
|
|
220
|
-
| `kilo/nvidia/nemotron-3-ultra-550b-a55b` |
|
|
226
|
+
| `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 203K | | | | | | $0.50 | $2 |
|
|
221
227
|
| `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
|
|
222
228
|
| `kilo/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.20 | $0.20 |
|
|
223
229
|
| `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
|
|
224
|
-
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.
|
|
230
|
+
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.07 | $0.18 |
|
|
225
231
|
| `kilo/nvidia/nemotron-3.5-lightning:free` | 1.0M | | | | | | — | — |
|
|
226
232
|
| `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
227
233
|
| `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
|
|
@@ -304,7 +310,7 @@ for await (const chunk of stream) {
|
|
|
304
310
|
| `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
305
311
|
| `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
306
312
|
| `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
|
|
307
|
-
| `kilo/qwen/qwen3-14b` |
|
|
313
|
+
| `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
|
|
308
314
|
| `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
|
|
309
315
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
310
316
|
| `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
|
|
@@ -346,14 +352,16 @@ for await (const chunk of stream) {
|
|
|
346
352
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
347
353
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
348
354
|
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
349
|
-
| `kilo/qwen/qwen3.8-27b` |
|
|
355
|
+
| `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.42 | $3 |
|
|
350
356
|
| `kilo/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
351
357
|
| `kilo/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
352
358
|
| `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
|
|
353
359
|
| `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
|
|
354
360
|
| `kilo/relace/relace-apply-3` | 256K | | | | | | $0.85 | $1 |
|
|
355
361
|
| `kilo/relace/relace-search` | 256K | | | | | | $1 | $3 |
|
|
362
|
+
| `kilo/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
356
363
|
| `kilo/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
364
|
+
| `kilo/sakana/fugu-ultra-v2` | 1.0M | | | | | | $5 | $30 |
|
|
357
365
|
| `kilo/sakana/sakana-namazu` | 262K | | | | | | $0.95 | $4 |
|
|
358
366
|
| `kilo/sao10k/l3-lunaris-8b` | 8K | | | | | | $0.04 | $0.05 |
|
|
359
367
|
| `kilo/sao10k/l3.1-euryale-70b` | 131K | | | | | | $0.85 | $0.85 |
|
|
@@ -370,16 +378,15 @@ for await (const chunk of stream) {
|
|
|
370
378
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
371
379
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
372
380
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
373
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
381
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
374
382
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
375
383
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
376
384
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
377
385
|
| `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
|
|
378
386
|
| `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
|
|
379
|
-
| `kilo/thinkingmachines/inkling` |
|
|
387
|
+
| `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
|
|
380
388
|
| `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
|
|
381
389
|
| `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
|
|
382
|
-
| `kilo/thinkingmachines/inkling:free` | 1.0M | | | | | | — | — |
|
|
383
390
|
| `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.35 | $0.65 |
|
|
384
391
|
| `kilo/upstage/solar-pro-3` | 131K | | | | | | $0.15 | $0.60 |
|
|
385
392
|
| `kilo/upstage/solar-pro4` | 524K | | | | | | $0.30 | $1 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
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 |
|
|
@@ -99,6 +101,7 @@ for await (const chunk of stream) {
|
|
|
99
101
|
| `llmgateway-providers/aws-mantle/gpt-5.6-luna` | 279K | | | | | | $0.22 | $1 |
|
|
100
102
|
| `llmgateway-providers/aws-mantle/gpt-5.6-sol` | 279K | | | | | | $6 | $33 |
|
|
101
103
|
| `llmgateway-providers/aws-mantle/gpt-5.6-terra` | 279K | | | | | | $2 | $13 |
|
|
104
|
+
| `llmgateway-providers/aws-mantle/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
102
105
|
| `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
|
|
103
106
|
| `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
|
|
104
107
|
| `llmgateway-providers/azure-ai-foundry/grok-4-3` | 20K | | | | | | $1 | $3 |
|
|
@@ -166,7 +169,8 @@ for await (const chunk of stream) {
|
|
|
166
169
|
| `llmgateway-providers/cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
|
|
167
170
|
| `llmgateway-providers/cerebras/llama-3.3-70b-instruct` | 128K | | | | | | $0.85 | $1 |
|
|
168
171
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
169
|
-
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 1.
