@mastra/mcp-docs-server 1.2.24-alpha.3 → 1.2.24-alpha.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.docs/models/environment-variables.md +1 -0
- package/.docs/models/gateways/netlify.md +6 -1
- package/.docs/models/gateways/openrouter.md +2 -1
- package/.docs/models/gateways/vercel.md +2 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/amd.md +7 -5
- package/.docs/models/providers/deepinfra.md +2 -1
- package/.docs/models/providers/edenai.md +7 -4
- package/.docs/models/providers/empiriolabs.md +2 -1
- package/.docs/models/providers/huggingface.md +76 -75
- package/.docs/models/providers/hyper.md +3 -3
- package/.docs/models/providers/kilo.md +7 -6
- package/.docs/models/providers/llmgateway-providers.md +4 -1
- package/.docs/models/providers/llmgateway.md +7 -5
- package/.docs/models/providers/meta.md +4 -2
- package/.docs/models/providers/nan.md +83 -0
- package/.docs/models/providers/nano-gpt.md +45 -44
- package/.docs/models/providers/ofox.md +3 -1
- package/.docs/models/providers/tinfoil.md +1 -1
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/client-js/observability.md +29 -0
- package/.docs/reference/index.md +1 -0
- package/.docs/reference/observability/tracing/trace-query.md +179 -0
- package/.docs/reference/rag/metadata-filters.md +1 -0
- package/package.json +4 -4
|
@@ -117,6 +117,7 @@ List of required environment variables for each model provider and gateway suppo
|
|
|
117
117
|
| [Moonshot AI](https://mastra.ai/models/providers/moonshotai) | `moonshotai/*` | `MOONSHOT_API_KEY` |
|
|
118
118
|
| [Moonshot AI (China)](https://mastra.ai/models/providers/moonshotai-cn) | `moonshotai-cn/*` | `MOONSHOT_API_KEY` |
|
|
119
119
|
| [Morph](https://mastra.ai/models/providers/morph) | `morph/*` | `MORPH_API_KEY` |
|
|
120
|
+
| [NaN](https://mastra.ai/models/providers/nan) | `nan/*` | `NAN_API_KEY` |
|
|
120
121
|
| [NanoGPT](https://mastra.ai/models/providers/nano-gpt) | `nano-gpt/*` | `NANO_GPT_API_KEY` |
|
|
121
122
|
| [NEAR AI Cloud](https://mastra.ai/models/providers/nearai) | `nearai/*` | `NEARAI_API_KEY` |
|
|
122
123
|
| [Nebius Token Factory](https://mastra.ai/models/providers/nebius) | `nebius/*` | `NEBIUS_API_KEY` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Netlify
|
|
6
6
|
|
|
7
|
-
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access
|
|
7
|
+
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 242 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
|
|
10
10
|
|
|
@@ -149,6 +149,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
149
149
|
| `openrouter/inception/mercury-2` |
|
|
150
150
|
| `openrouter/inception/mercury-2.5-preview` |
|
|
151
151
|
| `openrouter/inclusionai/ling-3.0-flash` |
|
|
152
|
+
| `openrouter/inclusionai/ling-3.0-flash-fin` |
|
|
152
153
|
| `openrouter/inclusionai/ling-3.0-flash-fin:free` |
|
|
153
154
|
| `openrouter/mancer/weaver` |
|
|
154
155
|
| `openrouter/meta-llama/llama-3.1-70b-instruct` |
|
|
@@ -171,14 +172,17 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
171
172
|
| `openrouter/mistralai/ministral-14b-2512` |
|
|
172
173
|
