@mastra/mcp-docs-server 1.2.19-alpha.0 → 1.2.19-alpha.13
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/deployment/mastra-server.md +19 -0
- package/.docs/docs/deployment/workers.md +2 -2
- package/.docs/docs/evals/built-in-scorers.md +1 -0
- package/.docs/docs/evals/multi-turn.md +84 -1
- package/.docs/docs/evals/overview.md +63 -1
- package/.docs/docs/harness/durable-agents.md +1 -1
- package/.docs/docs/mastra-platform/deploy.md +101 -0
- package/.docs/docs/mastra-platform/server.md +6 -11
- package/.docs/docs/mastra-platform/studio.md +8 -10
- package/.docs/docs/observability/integrations/exporters/mastra-storage.md +19 -14
- package/.docs/docs/sandbox/filesystem.md +8 -8
- package/.docs/docs/sandbox/overview.md +33 -66
- package/.docs/docs/server/middleware.md +4 -0
- package/.docs/docs/server/server-adapters.md +12 -8
- package/.docs/docs/storage.md +1 -0
- package/.docs/integrations/databases/mongodb.md +1 -1
- package/.docs/integrations/databases/postgresql.md +2 -0
- package/.docs/integrations/databases/valkey.md +99 -0
- package/.docs/integrations/deploy/render.md +47 -61
- package/.docs/integrations/sandboxes/e2b.md +2 -0
- package/.docs/integrations/tools/parallel.md +240 -0
- package/.docs/integrations.md +2 -0
- package/.docs/models/environment-variables.md +2 -0
- package/.docs/models/gateways/merge-gateway.md +2 -1
- package/.docs/models/gateways/netlify.md +9 -5
- package/.docs/models/gateways/openrouter.md +8 -9
- package/.docs/models/gateways/vercel.md +7 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/agentrouter.md +17 -34
- package/.docs/models/providers/aki-io.md +14 -13
- package/.docs/models/providers/chutes.md +2 -2
- package/.docs/models/providers/crof.md +3 -8
- package/.docs/models/providers/crossmodel.md +56 -55
- package/.docs/models/providers/deepseek.md +8 -7
- package/.docs/models/providers/digitalocean.md +8 -8
- package/.docs/models/providers/edenai.md +14 -14
- package/.docs/models/providers/google.md +3 -3
- package/.docs/models/providers/hyper.md +5 -5
- package/.docs/models/providers/inceptron.md +1 -1
- package/.docs/models/providers/kilo.md +24 -20
- package/.docs/models/providers/llmgateway-providers.md +11 -8
- package/.docs/models/providers/llmgateway.md +3 -5
- package/.docs/models/providers/nano-gpt.md +12 -6
- package/.docs/models/providers/nvidia.md +3 -1
- package/.docs/models/providers/ofox.md +114 -110
- package/.docs/models/providers/opencode-go.md +26 -23
- package/.docs/models/providers/opencode.md +1 -1
- package/.docs/models/providers/opper.md +112 -0
- package/.docs/models/providers/requesty.md +1 -1
- package/.docs/models/providers/scaleway.md +2 -1
- package/.docs/models/providers.md +2 -0
- package/.docs/reference/ai-sdk/handle-chat-stream.md +11 -0
- package/.docs/reference/ai-sdk/with-sse-heartbeat.md +47 -0
- package/.docs/reference/core/mastra-class.md +1 -1
- package/.docs/reference/evals/checks.md +6 -0
- package/.docs/reference/evals/multi-turn-judge.md +101 -0
- package/.docs/reference/index.md +4 -0
- package/.docs/reference/pubsub/valkey-streams.md +84 -0
- package/.docs/reference/rag/vector-databases.md +4 -4
- package/.docs/reference/server/express-adapter.md +6 -8
- package/.docs/reference/server/hono-adapter.md +19 -6
- package/.docs/reference/storage/turso.md +88 -0
- package/.docs/reference/streaming/ChunkType.md +29 -1
- package/.docs/reference/tools/mcp-client.md +41 -9
- package/.docs/reference/vectors/mongodb.md +11 -11
- package/.docs/reference/vectors/pg.md +2 -0