|
|
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 |
|
|
170
174
|
| `llmgateway-providers/consensusprotocol/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.25 |
|
|
171
175
|
| `llmgateway-providers/consensusprotocol/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
|
|
172
176
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
@@ -174,6 +178,7 @@ for await (const chunk of stream) {
|
|
|
174
178
|
| `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
|
|
175
179
|
| `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
176
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 |
|
|
177
182
|
| `llmgateway-providers/deepinfra/gemma-4-26b-a4b-it` | 262K | | | | | | $0.07 | $0.34 |
|
|
178
183
|
| `llmgateway-providers/deepinfra/gemma-4-31b-it` | 262K | | | | | | $0.13 | $0.38 |
|
|
179
184
|
| `llmgateway-providers/deepinfra/glm-5.1` | 198K | | | | | | $1 | $4 |
|
|
@@ -198,6 +203,7 @@ for await (const chunk of stream) {
|
|
|
198
203
|
| `llmgateway-providers/embercloud/qwen3-coder-next` | 262K | | | | | | $0.11 | $0.68 |
|
|
199
204
|
| `llmgateway-providers/fireworks/deepseek-v4-flash` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
200
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 |
|
|
201
207
|
| `llmgateway-providers/fireworks/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
202
208
|
| `llmgateway-providers/fireworks/kimi-k3-fast` | 1.0M | | | | | | $5 | $23 |
|
|
203
209
|
| `llmgateway-providers/gonka24/deepseek-v4-flash` | 390K | | | | | | $0.05 | $0.10 |
|
|
@@ -257,6 +263,7 @@ for await (const chunk of stream) {
|
|
|
257
263
|
| `llmgateway-providers/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
258
264
|
| `llmgateway-providers/novita/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
|
|
259
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 |
|
|
260
267
|
| `llmgateway-providers/novita/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
|
|
261
268
|
| `llmgateway-providers/novita/gemma-4-26b-a4b-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
262
269
|
| `llmgateway-providers/novita/gemma-4-31b-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
@@ -338,6 +345,7 @@ for await (const chunk of stream) {
|
|
|
338
345
|
| `llmgateway-providers/perplexity/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
339
346
|
| `llmgateway-providers/quartz/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
340
347
|
| `llmgateway-providers/ranoai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
348
|
+
| `llmgateway-providers/runpod/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
341
349
|
| `llmgateway-providers/runware/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.15 |
|
|
342
350
|
| `llmgateway-providers/runware/deepseek-v4-pro` | 1.0M | | | | | | $0.96 | $2 |
|
|
343
351
|
| `llmgateway-providers/runware/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
|
|
@@ -347,7 +355,9 @@ for await (const chunk of stream) {
|
|
|
347
355
|
| `llmgateway-providers/runware/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
|
|
348
356
|
| `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
|
|
349
357
|
| `llmgateway-providers/runware/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
358
|
+
| `llmgateway-providers/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
350
359
|
| `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
360
|
+
| `llmgateway-providers/sakana/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
|
|
351
361
|
| `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
|
|
352
362
|
| `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
353
363
|
| `llmgateway-providers/scx-ai-gp/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -360,8 +370,26 @@ for await (const chunk of stream) {
|
|
|
360
370
|
| `llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct` | 131K | | | | | | $0.53 | $2 |
|
|
361
371
|
| `llmgateway-providers/scx-ai/minimax-m2.7` | 197K | | | | | | $0.48 | $2 |
