@mastra/mcp-docs-server 1.2.2 → 1.2.3-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/{harness → agent-controller}/modes.md +19 -19
- package/.docs/docs/agent-controller/overview.md +128 -0
- package/.docs/docs/agent-controller/session.md +143 -0
- package/.docs/docs/{harness → agent-controller}/subagents.md +12 -12
- package/.docs/docs/agent-controller/threads-and-state.md +141 -0
- package/.docs/docs/{harness → agent-controller}/tool-approvals.md +23 -23
- package/.docs/docs/agents/agent-approval.md +38 -0
- package/.docs/docs/agents/channels.md +47 -0
- package/.docs/docs/agents/heartbeats.md +211 -0
- package/.docs/docs/agents/signals.md +25 -1
- package/.docs/docs/observability/metrics/overview.md +2 -2
- package/.docs/models/gateways/openrouter.md +1 -2
- package/.docs/models/gateways/vercel.md +3 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/anthropic.md +4 -5
- package/.docs/models/providers/chutes.md +17 -43
- package/.docs/models/providers/deepinfra.md +3 -2
- package/.docs/models/providers/friendli.md +1 -3
- package/.docs/models/providers/gmicloud.md +18 -15
- package/.docs/models/providers/huggingface.md +2 -1
- package/.docs/models/providers/inceptron.md +10 -8
- package/.docs/models/providers/llmgateway.md +3 -6
- package/.docs/models/providers/neuralwatt.md +9 -5
- package/.docs/models/providers/novita-ai.md +1 -1
- package/.docs/models/providers/nvidia.md +2 -1
- package/.docs/models/providers/siliconflow-cn.md +50 -78
- package/.docs/models/providers/siliconflow.md +52 -73
- package/.docs/models/providers/stepfun.md +1 -1
- package/.docs/models/providers/subconscious.md +71 -0
- package/.docs/models/providers/synthetic.md +8 -6
- package/.docs/models/providers/tinfoil.md +77 -0
- package/.docs/models/providers/xiaomi.md +2 -2
- package/.docs/models/providers.md +2 -0
- package/.docs/reference/{harness/harness-class.md → agent-controller/agent-controller-class.md} +106 -106
- package/.docs/reference/{harness → agent-controller}/session.md +97 -91
- package/.docs/reference/agents/channels.md +3 -1
- package/.docs/reference/agents/listSuspendedRuns.md +91 -0
- package/.docs/reference/channels/channel-provider.md +65 -0
- package/.docs/reference/channels/slack-provider.md +226 -0
- package/.docs/reference/client-js/agents.md +21 -0
- package/.docs/reference/index.md +6 -2
- package/.docs/reference/observability/metrics/automatic-metrics.md +2 -2
- package/.docs/reference/pubsub/lease-provider.md +131 -0
- package/.docs/reference/pubsub/redis-streams.md +10 -2
- package/CHANGELOG.md +42 -0
- package/package.json +4 -4
- package/.docs/docs/harness/overview.md +0 -128
- package/.docs/docs/harness/session.md +0 -143
- package/.docs/docs/harness/threads-and-state.md +0 -141
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Chutes
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 13 Chutes models through Mastra's model router. Authentication is handled automatically using the `CHUTES_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Chutes documentation](https://llm.chutes.ai).