- package/.docs/reference/workspace/workspace-class.md +15 -3
- package/CHANGELOG.md +59 -0
- package/package.json +4 -4
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Kilo Gateway
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 365 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
8
8
|
|
|
@@ -40,11 +40,11 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
|
|
41
41
|
| `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
|
|
42
42
|
| `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
|
|
43
|
-
| `kilo/~deepseek/deepseek-v4-flash-latest` |
|
|
43
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.08 |
|
|
44
44
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.38 | $2 |
|
|
45
45
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
46
46
|
| `kilo/~moonshotai/kimi-latest` | 975K | | | | | | $3 | $13 |
|
|
47
|
-
| `kilo/~openai/gpt-latest` | 1.1M | | | | | | $
|
|
47
|
+
| `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
|
|
48
48
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
49
49
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
50
50
|
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -92,10 +92,9 @@ for await (const chunk of stream) {
|
|
|
92
92
|
| `kilo/cohere/command-r-plus-08-2024` | 128K | | | | | | $3 | $10 |
|
|
93
93
|
| `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
|
|
94
94
|
| `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
|
|
95
|
-
| `kilo/deepcogito/cogito-v2.1-671b` | 128K | | | | | | $1 | $1 |
|
|
96
95
|
| `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.40 | $1 |
|
|
97
96
|
| `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.27 | $1 |
|
|
98
|
-
| `kilo/deepseek/deepseek-chat-v3.1` |
|
|
97
|
+
| `kilo/deepseek/deepseek-chat-v3.1` | 161K | | | | | | $0.27 | $1 |
|
|
99
98
|
| `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
|
|
100
99
|
| `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
|
|
101
100
|
| `kilo/deepseek/deepseek-r1-distill-llama-70b` | 8K | | | | | | $0.80 | $0.80 |
|
|
@@ -103,7 +102,8 @@ for await (const chunk of stream) {
|
|
|
103
102
|
| `kilo/deepseek/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
|
|
104
103
|
| `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
|
|
105
104
|
| `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
106
|
-
| `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
105
|
+
| `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
|
|
106
|
+
| `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
107
107
|
| `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
108
108
|
| `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
109
109
|
| `kilo/dots-studio/dots-3-note-preview:free` | 512K | | | | | | — | — |
|
|
@@ -132,7 +132,7 @@ for await (const chunk of stream) {
|
|
|
132
132
|
| `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
133
133
|
| `kilo/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
134
134
|
| `kilo/google/gemma-3n-e4b-it` | 33K | | | | | | $0.06 | $0.12 |
|
|
135
|
-
| `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.
|
|
135
|
+
| `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.04 | $0.22 |
|
|
136
136
|
| `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.08 | $0.35 |
|
|
137
137
|
| `kilo/google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
|
|
138
138
|
| `kilo/google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
|
|
@@ -140,10 +140,7 @@ for await (const chunk of stream) {
|
|
|
140
140
|
| `kilo/ibm-granite/granite-4.0-h-micro` | 131K | | | | | | $0.02 | $0.11 |