|
|
362
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 |
|
|
363
390
|
| `llmgateway-providers/together-ai/deepseek-v4-flash` | 164K | | | | | | $0.14 | $0.28 |
|
|
364
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 |
|
|
365
393
|
| `llmgateway-providers/together-ai/gemma-4-31b-it` | 262K | | | | | | $0.39 | $0.97 |
|
|
366
394
|
| `llmgateway-providers/together-ai/glm-4.7` | 203K | | | | | | $0.45 | $2 |
|
|
367
395
|
| `llmgateway-providers/together-ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
@@ -386,6 +414,7 @@ for await (const chunk of stream) {
|
|
|
386
414
|
| `llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.22 | $2 |
|
|
387
415
|
| `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
|
|
388
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 |
|
|
389
418
|
| `llmgateway-providers/vichar-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
390
419
|
| `llmgateway-providers/xai/grok-4` | 256K | | | | | | $3 | $15 |
|
|
391
420
|
| `llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 192 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
|
|
|
@@ -60,7 +60,9 @@ for await (const chunk of stream) {
|
|
|
60
60
|
| `llmgateway/deepseek-v4-pro` | 1.1M | | | | | | $0.43 | $0.87 |
|
|
61
61
|
| `llmgateway/deepseek-v4.1-flash` | 1.1M | | | | | | $0.15 | $0.60 |
|
|
62
62
|
| `llmgateway/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
|
|
63
|
+
| `llmgateway/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
63
64
|
| `llmgateway/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
65
|
+
| `llmgateway/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
|
|
64
66
|
| `llmgateway/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
65
67
|
| `llmgateway/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
66
68
|
| `llmgateway/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
|
|
@@ -88,11 +90,13 @@ for await (const chunk of stream) {
|
|
|
88
90
|
| `llmgateway/glm-4.7-flash` | 200K | | | | | | $0.06 | $0.40 |
|
|
89
91
|
| `llmgateway/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.40 |
|
|
90
92
|
| `llmgateway/glm-5` | 203K | | | | | | $0.72 | $2 |
|
|
93
|
+
| `llmgateway/glm-5-turbo` | 200K | | | | | | $1 | $4 |
|
|
91
94
|
| `llmgateway/glm-5.1` | 205K | | | | | | $0.93 | $3 |
|
|
92
95
|
| `llmgateway/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
|
|
93
96
|
| `llmgateway/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
94
97
|
| `llmgateway/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
95
98
|
| `llmgateway/glm-5.3-flash` | 1.0M | | | | | | $0.09 | $0.25 |
|
|
99
|
+
| `llmgateway/glm-5v-turbo` | 200K | | | | | | $1 | $4 |
|
|
96
100
|
| `llmgateway/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
97
101
|
| `llmgateway/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
98
102
|
| `llmgateway/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
|
|
@@ -137,7 +141,9 @@ for await (const chunk of stream) {
|
|
|
137
141
|
| `llmgateway/grok-4-5` | 500K | | | | | | $2 | $6 |
|
|
138
142
|
| `llmgateway/grok-4-6` | 500K | | | | | | $2 | $6 |
|
|
139
143
|
| `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
140
|
-
| `llmgateway/
|
|
144
|
+
| `llmgateway/hy-mt2-plus` | 8K | | | | | | $0.07 | $0.29 |
|
|
145
|
+
| `llmgateway/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
146
|
+
| `llmgateway/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
141
147
|
| `llmgateway/kimi-k2` | 256K | | | | | | $0.57 | $2 |
|
|
142
148
|
| `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
143
149
|
| `llmgateway/kimi-k2.5` | 262K | | | | | | $0.41 | $2 |
|
|
@@ -40,7 +40,7 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| ----------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
41
|
| `nan/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
42
42
|
| `nan/gemma4` | 262K | | | | | | — | — |
|
|
43
|
-
| `nan/glm5.