| `openrouter/mistralai/ministral-3b-2512` |
|
|
173
174
|
| `openrouter/mistralai/ministral-8b-2512` |
|
|
175
|
+
| `openrouter/mistralai/mistral-large-2407` |
|
|
174
176
|
| `openrouter/mistralai/mistral-large-2512` |
|
|
175
177
|
| `openrouter/mistralai/mistral-medium-3` |
|
|
176
178
|
| `openrouter/mistralai/mistral-medium-3-5` |
|
|
177
179
|
| `openrouter/mistralai/mistral-medium-3.1` |
|
|
178
180
|
| `openrouter/mistralai/mistral-nemo` |
|
|
181
|
+
| `openrouter/mistralai/mistral-saba` |
|
|
179
182
|
| `openrouter/mistralai/mistral-small-24b-instruct-2501` |
|
|
180
183
|
| `openrouter/mistralai/mistral-small-2603` |
|
|
181
184
|
| `openrouter/mistralai/mistral-small-3.2-24b-instruct` |
|
|
185
|
+
| `openrouter/mistralai/mixtral-8x22b-instruct` |
|
|
182
186
|
| `openrouter/mistralai/voxtral-small-24b-2507` |
|
|
183
187
|
| `openrouter/moonshotai/kimi-k2` |
|
|
184
188
|
| `openrouter/moonshotai/kimi-k2-0905` |
|
|
@@ -196,6 +200,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
196
200
|
| `openrouter/nvidia/nemotron-3-nano-30b-a3b` |
|
|
197
201
|
| `openrouter/nvidia/nemotron-3-super-120b-a12b` |
|
|
198
202
|
| `openrouter/nvidia/nemotron-3-ultra-550b-a55b` |
|
|
203
|
+
| `openrouter/nvidia/nemotron-3.5-content-safety` |
|
|
199
204
|
| `openrouter/nvidia/nemotron-3.5-lightning` |
|
|
200
205
|
| `openrouter/openai/gpt-oss-120b` |
|
|
201
206
|
| `openrouter/openai/gpt-oss-20b` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenRouter
|
|
6
6
|
|
|
7
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 358 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -144,6 +144,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
144
144
|
| `inception/mercury-2` |
|
|
145
145
|
| `inception/mercury-2.5-preview` |
|
|
146
146
|
| `inclusionai/ling-3.0-flash` |
|
|
147
|
+
| `inclusionai/ling-3.0-flash-fin` |
|
|
147
148
|
| `inclusionai/ling-3.0-flash-fin:free` |
|
|
148
149
|
| `kwaipilot/kat-coder-pro-v2` |
|
|
149
150
|
| `kwaipilot/kat-coder-pro-v2.5` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Vercel
|
|
6
6
|
|
|
7
|
-
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 369 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
|
|
10
10
|
|
|
@@ -403,6 +403,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
403
403
|
| `zai/glm-5.2` |
|
|
404
404
|
| `zai/glm-5.2-fast` |
|
|
405
405
|
| `zai/glm-5.3` |
|
|
406
|
+
| `zai/glm-5.3-fast` |
|
|
406
407
|
| `zai/glm-5.3-flash` |
|
|
407
408
|
| `zai/glm-5.3-promo-50` |
|
|
408
409
|
| `zai/glm-5v-turbo` |
|
package/.docs/models/index.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Model Providers
|
|
6
6
|
|
|
7
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
7
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7064 models from 200 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# AMD
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 4 AMD models through Mastra's model router. Authentication is handled automatically using the `AMD_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [AMD documentation](https://developer.amd.com.cn/radeon/tokenfactory).