|
|
141
141
|
| `kilo/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
|
|
142
142
|
| `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
|
|
143
|
-
| `kilo/inclusionai/ling-2.6-1t` | 262K | | | | | | $0.30 | $3 |
|
|
144
|
-
| `kilo/inclusionai/ling-2.6-flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
145
143
|
| `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
|
|
146
|
-
| `kilo/inclusionai/ring-2.6-1t` | 262K | | | | | | $0.30 | $3 |
|
|
147
144
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
148
145
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
149
146
|
| `kilo/kilo-auto/free` | 256K | | | | | | — | — |
|
|
@@ -152,8 +149,10 @@ for await (const chunk of stream) {
|
|
|
152
149
|
| `kilo/kwaipilot/kat-coder-air-v2.5` | 256K | | | | | | $0.15 | $0.60 |
|
|
153
150
|
| `kilo/kwaipilot/kat-coder-pro-v2` | 256K | | | | | | $0.30 | $1 |
|
|
154
151
|
| `kilo/kwaipilot/kat-coder-pro-v2.5` | 256K | | | | | | $0.74 | $3 |
|
|
155
|
-
| `kilo/liquid/lfm-2.5-2.6b:free` |
|
|
152
|
+
| `kilo/liquid/lfm-2.5-2.6b:free` | 66K | | | | | | — | — |
|
|
153
|
+
| `kilo/mancer/weaver` | 8K | | | | | | $0.50 | $0.75 |
|
|
156
154
|
| `kilo/meituan/longcat-2.0` | 1.0M | | | | | | $0.75 | $3 |
|
|
155
|
+
| `kilo/meituan/longcat-2.0-free` | 1.0M | | | | | | — | — |
|
|
157
156
|
| `kilo/meta-llama/llama-3.1-70b-instruct` | 131K | | | | | | $0.40 | $0.40 |
|
|
158
157
|
| `kilo/meta-llama/llama-3.1-8b-instruct` | 131K | | | | | | $0.02 | $0.04 |
|
|
159
158
|
| `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
|
|
@@ -165,6 +164,7 @@ for await (const chunk of stream) {
|
|
|
165
164
|
| `kilo/meta/muse-glimmer-30b` | 131K | | | | | | $0.30 | $1 |
|
|
166
165
|
| `kilo/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
|
|
167
166
|
| `kilo/meta/muse-spark-1.2` | 1.0M | | | | | | $1 | $4 |
|
|
167
|
+
| `kilo/meta/muse-spark-1.2-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
168
168
|
| `kilo/microsoft/phi-4` | 16K | | | | | | $0.07 | $0.14 |
|
|
169
169
|
| `kilo/microsoft/wizardlm-2-8x22b` | 66K | | | | | | $0.62 | $0.62 |
|
|
170
170
|
| `kilo/minimax/minimax-01` | 1.0M | | | | | | $0.20 | $1 |
|
|
@@ -172,10 +172,11 @@ for await (const chunk of stream) {
|
|
|
172
172
|
| `kilo/minimax/minimax-m2` | 205K | | | | | | $0.30 | $1 |
|
|
173
173
|
| `kilo/minimax/minimax-m2-her` | 66K | | | | | | $0.30 | $1 |
|
|
174
174
|
| `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
|
|
175
|
-
| `kilo/minimax/minimax-m2.5` |
|
|
176
|
-
| `kilo/minimax/minimax-m2.7` |
|
|
175
|
+
| `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
|
|
176
|
+
| `kilo/minimax/minimax-m2.7` | 197K | | | | | | $0.30 | $1 |
|
|
177
177
|
| `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
|
|
178
178
|
| `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
|
|
179
|
+
| `kilo/mistralai/devstral-2512` | 262K | | | | | | $0.44 | $2 |
|
|
179
180
|
| `kilo/mistralai/ministral-14b-2512` | 262K | | | | | | $0.20 | $0.20 |
|
|
180
181
|
| `kilo/mistralai/ministral-3b-2512` | 131K | | | | | | $0.10 | $0.10 |
|
|
181
182
|
| `kilo/mistralai/ministral-8b` | 128K | | | | | | $0.11 | $0.11 |
|
|
@@ -186,12 +187,12 @@ for await (const chunk of stream) {
|
|
|
186
187
|
| `kilo/mistralai/mistral-medium-3` | 131K | | | | | | $0.40 | $2 |
|
|
187
188
|
| `kilo/mistralai/mistral-medium-3-5` | 262K | | | | | | $2 | $8 |
|
|
188
189
|
| `kilo/mistralai/mistral-medium-3.1` | 131K | | | | | | $0.40 | $2 |
|
|
189
|
-
| `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.