|
|
43
|
+
| `nan/glm5.3` | 1.0M | | | | | | — | — |
|
|
44
44
|
| `nan/glm5.3-flash` | 1.0M | | | | | | — | — |
|
|
45
45
|
| `nan/mimo-v2.5` | 1.0M | | | | | | — | — |
|
|
46
46
|
| `nan/qwen3.6` | 262K | | | | | | — | — |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# NanoGPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 594 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
|
|
|
@@ -276,6 +276,7 @@ for await (const chunk of stream) {
|
|
|
276
276
|
| `nano-gpt/inflatebot/MN-12B-Mag-Mell-R1` | 16K | | | | | | $0.49 | $0.49 |
|
|
277
277
|
| `nano-gpt/kimi-k2-instruct-fast` | 131K | | | | | | $0.40 | $2 |
|
|
278
278
|
| `nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3` | 33K | | | | | | $0.70 | $0.70 |
|
|
279
|
+
| `nano-gpt/lightonai/LightOnOCR-2-1B` | 33K | | | | | | $0.18 | $0.35 |
|
|
279
280
|
| `nano-gpt/liquid/lfm-2.5-2.6b` | 128K | | | | | | $0.10 | $0.20 |
|
|
280
281
|
| `nano-gpt/LLM360/K2-Think` | 128K | | | | | | $0.17 | $0.68 |
|
|
281
282
|
| `nano-gpt/longcat-2.0` | 1.0M | | | | | | $0.75 | $3 |
|
|
@@ -287,6 +288,7 @@ for await (const chunk of stream) {
|
|
|
287
288
|
| `nano-gpt/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
|
|
288
289
|
| `nano-gpt/mercury-coder-small` | 33K | | | | | | $0.25 | $1 |
|
|
289
290
|
| `nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8` | 128K | | | | | | $0.02 | $0.03 |
|
|
291
|
+
| `nano-gpt/meta-llama/llama-3.1-405b-instruct` | 131K | | | | | | $2 | $2 |
|
|
290
292
|
| `nano-gpt/meta-llama/llama-3.1-8b-instruct` | 131K | | | | | | $0.05 | $0.09 |
|
|
291
293
|
| `nano-gpt/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.03 | $0.05 |
|
|
292
294
|
| `nano-gpt/meta-llama/llama-3.3-70b-instruct` | 131K | | | | | | $0.05 | $0.23 |
|
|
@@ -329,6 +331,7 @@ for await (const chunk of stream) {
|
|
|
329
331
|
| `nano-gpt/mistralai/mistral-medium-3.1` | 131K | | | | | | $0.40 | $2 |
|
|
330
332
|
| `nano-gpt/mistralai/Mistral-Nemo-Instruct-2407` | 16K | | | | | | $0.10 | $0.12 |
|
|
331
333
|
| `nano-gpt/mistralai/mistral-saba` | 33K | | | | | | $0.20 | $0.59 |
|
|
334
|
+
| `nano-gpt/mistralai/mistral-small-24b-instruct-2501` | 33K | | | | | | $0.12 | $0.35 |
|
|
332
335
|
| `nano-gpt/mistralai/mistral-small-4-119b-2603` | 262K | | | | | | $0.40 | $1 |
|
|
333
336
|
| `nano-gpt/mistralai/mistral-small-4-119b-2603:thinking` | 262K | | | | | | $0.40 | $1 |
|
|
334
337
|
| `nano-gpt/mistralai/mixtral-8x22b-instruct-v0.1` | 66K | | | | | | $2 | $6 |
|
|
@@ -398,11 +401,15 @@ for await (const chunk of stream) {
|
|
|
398
401
|
| `nano-gpt/openai/gpt-5.6-terra-pro` | 1.1M | | | | | | $2 | $12 |
|
|
399
402
|
| `nano-gpt/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
400
403
|
| `nano-gpt/openai/gpt-6-astra-pro` | 1.1M | | | | | | $10 | $50 |
|
|
404
|
+
| `nano-gpt/openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
|
|
401
405
|
| `nano-gpt/openai/gpt-chat-latest` | 1.1M | | | | | | $2 | $10 |
|
|
402
406
|
| `nano-gpt/openai/gpt-latest` | 1.1M | | | | | | $10 | $50 |
|
|
407
|
+
| `nano-gpt/openai/gpt-luna-latest` | 1.1M | | | | | | $0.20 | $1 |
|
|
403
408
|
| `nano-gpt/openai/gpt-oss-120b` | 128K | | | | | | $0.35 | $0.75 |
|
|
404
409
|
| `nano-gpt/openai/gpt-oss-20b` | 128K | | | | | | $0.20 | $0.30 |
|
|
405
410
|
| `nano-gpt/openai/gpt-oss-safeguard-20b` | 128K | | | | | | $0.07 | $0.30 |
|
|
411
|
+