|
|
10
10
|
|
|
@@ -36,10 +36,12 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `amd/DeepSeek-V4-Flash`
|
|
42
|
-
| `amd/
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `amd/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
42
|
+
| `amd/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
43
|
+
| `amd/MiniCPM5-1B` | 131K | | | | | | $0.12 | $0.74 |
|
|
44
|
+
| `amd/Qwen3.8-Flash-Next` | 262K | | | | | | $0.15 | $0.47 |
|
|
43
45
|
|
|
44
46
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
45
47
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Deep Infra
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 63 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
|
|
10
10
|
|
|
@@ -46,6 +46,7 @@ for await (const chunk of stream) {
|
|
|
46
46
|
| `deepinfra/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.26 | $0.38 |
|
|
47
47
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.09 | $0.18 |
|
|
48
48
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
49
|
+
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
49
50
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
50
51
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
51
52
|
| `deepinfra/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.07 | $0.34 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Eden AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 246 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
|
|
|
@@ -107,7 +107,6 @@ for await (const chunk of stream) {
|
|
|
107
107
|
| `edenai/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
108
108
|
| `edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
109
109
|
| `edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
110
|
-
| `edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
111
110
|
| `edenai/fireworks_ai/accounts/fireworks/models/muse-glimmer-30b` | 131K | | | | | | $0.35 | $2 |
|
|
112
111
|
| `edenai/fireworks_ai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
113
112
|
| `edenai/flexai/deepseek-v4-flash-0731` | 786K | | | | | | $0.03 | $0.10 |
|
|
@@ -131,6 +130,7 @@ for await (const chunk of stream) {
|
|
|
131
130
|
| `edenai/google/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
132
131
|
| `edenai/google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
133
132
|
| `edenai/google/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
133
|
+
| `edenai/google/gemini-3.8-flash` | 1.0M | | | | | | $2 | $8 |
|
|
134
134
|
| `edenai/google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
135
135
|
| `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
136
136
|
| `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
@@ -225,11 +225,11 @@ for await (const chunk of stream) {
|
|
|
225
225
|
| `edenai/qwen/qwen3-vl-235b-a22b-thinking` | 131K | | | | | | $0.40 | $4 |
|
|
226
226
|
| `edenai/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
227
227
|
| `edenai/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.50 | $3 |
|
|
228
|
-
| `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.
|
|
228
|
+
| `edenai/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
229
229
|
| `edenai/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
230
230
|
| `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
231
231
|
| `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
|
|
232
|
-
| `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.
|
|
232
|
+
| `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
|
|
233
233
|
| `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
|
|
234
234
|
| `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
|
|
235
235
|
| `edenai/tensorx/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
|
|
@@ -262,6 +262,9 @@ for await (const chunk of stream) {
|
|
|
262
262
|
| `edenai/vertex/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
263
263
|
| `edenai/vertex/gemini-3.7-flash@eu` | 1.0M | | | | | | $0.75 | $4 |
|
|
264
264
|
| `edenai/vertex/gemini-3.7-flash@us` | 1.0M | | | | | | $0.75 | $4 |
|
|
265
|
+
| `edenai/vertex/gemini-3.8-flash` | 1.0M | | | | | | $2 | $8 |
|
|
266
|
+
| `edenai/vertex/gemini-3.8-flash@eu` | 1.0M | | | | | | $2 | $8 |
|
|
267
|
+
| `edenai/vertex/gemini-3.8-flash@us` | 1.0M | | | | | | $2 | $8 |
|
|
265
268
|
| `edenai/vertex/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
266
269
|
| `edenai/vertex/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
267
270
|
| `edenai/xai/grok-4.20-0309-non-reasoning` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# EmpirioLabs AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 58 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
|
|
|
@@ -66,6 +66,7 @@ for await (const chunk of stream) {
|
|
|
66
66
|
| `empiriolabs/muse-glimmer-30b` | 131K | | | | | | $0.20 | $0.80 |
|
|
67
67
|
| `empiriolabs/muse-spark-1-1` | 1.0M | | | | | | $1 | $4 |
|
|
68
68
|
| `empiriolabs/muse-spark-1-2` | 1.0M | | | | | | $1 | $4 |
|
|
69
|
+
| `empiriolabs/muse-spark-1-3` | 1.0M | | | | | | $1 | $4 |
|
|
69
70
|
| `empiriolabs/qwen3-5-122b-a10b` | 256K | | | | | | $0.12 | $0.92 |
|
|
70
71
|
| `empiriolabs/qwen3-5-27b` | 256K | | | | | | $0.09 | $0.69 |
|
|
71
72
|
| `empiriolabs/qwen3-5-35b-a3b` | 256K | | | | | | $0.06 | $0.46 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Hugging Face
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 73 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
|
|
|
@@ -36,80 +36,81 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `huggingface/deepseek-ai/DeepSeek-R1`
|
|
42
|
-
| `huggingface/deepseek-ai/DeepSeek-R1-0528`
|
|
43
|
-
| `huggingface/deepseek-ai/DeepSeek-V3`
|
|
44
|
-
| `huggingface/deepseek-ai/DeepSeek-V3-0324`
|
|
45
|
-
| `huggingface/deepseek-ai/DeepSeek-V3.1`
|
|
46
|
-
| `huggingface/deepseek-ai/DeepSeek-V3.2`
|
|
47
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Flash`
|
|
48
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-0731`
|
|
49
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-
|
|
50
|
-
| `huggingface/deepseek-ai/DeepSeek-V4-Pro
|
|
51
|
-
| `huggingface/
|
|
52
|
-
| `huggingface/google/gemma-4-
|
|
53
|
-
| `huggingface/
|
|
54
|
-
| `huggingface/meta-llama/Llama-3.