|
|
6
6
|
|
|
@@ -32,47 +32,21 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `chutes/deepseek-ai/DeepSeek-
|
|
38
|
-
| `chutes/
|
|
39
|
-
| `chutes/
|
|
40
|
-
| `chutes/
|
|
41
|
-
| `chutes/
|
|
42
|
-
| `chutes/
|
|
43
|
-
| `chutes/
|
|
44
|
-
| `chutes/
|
|
45
|
-
| `chutes/
|
|
46
|
-
| `chutes/
|
|
47
|
-
| `chutes/
|
|
48
|
-
| `chutes/
|
|
49
|
-
| `chutes/
|
|
50
|
-
| `chutes/Qwen/Qwen2.5-Coder-32B-Instruct` | 33K | | | | | | $0.03 | $0.11 |
|
|
51
|
-
| `chutes/Qwen/Qwen2.5-VL-32B-Instruct` | 16K | | | | | | $0.05 | $0.22 |
|
|
52
|
-
| `chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE` | 262K | | | | | | $0.10 | $0.60 |
|
|
53
|
-
| `chutes/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.11 | $0.60 |
|
|
54
|
-
| `chutes/Qwen/Qwen3-30B-A3B` | 41K | | | | | | $0.06 | $0.22 |
|
|
55
|
-
| `chutes/Qwen/Qwen3-32B-TEE` | 41K | | | | | | $0.08 | $0.24 |
|
|
56
|
-
| `chutes/Qwen/Qwen3-Coder-Next-TEE` | 262K | | | | | | $0.12 | $0.75 |
|
|
57
|
-
| `chutes/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.10 | $0.80 |
|
|
58
|
-
| `chutes/Qwen/Qwen3.5-397B-A17B-TEE` | 262K | | | | | | $0.39 | $2 |
|
|
59
|
-
| `chutes/Qwen/Qwen3.6-27B-TEE` | 262K | | | | | | $0.20 | $2 |
|
|
60
|
-
| `chutes/Qwen/Qwen3Guard-Gen-0.6B` | 33K | | | | | | $0.01 | $0.01 |
|
|
61
|
-
| `chutes/rednote-hilab/dots.ocr` | 131K | | | | | | $0.01 | $0.01 |
|
|
62
|
-
| `chutes/tngtech/DeepSeek-TNG-R1T2-Chimera-TEE` | 164K | | | | | | $0.30 | $1 |
|
|
63
|
-
| `chutes/unsloth/gemma-3-12b-it` | 131K | | | | | | $0.03 | $0.10 |
|
|
64
|
-
| `chutes/unsloth/gemma-3-27b-it` | 128K | | | | | | $0.03 | $0.11 |
|
|
65
|
-
| `chutes/unsloth/gemma-3-4b-it` | 96K | | | | | | $0.01 | $0.03 |
|
|
66
|
-
| `chutes/unsloth/Llama-3.2-1B-Instruct` | 16K | | | | | | $0.01 | $0.01 |
|
|
67
|
-
| `chutes/unsloth/Llama-3.2-3B-Instruct` | 16K | | | | | | $0.01 | $0.01 |
|
|
68
|
-
| `chutes/unsloth/Mistral-Nemo-Instruct-2407` | 131K | | | | | | $0.02 | $0.04 |
|
|
69
|
-
| `chutes/XiaomiMiMo/MiMo-V2-Flash-TEE` | 262K | | | | | | $0.09 | $0.29 |
|
|
70
|
-
| `chutes/zai-org/GLM-4.6V` | 131K | | | | | | $0.30 | $0.90 |
|
|
71
|
-
| `chutes/zai-org/GLM-4.7-FP8` | 203K | | | | | | $0.30 | $1 |
|
|
72
|
-
| `chutes/zai-org/GLM-4.7-TEE` | 203K | | | | | | $0.39 | $2 |
|
|
73
|
-
| `chutes/zai-org/GLM-5-TEE` | 203K | | | | | | $0.95 | $3 |
|
|
74
|
-
| `chutes/zai-org/GLM-5-Turbo` | 203K | | | | | | $0.49 | $2 |
|
|
75
|
-
| `chutes/zai-org/GLM-5.1-TEE` | 203K | | | | | | $1 | $4 |
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ----------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `chutes/deepseek-ai/DeepSeek-V3.2-TEE` | 131K | | | | | | $1 | $1 |
|
|
38
|
+
| `chutes/google/gemma-4-31B-turbo-TEE` | 131K | | | | | | $0.12 | $0.37 |
|
|
39
|
+
| `chutes/MiniMaxAI/MiniMax-M2.5-TEE` | 197K | | | | | | $0.15 | $1 |
|
|
40
|
+
| `chutes/moonshotai/Kimi-K2.5-TEE` | 262K | | | | | | $0.44 | $2 |
|
|
41
|
+
| `chutes/moonshotai/Kimi-K2.6-TEE` | 262K | | | | | | $0.66 | $4 |
|
|
42
|
+
| `chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE` | 262K | | | | | | $0.30 | $1 |
|
|
43
|
+
| `chutes/Qwen/Qwen3-32B-TEE` | 41K | | | | | | $0.10 | $0.42 |
|
|
44
|
+
| `chutes/Qwen/Qwen3.5-397B-A17B-TEE` | 262K | | | | | | $0.45 | $3 |
|
|
45
|
+
| `chutes/Qwen/Qwen3.6-27B-TEE` | 262K | | | | | | $0.30 | $2 |
|
|
46
|
+
| `chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE` | 131K | | | | | | $0.02 | $0.10 |
|
|
47
|
+
| `chutes/zai-org/GLM-5-TEE` | 203K | | | | | | $0.95 | $3 |
|
|
48
|
+
| `chutes/zai-org/GLM-5.1-TEE` | 203K | | | | | | $0.98 | $3 |
|
|
49
|
+
| `chutes/zai-org/GLM-5.2-TEE` | 1.0M | | | | | | $1 | $4 |
|
|
76
50
|
|
|
77
51
|
## Advanced configuration
|
|
78
52
|
|
|
@@ -102,7 +76,7 @@ const agent = new Agent({
|
|
|
102
76
|
model: ({ requestContext }) => {
|
|
103
77
|
const useAdvanced = requestContext.task === "complex";
|
|
104
78
|
return useAdvanced
|
|
105
|
-
? "chutes/zai-org/GLM-5.