| `nano-gpt/openai/gpt-sol-latest` | 1.1M | | | | | | $2 | $10 |
|
|
412
|
+
| `nano-gpt/openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
|
|
406
413
|
| `nano-gpt/openai/o1` | 200K | | | | | | $15 | $60 |
|
|
407
414
|
| `nano-gpt/openai/o1-pro` | 200K | | | | | | $150 | $600 |
|
|
408
415
|
| `nano-gpt/openai/o3` | 200K | | | | | | $2 | $8 |
|
|
@@ -492,8 +499,9 @@ for await (const chunk of stream) {
|
|
|
492
499
|
| `nano-gpt/qwen3.8-max` | 991K | | | | | | $2 | $6 |
|
|
493
500
|
| `nano-gpt/qwen3.8-max:thinking` | 991K | | | | | | $2 | $6 |
|
|
494
501
|
| `nano-gpt/ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0` | 33K | | | | | | $0.50 | $0.50 |
|
|
495
|
-
| `nano-gpt/sakana/fugu-
|
|
496
|
-
| `nano-gpt/sakana/fugu-ultra
|
|
502
|
+
| `nano-gpt/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
503
|
+
| `nano-gpt/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
504
|
+
| `nano-gpt/sakana/fugu-ultra-v1.1` | 1.0M | | | | | | $5 | $30 |
|
|
497
505
|
| `nano-gpt/Salesforce/Llama-xLAM-2-70b-fc-r` | 128K | | | | | | $3 | $3 |
|
|
498
506
|
| `nano-gpt/Sao10K/L3-8B-Stheno-v3.2` | 16K | | | | | | $0.20 | $0.20 |
|
|
499
507
|
| `nano-gpt/Sao10K/L3.1-70B-Euryale-v2.2` | 20K | | | | | | $0.31 | $0.36 |
|
|
@@ -529,12 +537,13 @@ for await (const chunk of stream) {
|
|
|
529
537
|
| `nano-gpt/TEE/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
530
538
|
| `nano-gpt/TEE/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
531
539
|
| `nano-gpt/TEE/gpt-oss-120b` | 131K | | | | | | $2 | $2 |
|
|
532
|
-
| `nano-gpt/TEE/gpt-oss-20b` | 131K | | | | | | $0.
|
|
540
|
+
| `nano-gpt/TEE/gpt-oss-20b` | 131K | | | | | | $0.04 | $0.15 |
|
|
533
541
|
| `nano-gpt/TEE/kimi-k2.6` | 262K | | | | | | $2 | $5 |
|
|
534
542
|
| `nano-gpt/TEE/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
535
543
|
| `nano-gpt/TEE/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
536
544
|
| `nano-gpt/TEE/llama3-3-70b` | 128K | | | | | | $2 | $3 |
|
|
537
545
|
| `nano-gpt/TEE/muse-glimmer-30b` | 131K | | | | | | $0.35 | $2 |
|
|
546
|
+
| `nano-gpt/TEE/nemotron-3.5-lightning` | 262K | | | | | | $0.08 | $0.20 |
|
|
538
547
|
| `nano-gpt/TEE/qwen2.5-vl-72b-instruct` | 66K | | | | | | $0.70 | $0.70 |
|
|
539
548
|
| `nano-gpt/TEE/qwen3-8b` | 41K | | | | | | $0.11 | $0.45 |
|
|
540
549
|
| `nano-gpt/TEE/qwen3.5-27b` | 262K | | | | | | $0.30 | $2 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Nvidia
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 104 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
|
|
10
10
|
|
|
@@ -139,6 +139,7 @@ for await (const chunk of stream) {
|
|
|
139
139
|
| `nvidia/thinkingmachines/inkling` | 1.0M | | | | | | — | — |
|
|
140
140
|
| `nvidia/upstage/solar-10.7b-instruct` | 128K | | | | | | — | — |
|
|
141
141
|
| `nvidia/z-ai/glm-5.2` | 1.0M | | | | | | — | — |
|
|
142
|
+
| `nvidia/z-ai/glm-5.3-flash` | 1.0M | | | | | | — | — |
|
|
142
143
|
|
|
143
144
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
144
145
|
|
|
@@ -170,7 +171,7 @@ const agent = new Agent({
|
|
|
170
171
|
model: ({ requestContext }) => {
|
|
171
172
|
const useAdvanced = requestContext.task === "complex";
|
|
172
173
|
return useAdvanced
|
|
173
|
-
? "nvidia/z-ai/glm-5.
|
|
174
|
+
? "nvidia/z-ai/glm-5.3-flash"
|
|
174
175
|
: "nvidia/abacusai/dracarys-llama-3.1-70b-instruct";
|
|
175
176
|
}
|
|
176
177
|
});
|