|
|
55
|
-
| `huggingface/
|
|
56
|
-
| `huggingface/MiniMaxAI/MiniMax-M2
|
|
57
|
-
| `huggingface/MiniMaxAI/MiniMax-M2.
|
|
58
|
-
| `huggingface/MiniMaxAI/MiniMax-M2.
|
|
59
|
-
| `huggingface/MiniMaxAI/MiniMax-
|
|
60
|
-
| `huggingface/
|
|
61
|
-
| `huggingface/moonshotai/Kimi-K2-Instruct
|
|
62
|
-
| `huggingface/moonshotai/Kimi-K2-
|
|
63
|
-
| `huggingface/moonshotai/Kimi-K2
|
|
64
|
-
| `huggingface/moonshotai/Kimi-K2.
|
|
65
|
-
| `huggingface/moonshotai/Kimi-K2.
|
|
66
|
-
| `huggingface/moonshotai/Kimi-
|
|
67
|
-
| `huggingface/
|
|
68
|
-
| `huggingface/openai/gpt-oss-
|
|
69
|
-
| `huggingface/
|
|
70
|
-
| `huggingface/Qwen/
|
|
71
|
-
| `huggingface/Qwen/Qwen3-235B-A22B
|
|
72
|
-
| `huggingface/Qwen/Qwen3-235B-A22B-
|
|
73
|
-
| `huggingface/Qwen/Qwen3-
|
|
74
|
-
| `huggingface/Qwen/Qwen3-
|
|
75
|
-
| `huggingface/Qwen/Qwen3-
|
|
76
|
-
| `huggingface/Qwen/Qwen3-Coder-
|
|
77
|
-
| `huggingface/Qwen/Qwen3-Coder-
|
|
78
|
-
| `huggingface/Qwen/Qwen3-
|
|
79
|
-
| `huggingface/Qwen/Qwen3-Embedding-
|
|
80
|
-
| `huggingface/Qwen/Qwen3-
|
|
81
|
-
| `huggingface/Qwen/Qwen3-Next-80B-A3B-
|
|
82
|
-
| `huggingface/Qwen/Qwen3-
|
|
83
|
-
| `huggingface/Qwen/Qwen3-VL-235B-A22B-
|
|
84
|
-
| `huggingface/Qwen/Qwen3
|
|
85
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
86
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
87
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
88
|
-
| `huggingface/Qwen/Qwen3.5-
|
|
89
|
-
| `huggingface/Qwen/Qwen3.
|
|
90
|
-
| `huggingface/Qwen/Qwen3.6-
|
|
91
|
-
| `huggingface/Qwen/Qwen3.
|
|
92
|
-
| `huggingface/Qwen/Qwen3.8-
|
|
93
|
-
| `huggingface/
|
|
94
|
-
| `huggingface/stepfun-ai/Step-3.