|
|
79
|
+
? "chutes/zai-org/GLM-5.2-TEE"
|
|
106
80
|
: "chutes/MiniMaxAI/MiniMax-M2.5-TEE";
|
|
107
81
|
}
|
|
108
82
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Deep Infra
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 26 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
|
|
6
6
|
|
|
@@ -57,6 +57,7 @@ for await (const chunk of stream) {
|
|
|
57
57
|
| `deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
58
58
|
| `deepinfra/zai-org/GLM-5` | 203K | | | | | | $0.60 | $2 |
|
|
59
59
|
| `deepinfra/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
60
|
+
| `deepinfra/zai-org/GLM-5.2` | 1.0M | | | | | | $0.95 | $3 |
|
|
60
61
|
|
|
61
62
|
## Advanced configuration
|
|
62
63
|
|
|
@@ -85,7 +86,7 @@ const agent = new Agent({
|
|
|
85
86
|
model: ({ requestContext }) => {
|
|
86
87
|
const useAdvanced = requestContext.task === "complex";
|
|
87
88
|
return useAdvanced
|
|
88
|
-
? "deepinfra/zai-org/GLM-5.
|
|
89
|
+
? "deepinfra/zai-org/GLM-5.2"
|
|
89
90
|
: "deepinfra/MiniMaxAI/MiniMax-M2.5";
|
|
90
91
|
}
|
|
91
92
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Friendli
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 7 Friendli models through Mastra's model router. Authentication is handled automatically using the `FRIENDLI_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Friendli documentation](https://friendli.ai/docs/guides/serverless_endpoints/introduction).
|
|
6
6
|
|
|
@@ -36,8 +36,6 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `friendli/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.50 | $2 |
|
|
38
38
|
| `friendli/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
39
|
-
| `friendli/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.10 | $0.10 |
|
|
40
|
-
| `friendli/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.60 | $0.60 |
|
|
41
39
|
| `friendli/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.30 | $1 |
|
|
42
40
|
| `friendli/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.20 | $0.80 |
|
|
43
41
|
| `friendli/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# GMI Cloud
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 11 GMI Cloud models through Mastra's model router. Authentication is handled automatically using the `GMICLOUD_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [GMI Cloud documentation](https://docs.gmicloud.ai).
|
|
6
6
|
|
|
@@ -15,7 +15,7 @@ const agent = new Agent({
|
|
|
15
15
|
id: "my-agent",
|
|
16
16
|
name: "My Agent",
|
|
17
17
|
instructions: "You are a helpful assistant",
|
|
18
|
-
model: "gmicloud/
|
|
18
|
+
model: "gmicloud/Qwen/Qwen3.7-Max"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -32,16 +32,19 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `gmicloud/anthropic/claude-opus-4.6`
|
|
38
|
-
| `gmicloud/anthropic/claude-opus-4.7`
|
|
39
|
-
| `gmicloud/anthropic/claude-sonnet-4.6`
|
|
40
|
-
| `gmicloud/deepseek-ai/DeepSeek-V4-Flash`
|
|
41
|
-
| `gmicloud/deepseek-ai/DeepSeek-V4-Pro`
|
|
42
|
-
| `gmicloud/moonshotai/Kimi-K2.6`
|
|
43
|
-
| `gmicloud/
|
|
44
|
-
| `gmicloud/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `gmicloud/anthropic/claude-opus-4.6` | 410K | | | | | | $5 | $25 |
|
|
38
|
+
| `gmicloud/anthropic/claude-opus-4.7` | 410K | | | | | | $5 | $23 |
|
|
39
|
+
| `gmicloud/anthropic/claude-sonnet-4.6` | 410K | | | | | | $3 | $15 |
|
|
40
|
+
| `gmicloud/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.11 | $0.22 |
|
|
41
|
+
| `gmicloud/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
42
|
+
| `gmicloud/moonshotai/Kimi-K2.6` | 66K | | | | | | $0.85 | $4 |
|
|
43
|
+
| `gmicloud/moonshotai/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
|
|
44
|
+
| `gmicloud/Qwen/Qwen3.7-Max` | 1.0M | | | | | | $3 | $8 |
|
|
45
|
+
| `gmicloud/zai-org/GLM-5-FP8` | 203K | | | | | | $0.60 | $2 |
|
|
46
|
+
| `gmicloud/zai-org/GLM-5.1-FP8` | 203K | | | | | | $0.98 | $3 |
|
|
47
|
+
| `gmicloud/zai-org/GLM-5.2-FP8` | 1.0M | | | | | | $0.98 | $3 |
|
|
45
48
|
|
|
46
49
|
## Advanced configuration
|
|
47
50
|
|
|
@@ -53,7 +56,7 @@ const agent = new Agent({
|
|
|
53
56
|
name: "custom-agent",
|
|
54
57
|
model: {
|
|
55
58
|
url: "https://api.gmi-serving.com/v1",
|
|
56
|
-
id: "gmicloud/
|
|
59
|
+
id: "gmicloud/Qwen/Qwen3.7-Max",
|
|
57
60
|
apiKey: process.env.GMICLOUD_API_KEY,
|
|
58
61
|
headers: {
|
|
59
62
|
"X-Custom-Header": "value"
|
|
@@ -71,8 +74,8 @@ const agent = new Agent({
|
|
|
71
74
|
model: ({ requestContext }) => {
|
|
72
75
|
const useAdvanced = requestContext.task === "complex";
|
|
73
76
|
return useAdvanced
|
|
74
|
-
? "gmicloud/zai-org/GLM-5.