|
|
190
|
+
| `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.17 | $0.17 |
|
|
190
191
|
| `kilo/mistralai/mistral-saba` | 33K | | | | | | $0.20 | $0.60 |
|
|
191
192
|
| `kilo/mistralai/mistral-small-24b-instruct-2501` | 33K | | | | | | $0.05 | $0.08 |
|
|
192
193
|
| `kilo/mistralai/mistral-small-2603` | 262K | | | | | | $0.15 | $0.60 |
|
|
193
194
|
| `kilo/mistralai/mistral-small-3.1-24b-instruct` | 128K | | | | | | $0.35 | $0.56 |
|
|
194
|
-
| `kilo/mistralai/mistral-small-3.2-24b-instruct` |
|
|
195
|
+
| `kilo/mistralai/mistral-small-3.2-24b-instruct` | 128K | | | | | | $0.11 | $0.33 |
|
|
195
196
|
| `kilo/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | $2 | $6 |
|
|
196
197
|
| `kilo/mistralai/voxtral-small-24b-2507` | 32K | | | | | | $0.10 | $0.30 |
|
|
197
198
|
| `kilo/moonshotai/kimi-k2` | 131K | | | | | | $0.57 | $2 |
|
|
@@ -258,9 +259,9 @@ for await (const chunk of stream) {
|
|
|
258
259
|
| `kilo/openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
|
|
259
260
|
| `kilo/openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
260
261
|
| `kilo/openai/gpt-5.6-luna-pro` | 1.1M | | | | | | $0.20 | $1 |
|
|
261
|
-
| `kilo/openai/gpt-5.6-sol` | 1.1M | | | | | | $
|
|
262
|
+
| `kilo/openai/gpt-5.6-sol` | 1.1M | | | | | | $4 | $20 |
|
|
262
263
|
| `kilo/openai/gpt-5.6-sol-discounted` | 1.1M | | | | | | $3 | $15 |
|
|
263
|
-
| `kilo/openai/gpt-5.6-sol-pro` | 1.1M | | | | | | $
|
|
264
|
+
| `kilo/openai/gpt-5.6-sol-pro` | 1.1M | | | | | | $4 | $20 |
|
|
264
265
|
| `kilo/openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
265
266
|
| `kilo/openai/gpt-5.6-terra-pro` | 1.1M | | | | | | $2 | $12 |
|
|
266
267
|
| `kilo/openai/gpt-audio` | 128K | | | | | | $3 | $10 |
|
|
@@ -302,7 +303,7 @@ for await (const chunk of stream) {
|
|
|
302
303
|
| `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
|
|
303
304
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
304
305
|
| `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
|
|
305
|
-
| `kilo/qwen/qwen3-30b-a3b` |
|
|
306
|
+
| `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
|
|
306
307
|
| `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.13 | $0.52 |
|
|
307
308
|
| `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
|
|
308
309
|
| `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
|
|
@@ -340,7 +341,7 @@ for await (const chunk of stream) {
|
|
|
340
341
|
| `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
341
342
|
| `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
342
343
|
| `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
|
|
343
|
-
| `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.
|
|
344
|
+
| `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.42 | $3 |
|
|
344
345
|
| `kilo/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
345
346
|
| `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
|
|
346
347
|
| `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
|
|
@@ -363,15 +364,18 @@ for await (const chunk of stream) {
|
|
|
363
364
|
| `kilo/tencent/hunyuan-a13b-instruct` | 131K | | | | | | $0.14 | $0.57 |
|
|
364
365
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
365
366
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
367
|
+
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
366
368
|
| `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
367
369
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
368
370
|
| `kilo/tencent/hy3:free` | 262K | | | | | | — | — |
|
|
369
371
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
370
372
|
| `kilo/thedrummer/rocinante-12b` | 66K | | | | | | $0.25 | $0.50 |
|
|
371
373
|
| `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
|
|
372
|
-
| `kilo/thedrummer/unslopnemo-12b` |
|
|
374
|
+
| `kilo/thedrummer/unslopnemo-12b` | 33K | | | | | | $0.40 | $0.40 |
|
|
373
375
|
| `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