|
|
95
|
-
| `huggingface/
|
|
96
|
-
| `huggingface/
|
|
97
|
-
| `huggingface/thinkingmachines/Inkling
|
|
98
|
-
| `huggingface/
|
|
99
|
-
| `huggingface/XiaomiMiMo/MiMo-V2
|
|
100
|
-
| `huggingface/XiaomiMiMo/MiMo-V2.5
|
|
101
|
-
| `huggingface/
|
|
102
|
-
| `huggingface/zai-org/GLM-4.5
|
|
103
|
-
| `huggingface/zai-org/GLM-4.
|
|
104
|
-
| `huggingface/zai-org/GLM-4.
|
|
105
|
-
| `huggingface/zai-org/GLM-4.
|
|
106
|
-
| `huggingface/zai-org/GLM-4.
|
|
107
|
-
| `huggingface/zai-org/GLM-4.7
|
|
108
|
-
| `huggingface/zai-org/GLM-
|
|
109
|
-
| `huggingface/zai-org/GLM-5
|
|
110
|
-
| `huggingface/zai-org/GLM-5.
|
|
111
|
-
| `huggingface/zai-org/GLM-5.
|
|
112
|
-
| `huggingface/zai-org/GLM-5.3
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `huggingface/deepseek-ai/DeepSeek-R1` | 64K | | | | | | $0.70 | $3 |
|
|
42
|
+
| `huggingface/deepseek-ai/DeepSeek-R1-0528` | 164K | | | | | | $3 | $5 |
|
|
43
|
+
| `huggingface/deepseek-ai/DeepSeek-V3` | 64K | | | | | | $0.40 | $1 |
|
|
44
|
+
| `huggingface/deepseek-ai/DeepSeek-V3-0324` | 164K | | | | | | $0.27 | $1 |
|
|
45
|
+
| `huggingface/deepseek-ai/DeepSeek-V3.1` | 131K | | | | | | $0.27 | $1 |
|
|
46
|
+
| `huggingface/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.28 | $0.40 |
|
|
47
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
48
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
49
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
50
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
51
|
+
| `huggingface/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
52
|
+
| `huggingface/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
53
|
+
| `huggingface/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
54
|
+
| `huggingface/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.06 | $0.06 |
|
|
55
|
+
| `huggingface/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.59 | $0.79 |
|
|
56
|
+
| `huggingface/MiniMaxAI/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
|
|
57
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
58
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
59
|
+
| `huggingface/MiniMaxAI/MiniMax-M2.7` | 205K | | | | | | $0.30 | $1 |
|
|
60
|
+
| `huggingface/MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.30 | $1 |
|
|
61
|
+
| `huggingface/moonshotai/Kimi-K2-Instruct` | 131K | | | | | | $1 | $3 |
|
|
62
|
+
| `huggingface/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $1 | $3 |
|
|
63
|
+
| `huggingface/moonshotai/Kimi-K2-Thinking` | 262K | | | | | | $0.60 | $3 |
|
|
64
|
+
| `huggingface/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
65
|
+
| `huggingface/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
66
|
+
| `huggingface/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
67
|
+
| `huggingface/moonshotai/Kimi-K3` | 1.0M | | | | | | $3 | $15 |
|
|
68
|
+
| `huggingface/openai/gpt-oss-120b` | 131K | | | | | | $0.25 | $0.69 |
|
|
69
|
+
| `huggingface/openai/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
|
|
70
|
+
| `huggingface/Qwen/Qwen2.5-Coder-32B-Instruct` | 131K | | | | | | $0.06 | $0.20 |
|
|
71
|
+
| `huggingface/Qwen/Qwen3-235B-A22B` | 41K | | | | | | $0.20 | $0.80 |
|
|
72
|
+
| `huggingface/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.85 | $3 |
|
|
73
|
+
| `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.30 | $3 |
|
|
74
|
+