|
|
75
|
-
: "gmicloud/
|
|
77
|
+
? "gmicloud/zai-org/GLM-5.2-FP8"
|
|
78
|
+
: "gmicloud/Qwen/Qwen3.7-Max";
|
|
76
79
|
}
|
|
77
80
|
});
|
|
78
81
|
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Hugging Face
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 50 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Hugging Face documentation](https://huggingface.co).
|
|
6
6
|
|
|
@@ -53,6 +53,7 @@ for await (const chunk of stream) {
|
|
|
53
53
|
| `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
54
54
|
| `huggingface/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
55
55
|
| `huggingface/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
56
|
+
| `huggingface/openai/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
|
|
56
57
|
| `huggingface/Qwen/Qwen3-235B-A22B` | 41K | | | | | | $0.20 | $0.80 |
|
|
57
58
|
| `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.30 | $3 |
|
|
58
59
|
| `huggingface/Qwen/Qwen3-32B` | 131K | | | | | | $0.29 | $0.59 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Inceptron
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 6 Inceptron models through Mastra's model router. Authentication is handled automatically using the `INCEPTRON_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Inceptron documentation](https://docs.inceptron.io).
|
|
6
6
|
|
|
@@ -32,12 +32,14 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `inceptron/MiniMaxAI/MiniMax-M2.5`
|
|
38
|
-
| `inceptron/moonshotai/Kimi-K2.6`
|
|
39
|
-
| `inceptron/
|
|
40
|
-
| `inceptron/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `inceptron/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.15 | $0.90 |
|
|
38
|
+
| `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.66 | $4 |
|
|
39
|
+
| `inceptron/moonshotai/Kimi-K2.6-Fast` | 262K | | | | | | $1 | $7 |
|
|
40
|
+
| `inceptron/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.75 | $4 |
|
|
41
|
+
| `inceptron/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
42
|
+
| `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
41
43
|
|
|
42
44
|
## Advanced configuration
|
|
43
45
|
|
|
@@ -67,7 +69,7 @@ const agent = new Agent({
|
|
|
67
69
|
model: ({ requestContext }) => {
|
|
68
70
|
const useAdvanced = requestContext.task === "complex";
|
|
69
71
|
return useAdvanced
|
|
70
|
-
? "inceptron/zai-org/GLM-5.