|
|
374
376
|
| `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
|
|
377
|
+
| `kilo/thinkingmachines/inkling-small:free` | 262K | | | | | | — | — |
|
|
378
|
+
| `kilo/thinkingmachines/inkling:free` | 262K | | | | | | — | — |
|
|
375
379
|
| `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.45 | $0.65 |
|
|
376
380
|
| `kilo/upstage/solar-pro-3` | 131K | | | | | | $0.15 | $0.60 |
|
|
377
381
|
| `kilo/upstage/solar-pro4` | 524K | | | | | | $0.30 | $1 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# LLM Gateway
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 371 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
8
8
|
|
|
@@ -48,14 +48,14 @@ for await (const chunk of stream) {
|
|
|
48
48
|
| `llmgateway-providers/alibaba/qwen-plus` | 131K | | | | | | $0.40 | $1 |
|
|
49
49
|
| `llmgateway-providers/alibaba/qwen-plus-latest` | 1.0M | | | | | | $0.40 | $1 |
|
|
50
50
|
| `llmgateway-providers/alibaba/qwen3-coder-flash` | 1.0M | | | | | | $0.30 | $2 |
|
|
51
|
-
| `llmgateway-providers/alibaba/qwen3-coder-plus` | 1.0M | | | | | | $
|
|
52
|
-
| `llmgateway-providers/alibaba/qwen3-max` | 256K | | | | | | $
|
|
51
|
+
| `llmgateway-providers/alibaba/qwen3-coder-plus` | 1.0M | | | | | | $1 | $5 |
|
|
52
|
+
| `llmgateway-providers/alibaba/qwen3-max` | 256K | | | | | | $1 | $6 |
|
|
53
53
|
| `llmgateway-providers/alibaba/qwen3-vl-flash` | 262K | | | | | | $0.05 | $0.40 |
|
|
54
54
|
| `llmgateway-providers/alibaba/qwen3-vl-plus` | 262K | | | | | | $0.20 | $2 |
|
|
55
|
-
| `llmgateway-providers/alibaba/qwen3.6-35b-a3b` | 262K | | | | | | $0.
|
|
55
|
+
| `llmgateway-providers/alibaba/qwen3.6-35b-a3b` | 262K | | | | | | $0.38 | $2 |
|
|
56
56
|
| `llmgateway-providers/alibaba/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
|
|
57
57
|
| `llmgateway-providers/alibaba/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
|
|
58
|
-
| `llmgateway-providers/alibaba/qwen3.6-plus` |
|
|
58
|
+
| `llmgateway-providers/alibaba/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
59
59
|
| `llmgateway-providers/alibaba/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
60
60
|
| `llmgateway-providers/alibaba/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
61
61
|
| `llmgateway-providers/alibaba/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
@@ -162,6 +162,8 @@ for await (const chunk of stream) {
|
|
|
162
162
|
| `llmgateway-providers/deepinfra/hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
163
163
|
| `llmgateway-providers/deepinfra/kimi-k2.5` | 256K | | | | | | $0.45 | $2 |
|
|
164
164
|
| `llmgateway-providers/deepinfra/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
|
|
165
|
+
| `llmgateway-providers/deepinfra/mimo-v2.5` | 262K | | | | | | $0.40 | $2 |
|
|
166
|
+
| `llmgateway-providers/deepinfra/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
|
|
165
167
|
| `llmgateway-providers/deepinfra/nemotron-3-ultra-550b` | 262K | | | | | | $0.50 | $2 |
|
|
166
168
|
| `llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct` | 262K | | | | | | $0.20 | $0.88 |
|
|
167
169
|
| `llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct` | 262K | | | | | | $0.15 | $0.60 |
|
|
@@ -205,7 +207,6 @@ for await (const chunk of stream) {
|
|
|
205
207
|
| `llmgateway-providers/google-vertex/gemini-3.5-flash-lite` | 1.0M | | | | | | $0.30 | $3 |
|
|
206
208
|
| `llmgateway-providers/google-vertex/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
207
209
|
| `llmgateway-providers/google-vertex/gemini-3.7-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
208
|
-
| `llmgateway-providers/granite/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
209
210
|
| `llmgateway-providers/groq/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.75 |
|
|
210
211
|
| `llmgateway-providers/groq/gpt-oss-20b` | 131K | | | | | | $0.10 | $0.50 |
|
|
211
212