| `huggingface/Qwen/Qwen3-30B-A3B` | 41K | | | | | | $0.12 | $0.50 |
|
|
75
|
+
| `huggingface/Qwen/Qwen3-32B` | 131K | | | | | | $0.29 | $0.59 |
|
|
76
|
+
| `huggingface/Qwen/Qwen3-Coder-30B-A3B-Instruct` | 262K | | | | | | $0.07 | $0.26 |
|
|
77
|
+
| `huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K | | | | | | $2 | $2 |
|
|
78
|
+
| `huggingface/Qwen/Qwen3-Coder-Next` | 262K | | | | | | $0.20 | $2 |
|
|
79
|
+
| `huggingface/Qwen/Qwen3-Embedding-4B` | 32K | | | | | | $0.01 | — |
|
|
80
|
+
| `huggingface/Qwen/Qwen3-Embedding-8B` | 32K | | | | | | $0.01 | — |
|
|
81
|
+
| `huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.25 | $1 |
|
|
82
|
+
| `huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking` | 262K | | | | | | $0.30 | $2 |
|
|
83
|
+
| `huggingface/Qwen/Qwen3-VL-235B-A22B-Instruct` | 131K | | | | | | $0.30 | $2 |
|
|
84
|
+
| `huggingface/Qwen/Qwen3-VL-235B-A22B-Thinking` | 131K | | | | | | $0.98 | $4 |
|
|
85
|
+
| `huggingface/Qwen/Qwen3.5-122B-A10B` | 262K | | | | | | $0.40 | $3 |
|
|
86
|
+
| `huggingface/Qwen/Qwen3.5-27B` | 262K | | | | | | $0.30 | $2 |
|
|
87
|
+
| `huggingface/Qwen/Qwen3.5-35B-A3B` | 262K | | | | | | $0.25 | $2 |
|
|
88
|
+
| `huggingface/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
|
|
89
|
+
| `huggingface/Qwen/Qwen3.5-9B` | 262K | | | | | | $0.17 | $0.25 |
|
|
90
|
+
| `huggingface/Qwen/Qwen3.6-27B` | 262K | | | | | | $0.47 | $3 |
|
|
91
|
+
| `huggingface/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.15 | $0.95 |
|
|
92
|
+
| `huggingface/Qwen/Qwen3.8-2.4T-A95B` | 262K | | | | | | $3 | $6 |
|
|
93
|
+
| `huggingface/Qwen/Qwen3.8-27B` | 262K | | | | | | $0.40 | $3 |
|
|
94
|
+
| `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
95
|
+
| `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
|
|
96
|
+
| `huggingface/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
97
|
+
| `huggingface/thinkingmachines/Inkling` | 1.0M | | | | | | $1 | $4 |
|
|
98
|
+
| `huggingface/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.50 | $1 |
|
|
99
|
+
| `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
100
|
+
| `huggingface/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.40 | $2 |
|
|
101
|
+
| `huggingface/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
102
|
+
| `huggingface/zai-org/GLM-4.5` | 131K | | | | | | $0.60 | $2 |
|
|
103
|
+
| `huggingface/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.13 | $0.85 |
|
|
104
|
+
| `huggingface/zai-org/GLM-4.5V` | 66K | | | | | | $0.60 | $2 |
|
|
105
|
+
| `huggingface/zai-org/GLM-4.6` | 205K | | | | | | $0.55 | $2 |
|
|
106
|
+
| `huggingface/zai-org/GLM-4.6V-Flash` | 131K | | | | | | $0.30 | $0.90 |
|
|
107
|
+
| `huggingface/zai-org/GLM-4.7` | 205K | | | | | | $0.60 | $2 |
|
|
108
|
+
| `huggingface/zai-org/GLM-4.7-Flash` | 200K | | | | | | — | — |
|
|
109
|
+
| `huggingface/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
110
|
+
| `huggingface/zai-org/GLM-5.1` | 203K | | | | | | $1 | $3 |
|
|
111
|
+
| `huggingface/zai-org/GLM-5.2` | 262K | | | | | | $1 | $4 |
|
|
112
|
+
| `huggingface/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
113
|
+
| `huggingface/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
113
114
|
|
|
114
115
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
115
116
|
|
|
@@ -42,8 +42,8 @@ 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.