|
|
72
|
+
? "inceptron/zai-org/GLM-5.2"
|
|
71
73
|
: "inceptron/MiniMaxAI/MiniMax-M2.5";
|
|
72
74
|
}
|
|
73
75
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# LLM Gateway
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 178 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
6
6
|
|
|
@@ -40,6 +40,7 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| `llmgateway/claude-3-opus` | 200K | | | | | | $15 | $75 |
|
|
41
41
|
| `llmgateway/claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
|
|
42
42
|
| `llmgateway/claude-haiku-4-5-20251001` | 200K | | | | | | $1 | $5 |
|
|
43
|
+
| `llmgateway/claude-haiku-4-5-free` | 200K | | | | | | — | — |
|
|
43
44
|
| `llmgateway/claude-opus-4-1-20250805` | 200K | | | | | | $15 | $75 |
|
|
44
45
|
| `llmgateway/claude-opus-4-5-20251101` | 200K | | | | | | $5 | $25 |
|
|
45
46
|
| `llmgateway/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
@@ -70,16 +71,13 @@ for await (const chunk of stream) {
|
|
|
70
71
|
| `llmgateway/glm-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
71
72
|
| `llmgateway/glm-4.5-air` | 131K | | | | | | $0.13 | $0.85 |
|
|
72
73
|
| `llmgateway/glm-4.5-airx` | 128K | | | | | | $1 | $5 |
|
|
73
|
-
| `llmgateway/glm-4.5-flash` | 128K | | | | | | — | — |
|
|
74
74
|
| `llmgateway/glm-4.5-x` | 128K | | | | | | $2 | $9 |
|
|
75
75
|
| `llmgateway/glm-4.5v` | 128K | | | | | | $0.60 | $2 |
|
|
76
76
|
| `llmgateway/glm-4.6` | 205K | | | | | | $0.43 | $2 |
|
|
77
77
|
| `llmgateway/glm-4.6v` | 131K | | | | | | $0.30 | $0.90 |
|
|
78
|
-
| `llmgateway/glm-4.6v-flash` | 128K | | | | | | — | — |
|
|
79
78
|
| `llmgateway/glm-4.6v-flashx` | 128K | | | | | | $0.04 | $0.40 |
|
|
80
79
|
| `llmgateway/glm-4.7` | 205K | | | | | | $0.38 | $2 |
|
|
81
80
|
| `llmgateway/glm-4.7-flash` | 200K | | | | | | $0.06 | $0.40 |
|
|
82
|
-
| `llmgateway/glm-4.7-flash-free` | 200K | | | | | | — | — |
|
|
83
81
|
| `llmgateway/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.40 |
|
|
84
82
|
| `llmgateway/glm-5` | 203K | | | | | | $0.72 | $2 |
|
|
85
83
|
| `llmgateway/glm-5.1` | 205K | | | | | | $0.93 | $3 |
|
|
@@ -127,9 +125,8 @@ for await (const chunk of stream) {
|
|
|
127
125
|
| `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
128
126
|
| `llmgateway/kimi-k2` | 256K | | | | | | $0.57 | $2 |
|
|
129
127
|
| `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.57 | $2 |
|
|
130
|
-
| `llmgateway/kimi-k2-thinking-turbo` | 262K | | | | | | $1 | $8 |
|
|
131
128
|
| `llmgateway/kimi-k2.5` | 262K | | | | | | $0.41 | $2 |
|
|
132
|
-
| `llmgateway/kimi-k2.6` | 262K | | | | | | $0.
|
|
129
|
+
| `llmgateway/kimi-k2.6` | 262K | | | | | | $0.40 | $2 |
|
|
133
130
|
| `llmgateway/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
134
131
|
| `llmgateway/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
|
|
135
132
|
| `llmgateway/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Neuralwatt
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 18 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).
|
|
6
6
|
|
|
@@ -34,12 +34,17 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `neuralwatt/glm-5-fast` | 203K | | | | | | $1 | $4 |
|
|
38
|
-
| `neuralwatt/glm-5.1-fast` | 203K | | | | | | $1 | $4 |
|
|
39
37
|
| `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
|
|
38
|
+
| `neuralwatt/glm-5.2-fast` | 1.0M | | | | | | $1 | $5 |
|
|
39
|
+
| `neuralwatt/glm-5.2-flex` | 1.0M | | | | | | $0.72 | $2 |
|
|
40
40
|
| `neuralwatt/glm-5.2-short` | 200K | | | | | | $1 | $5 |
|
|
41
|
+
| `neuralwatt/glm-5.2-short-fast` | 200K | | | | | | $1 | $5 |
|
|
42
|
+
| `neuralwatt/glm-5.2-short-fast-flex` | 200K | | | | | | $0.72 | $2 |
|
|
43
|
+
| `neuralwatt/glm-5.2-short-flex` | 200K | | | | | | $0.72 | $2 |
|
|
41
44
|
| `neuralwatt/kimi-k2.5-fast` | 262K | | | | | | $0.52 | $3 |
|
|
42
45
|
| `neuralwatt/kimi-k2.6-fast` | 262K | | | | | | $0.69 | $3 |
|
|
46
|
+
| `neuralwatt/kimi-k2.6-flex` | 262K | | | | | | $0.34 | $2 |
|
|
47
|
+
| `neuralwatt/kimi-k2.7-code-flex` | 262K | | | | | | $0.47 | $2 |
|
|
43
48
|
| `neuralwatt/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.52 | $3 |
|
|
44
49
|
| `neuralwatt/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.69 | $3 |
|
|
45
50
|
| `neuralwatt/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
@@ -47,7 +52,6 @@ for await (const chunk of stream) {
|
|
|
47
52
|
| `neuralwatt/Qwen/Qwen3.6-35B-A3B` | 131K | | | | | | $0.29 | $1 |
|
|
48
53
|
| `neuralwatt/qwen3.5-397b-fast` | 262K | | | | | | $0.69 | $4 |
|
|
49
54
|
| `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
|
|
50
|
-
| `neuralwatt/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
51
55
|
|
|
52
56
|
## Advanced configuration
|
|
53
57
|
|
|
@@ -77,7 +81,7 @@ const agent = new Agent({
|
|
|
77
81
|
model: ({ requestContext }) => {
|
|
78
82
|
const useAdvanced = requestContext.task === "complex";
|
|
79
83
|
return useAdvanced
|
|
80
|
-
? "neuralwatt/
|
|
84
|
+
? "neuralwatt/qwen3.6-35b-fast"
|
|
81
85
|
: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8";
|
|
82
86
|
}
|
|
83
87
|
});
|
|
@@ -63,7 +63,7 @@ for await (const chunk of stream) {
|
|
|
63
63
|
| `novita-ai/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
64
64
|
| `novita-ai/google/gemma-4-31b-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
65
65
|
| `novita-ai/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.09 | $0.09 |
|
|
66
|
-
| `novita-ai/inclusionai/ling-2.6-1t` | 262K | | | | | |
|
|
66
|
+
| `novita-ai/inclusionai/ling-2.6-1t` | 262K | | | | | | $0.30 | $3 |
|
|
67
67
|
| `novita-ai/inclusionai/ling-2.6-flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
68
68
|
| `novita-ai/inclusionai/ring-2.6-1t` | 262K | | | | | | $0.30 | $3 |
|
|
69
69
|
| `novita-ai/kwaipilot/kat-coder-pro` | 256K | | | | | | $0.30 | $1 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Nvidia
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 84 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
|
|
6
6
|
|
|
@@ -62,6 +62,7 @@ for await (const chunk of stream) {
|
|
|
62
62
|
| `nvidia/microsoft/phi-4-mini-instruct` | 131K | | | | | | — | — |
|
|
63
63
|
| `nvidia/microsoft/phi-4-multimodal-instruct` | 128K | | | | | | — | — |
|
|
64
64
|
| `nvidia/minimaxai/minimax-m2.7` | 205K | | | | | | — | — |
|
|
65
|
+
| `nvidia/minimaxai/minimax-m3` | 1.0M | | | | | | — | — |
|
|
65
66
|
| `nvidia/mistralai/magistral-small-2506` | 33K | | | | | | — | — |
|
|
66
67
|
| `nvidia/mistralai/mistral-7b-instruct-v03` | 66K | | | | | | — | — |
|
|
67
68
|
| `nvidia/mistralai/mistral-large-3-675b-instruct-2512` | 262K | | | | | | — | — |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# SiliconFlow (China)
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 47 SiliconFlow (China) models through Mastra's model router. Authentication is handled automatically using the `SILICONFLOW_CN_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [SiliconFlow (China) documentation](https://cloud.siliconflow.com/models).
|
|
6
6
|
|
|
@@ -32,83 +32,55 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `siliconflow-cn/baidu/ERNIE-4.5-300B-A47B`
|
|
38
|
-
| `siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct`
|
|
39
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-OCR`
|
|
40
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-R1`
|
|
41
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-
|
|
42
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-
|
|
43
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-V3`
|
|
44
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-
|
|
45
|
-
| `siliconflow-cn/deepseek-ai/DeepSeek-
|
|
46
|
-
| `siliconflow-cn/
|
|
47
|
-
| `siliconflow-cn/
|
|
48
|
-
| `siliconflow-cn/deepseek-ai/
|
|
49
|
-
| `siliconflow-cn/
|
|
50
|
-
| `siliconflow-cn/
|
|
51
|
-
| `siliconflow-cn/
|
|
52
|
-
| `siliconflow-cn/
|
|
53
|
-
| `siliconflow-cn/
|
|
54
|
-