|
|
46
|
-
| `hyper/glm-5` | 203K | | | | | | $0.
|
|
45
|
+
| `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.37 |
|
|
46
|
+
| `hyper/glm-5` | 203K | | | | | | $0.93 | $3 |
|
|
47
47
|
| `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
48
48
|
| `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
|
|
49
49
|
| `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
|
|
@@ -56,7 +56,7 @@ for await (const chunk of stream) {
|
|
|
56
56
|
| `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
|
|
57
57
|
| `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
|
|
58
58
|
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.90 |
|
|
59
|
-
| `hyper/minimax-m2.7` | 262K | | | | | | $0.
|
|
59
|
+
| `hyper/minimax-m2.7` | 262K | | | | | | $0.42 | $2 |
|
|
60
60
|
| `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
|
|
61
61
|
| `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
|
|
62
62
|
| `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 366 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
10
10
|
|
|
@@ -45,12 +45,12 @@ for await (const chunk of stream) {
|
|
|
45
45
|
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.05 | $0.16 |
|
|
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 | | | | | | $3 | $
|
|
48
|
+
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $3 | $14 |
|
|
49
49
|
| `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
|
|
50
50
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
51
51
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
52
52
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
53
|
-
| `kilo/~z-ai/glm-latest` |
|
|
53
|
+
| `kilo/~z-ai/glm-latest` | 262K | | | | | | $1 | $4 |
|
|
54
54
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
55
55
|
| `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
|
|
56
56
|
| `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
|
|
@@ -93,7 +93,7 @@ for await (const chunk of stream) {
|
|
|
93
93
|
| `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
|
|
94
94
|
| `kilo/deepseek/deepseek-chat` | 164K | | | | | | $0.32 | $0.89 |
|
|
95
95
|
| `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.25 | $1 |
|
|
96
|
-
| `kilo/deepseek/deepseek-chat-v3.1` |
|
|
96
|
+
| `kilo/deepseek/deepseek-chat-v3.1` | 161K | | | | | | $0.27 | $1 |
|
|
97
97
|
| `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
|
|
98
98
|
| `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
|
|
99
99
|
| `kilo/deepseek/deepseek-r1-distill-llama-70b` | 8K | | | | | | $0.80 | $0.80 |
|
|
@@ -142,6 +142,7 @@ for await (const chunk of stream) {
|
|
|
142
142
|
| `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
|
|
143
143
|
| `kilo/inception/mercury-2.5-preview` | 260K | | | | | | $0.20 | $0.75 |
|
|
144
144
|
| `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
|
|
145
|
+
| `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.06 | $0.18 |
|
|
145
146
|
| `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
|
|
146
147
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
147
148
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
@@ -300,7 +301,7 @@ for await (const chunk of stream) {
|
|
|
300
301
|
| `kilo/qwen/qwen-2.5-coder-32b-instruct` | 33K | | | | | | $0.66 | $1 |
|
|
301
302
|
| `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
302
303
|
| `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
|
|
303
|
-
| `kilo/qwen/qwen2.5-vl-72b-instruct` |
|
|
304
|
+
| `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
|
|
304
305
|
| `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
|
|
305
306
|
| `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
|
|
306
307
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
@@ -367,7 +368,7 @@ for await (const chunk of stream) {
|
|
|
367
368
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
368
369
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
369
370
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
370
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
371
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
|
|
371
372
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