| `siliconflow-cn/Pro/
|
|
55
|
-
| `siliconflow-cn/Pro/
|
|
56
|
-
| `siliconflow-cn/Pro/
|
|
57
|
-
| `siliconflow-cn/
|
|
58
|
-
| `siliconflow-cn/
|
|
59
|
-
| `siliconflow-cn/
|
|
60
|
-
| `siliconflow-cn/
|
|
61
|
-
| `siliconflow-cn/
|
|
62
|
-
| `siliconflow-cn/
|
|
63
|
-
| `siliconflow-cn/
|
|
64
|
-
| `siliconflow-cn/
|
|
65
|
-
| `siliconflow-cn/
|
|
66
|
-
| `siliconflow-cn/
|
|
67
|
-
| `siliconflow-cn/Qwen/
|
|
68
|
-
| `siliconflow-cn/Qwen/
|
|
69
|
-
| `siliconflow-cn/Qwen/
|
|
70
|
-
| `siliconflow-cn/Qwen/
|
|
71
|
-
| `siliconflow-cn/Qwen/
|
|
72
|
-
| `siliconflow-cn/Qwen/
|
|
73
|
-
| `siliconflow-cn/Qwen/
|
|
74
|
-
| `siliconflow-cn/Qwen/
|
|
75
|
-
| `siliconflow-cn/Qwen/Qwen3-
|
|
76
|
-
| `siliconflow-cn/Qwen/Qwen3-
|
|
77
|
-
| `siliconflow-cn/Qwen/Qwen3-
|
|
78
|
-
| `siliconflow-cn/Qwen/Qwen3-
|
|
79
|
-
| `siliconflow-cn/Qwen/Qwen3-
|
|
80
|
-
| `siliconflow-cn/
|
|
81
|
-
| `siliconflow-cn/
|
|
82
|
-
| `siliconflow-cn/
|
|
83
|
-
| `siliconflow-cn/
|
|
84
|
-
| `siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.14 | $1 |
|
|
85
|
-
| `siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Thinking` | 262K | | | | | | $0.14 | $0.57 |
|
|
86
|
-
| `siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Captioner` | 66K | | | | | | $0.10 | $0.40 |
|
|
87
|
-
| `siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Instruct` | 66K | | | | | | $0.10 | $0.40 |
|
|
88
|
-
| `siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Thinking` | 66K | | | | | | $0.10 | $0.40 |
|
|
89
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct` | 262K | | | | | | $0.30 | $2 |
|
|
90
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking` | 262K | | | | | | $0.45 | $4 |
|
|
91
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct` | 262K | | | | | | $0.29 | $1 |
|
|
92
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking` | 262K | | | | | | $0.29 | $1 |
|
|
93
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct` | 262K | | | | | | $0.20 | $0.60 |
|
|
94
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking` | 262K | | | | | | $0.20 | $2 |
|
|
95
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct` | 262K | | | | | | $0.18 | $0.68 |
|
|
96
|
-
| `siliconflow-cn/Qwen/Qwen3-VL-8B-Thinking` | 262K | | | | | | $0.18 | $2 |
|
|
97
|
-
| `siliconflow-cn/Qwen/Qwen3.5-122B-A10B` | 262K | | | | | | $0.29 | $2 |
|
|
98
|
-
| `siliconflow-cn/Qwen/Qwen3.5-27B` | 262K | | | | | | $0.26 | $2 |
|
|
99
|
-
| `siliconflow-cn/Qwen/Qwen3.5-35B-A3B` | 262K | | | | | | $0.23 | $2 |
|
|
100
|
-
| `siliconflow-cn/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.29 | $2 |
|
|
101
|
-
| `siliconflow-cn/Qwen/Qwen3.5-4B` | 262K | | | | | | — | — |
|
|
102
|
-
| `siliconflow-cn/Qwen/Qwen3.5-9B` | 262K | | | | | | $0.22 | $2 |
|
|
103
|
-
| `siliconflow-cn/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.23 | $2 |
|
|
104
|
-
| `siliconflow-cn/Qwen/QwQ-32B` | 131K | | | | | | $0.15 | $0.58 |
|
|
105
|
-
| `siliconflow-cn/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
106
|
-
| `siliconflow-cn/tencent/Hunyuan-A13B-Instruct` | 131K | | | | | | $0.14 | $0.57 |
|
|
107
|
-
| `siliconflow-cn/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.14 | $0.86 |
|
|
108
|
-
| `siliconflow-cn/zai-org/GLM-4.5V` | 66K | | | | | | $0.14 | $0.86 |
|
|
109
|
-
| `siliconflow-cn/zai-org/GLM-4.6` | 205K | | | | | | $0.50 | $2 |
|
|
110
|
-
| `siliconflow-cn/zai-org/GLM-4.6V` | 131K | | | | | | $0.30 | $0.90 |
|
|
111
|
-
| `siliconflow-cn/zai-org/GLM-5.2` | 205K | | | | | | $1 | $4 |
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `siliconflow-cn/baidu/ERNIE-4.5-300B-A47B` | 131K | | | | | | $0.28 | $1 |
|
|
38
|
+
| `siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct` | 262K | | | | | | $0.21 | $0.57 |
|
|
39
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-OCR` | 8K | | | | | | — | — |
|
|
40
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-R1` | 164K | | | | | | $0.50 | $2 |