372
373
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
373
374
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 367 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
|
|
|
@@ -166,6 +166,7 @@ for await (const chunk of stream) {
|
|
|
166
166
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
167
167
|
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.13 | $0.27 |
|
|
168
168
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
169
|
+
| `llmgateway-providers/consensusprotocol/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
169
170
|
| `llmgateway-providers/deepinfra/deepseek-v3.2` | 160K | | | | | | $0.26 | $0.38 |
|
|
170
171
|
| `llmgateway-providers/deepinfra/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.18 |
|
|
171
172
|
| `llmgateway-providers/deepinfra/deepseek-v4-pro` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -225,8 +226,10 @@ for await (const chunk of stream) {
|
|
|
225
226
|
| `llmgateway-providers/groq/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.75 |
|
|
226
227
|
| `llmgateway-providers/groq/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
|
|
227
228
|
| `llmgateway-providers/inference.net/llama-3.2-11b-instruct` | 128K | | | | | | $0.07 | $0.33 |
|
|
229
|
+
| `llmgateway-providers/meta-contributor/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
228
230
|
| `llmgateway-providers/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
229
231
|
| `llmgateway-providers/meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
232
|
+
| `llmgateway-providers/meta/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
|
|
230
233
|
| `llmgateway-providers/minimax/minimax-m2` | 197K | | | | | | $0.20 | $1 |
|
|
231
234
|
| `llmgateway-providers/minimax/minimax-m2.1` | 197K | | | | | | $0.27 | $1 |
|
|
232
235
|
| `llmgateway-providers/minimax/minimax-m2.1-lightning` | 197K | | | | | | $0.12 | $0.48 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 184 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
|
|
|
@@ -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: "llmgateway/
|
|
22
|
+
model: "llmgateway/Qwen3.8-27B"
|
|
23
23
|
});
|
|
24
24
|
|
|
25
25
|
// Generate a response
|
|
@@ -172,6 +172,8 @@ for await (const chunk of stream) {
|
|
|
172
172
|
| `llmgateway/mistral-small-2506` | 128K | | | | | | $0.10 | $0.30 |
|
|
173
173
|
| `llmgateway/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
174
174
|
| `llmgateway/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
175
|
+
| `llmgateway/muse-spark-1.3` | 1.0M | | | | | | $1 | $4 |
|
|
176
|
+
| `llmgateway/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
175
177
|
| `llmgateway/nemotron-3-ultra-550b` | 1.0M | | | | | | $0.50 | $2 |
|
|
176
178
|
| `llmgateway/o1` | 200K | | | | | | $15 | $60 |
|
|
177
179
|
| `llmgateway/o3` | 200K | | | | | | $2 | $8 |
|
|
@@ -208,7 +210,7 @@ for await (const chunk of stream) {
|
|
|
208
210
|
| `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
209
211
|
| `llmgateway/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
210
212
|
| `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
211
|
-
| `llmgateway/
|
|
213
|
+
| `llmgateway/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
212
214
|
| `llmgateway/qwen3.8-flash` | 1.0M | | | | | | $0.15 | $0.47 |
|
|
213
215
|
| `llmgateway/qwen3.8-max` | 1.0M | | | | | | $2 | $5 |
|
|
214
216
|
| `llmgateway/qwen35-397b-a17b` | 262K | | | | | | $0.60 | $4 |
|
|
@@ -232,7 +234,7 @@ const agent = new Agent({
|
|
|
232
234
|
name: "custom-agent",
|
|
233
235
|
model: {
|
|
234
236
|
url: "https://api.llmgateway.io/v1",
|
|
235
|
-
id: "llmgateway/
|
|
237
|
+
id: "llmgateway/Qwen3.8-27B",
|
|
236
238
|
apiKey: process.env.LLMGATEWAY_API_KEY,
|
|
237
239
|
headers: {
|
|
238
240
|
"X-Custom-Header": "value"
|
|
@@ -251,7 +253,7 @@ const agent = new Agent({
|
|
|
251
253
|
const useAdvanced = requestContext.task === "complex";
|
|
252
254
|
return useAdvanced
|
|
253
255
|
? "llmgateway/sonar-reasoning-pro"
|
|
254
|
-
: "llmgateway/
|
|
256
|
+
: "llmgateway/Qwen3.8-27B";
|
|
255
257
|
}
|
|
256
258
|
});
|
|
257
259
|
```
|