|
|
41
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-V3` | 164K | | | | | | $0.25 | $1 |
|
|
42
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-V3.1-Terminus` | 164K | | | | | | $0.27 | $1 |
|
|
43
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.27 | $0.42 |
|
|
44
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
45
|
+
| `siliconflow-cn/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $3 |
|
|
46
|
+
| `siliconflow-cn/inclusionAI/Ling-flash-2.0` | 131K | | | | | | $0.14 | $0.57 |
|
|
47
|
+
| `siliconflow-cn/PaddlePaddle/PaddleOCR-VL-1.5` | 16K | | | | | | — | — |
|
|
48
|
+
| `siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1` | 164K | | | | | | $0.50 | $2 |
|
|
49
|
+
| `siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3` | 164K | | | | | | $0.25 | $1 |
|
|
50
|
+
| `siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.1-Terminus` | 164K | | | | | | $0.27 | $1 |
|
|
51
|
+
| `siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.27 | $0.42 |
|
|
52
|
+
| `siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.5` | 192K | | | | | | $0.30 | $1 |
|
|
53
|
+
| `siliconflow-cn/Pro/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.45 | $2 |
|
|
54
|
+
| `siliconflow-cn/Pro/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
55
|
+
| `siliconflow-cn/Pro/zai-org/GLM-5` | 205K | | | | | | $1 | $3 |
|
|
56
|
+
| `siliconflow-cn/Pro/zai-org/GLM-5.1` | 205K | | | | | | $1 | $4 |
|
|
57
|
+
| `siliconflow-cn/Qwen/Qwen2.5-72B-Instruct` | 33K | | | | | | $0.59 | $0.59 |
|
|
58
|
+
| `siliconflow-cn/Qwen/Qwen2.5-7B-Instruct` | 33K | | | | | | $0.05 | $0.05 |
|
|
59
|
+
| `siliconflow-cn/Qwen/Qwen3-14B` | 131K | | | | | | $0.07 | $0.28 |
|
|
60
|
+
| `siliconflow-cn/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.13 | $0.60 |
|
|
61
|
+
| `siliconflow-cn/Qwen/Qwen3-30B-A3B-Instruct-2507` | 262K | | | | | | $0.09 | $0.30 |
|
|
62
|
+
| `siliconflow-cn/Qwen/Qwen3-32B` | 131K | | | | | | $0.14 | $0.57 |
|
|
63
|
+
| `siliconflow-cn/Qwen/Qwen3-8B` | 131K | | | | | | $0.06 | $0.06 |
|
|
64
|
+
| `siliconflow-cn/Qwen/Qwen3-Coder-30B-A3B-Instruct` | 262K | | | | | | $0.07 | $0.28 |
|
|
65
|
+
| `siliconflow-cn/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $0.25 | $1 |
|
|
66
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct` | 262K | | | | | | $0.30 | $2 |
|
|
67
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking` | 262K | | | | | | $0.45 | $4 |
|
|
68
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct` | 262K | | | | | | $0.29 | $1 |
|
|
69
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking` | 262K | | | | | | $0.29 | $1 |
|
|
70
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct` | 262K | | | | | | $0.20 | $0.60 |
|
|
71
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking` | 262K | | | | | | $0.20 | $2 |
|
|
72
|
+
| `siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct` | 262K | | | | | | $0.18 | $0.68 |
|
|
73
|
+
| `siliconflow-cn/Qwen/Qwen3.5-122B-A10B` | 262K | | | | | | $0.29 | $2 |
|
|
74
|
+
| `siliconflow-cn/Qwen/Qwen3.5-27B` | 262K | | | | | | $0.26 | $2 |
|
|
75
|
+
| `siliconflow-cn/Qwen/Qwen3.5-35B-A3B` | 262K | | | | | | $0.23 | $2 |
|
|
76
|
+
| `siliconflow-cn/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.29 | $2 |
|
|
77
|
+
| `siliconflow-cn/Qwen/Qwen3.5-4B` | 262K | | | | | | — | — |
|
|
78
|
+
| `siliconflow-cn/Qwen/Qwen3.5-9B` | 262K | | | | | | $0.22 | $2 |
|
|
79
|
+
| `siliconflow-cn/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.23 | $2 |
|
|
80
|
+
| `siliconflow-cn/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
81
|
+
| `siliconflow-cn/tencent/Hunyuan-A13B-Instruct` | 131K | | | | | | $0.14 | $0.57 |
|
|
82
|
+
| `siliconflow-cn/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.14 | $0.86 |
|
|
83
|
+
| `siliconflow-cn/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
112
84
|
|
|
113
85
|
## Advanced configuration
|
|
114
86
|
|