|
| `llmgateway-providers/iceberg/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
|
|
@@ -284,6 +285,8 @@ for await (const chunk of stream) {
|
|
|
284
285
|
| `llmgateway-providers/novita/llama-3.3-70b-instruct` | 131K | | | | | | $0.14 | $0.40 |
|
|
285
286
|
| `llmgateway-providers/novita/llama-4-maverick-17b-instruct` | 1.0M | | | | | | $0.27 | $0.85 |
|
|
286
287
|
| `llmgateway-providers/novita/llama-4-scout-17b-instruct` | 131K | | | | | | $0.18 | $0.59 |
|
|
288
|
+
| `llmgateway-providers/novita/mimo-v2.5` | 1.0M | | | | | | $0.17 | $0.34 |
|
|
289
|
+
| `llmgateway-providers/novita/mimo-v2.5-pro` | 1.0M | | | | | | $0.52 | $1 |
|
|
287
290
|
| `llmgateway-providers/novita/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
|
|
288
291
|
| `llmgateway-providers/novita/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
289
292
|
| `llmgateway-providers/novita/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
|
|
@@ -309,9 +312,7 @@ for await (const chunk of stream) {
|
|
|
309
312
|
| `llmgateway-providers/openai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
310
313
|
| `llmgateway-providers/openai/gpt-4o` | 128K | | | | | | $3 | $10 |
|
|
311
314
|
| `llmgateway-providers/openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
312
|
-
| `llmgateway-providers/openai/gpt-4o-mini-search-preview` | 128K | | | | | | $0.15 | $0.60 |
|
|
313
315
|
| `llmgateway-providers/openai/gpt-4o-mini-transcribe` | 16K | | | | | | $1 | $5 |
|
|
314
|
-
| `llmgateway-providers/openai/gpt-4o-search-preview` | 128K | | | | | | $3 | $10 |
|
|
315
316
|
| `llmgateway-providers/openai/gpt-4o-transcribe` | 16K | | | | | | $3 | $10 |
|
|
316
317
|
| `llmgateway-providers/openai/gpt-5` | 400K | | | | | | $1 | $10 |
|
|
317
318
|
| `llmgateway-providers/openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
@@ -339,6 +340,7 @@ for await (const chunk of stream) {
|
|
|
339
340
|
| `llmgateway-providers/perplexity/sonar-pro` | 200K | | | | | | $3 | $15 |
|
|
340
341
|
| `llmgateway-providers/perplexity/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
341
342
|
| `llmgateway-providers/quartz/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
343
|
+
| `llmgateway-providers/ranoai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
342
344
|
| `llmgateway-providers/runware/deepseek-v4-flash` | 1.0M | | | | | | $0.08 | $0.15 |
|
|
343
345
|
| `llmgateway-providers/runware/deepseek-v4-pro` | 1.0M | | | | | | $0.96 | $2 |
|
|
344
346
|
| `llmgateway-providers/runware/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.30 |
|
|
@@ -375,6 +377,7 @@ for await (const chunk of stream) {
|
|
|
375
377
|
| `llmgateway-providers/vertex-openai/glm-5` | 203K | | | | | | $1 | $3 |
|
|
376
378
|
| `llmgateway-providers/vertex-openai/grok-4-20-non-reasoning` | 2.0M | | | | | | $1 | $3 |
|
|
377
379
|
| `llmgateway-providers/vertex-openai/grok-4-20-reasoning` | 2.0M | | | | | | $1 | $3 |
|
|
380
|
+
| `llmgateway-providers/vertex-openai/grok-4-6` | 500K | | | | | | $2 | $6 |
|
|
378
381
|
| `llmgateway-providers/vertex-openai/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
379
382
|
| `llmgateway-providers/vertex-openai/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.22 | $0.88 |
|
|
380
383
|
| `llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.22 | $2 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# DevPass (LLM Gateway)
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 187 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
|
|
8
8
|
|
|
@@ -97,9 +97,7 @@ for await (const chunk of stream) {
|
|
|
97
97
|
| `llmgateway/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
98
98
|
| `llmgateway/gpt-4o` | 128K | | | | | | $3 | $10 |
|
|
99
99
|
| `llmgateway/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
100
|
-
| `llmgateway/gpt-4o-mini-search-preview` | 128K | | | | | | $0.15 | $0.60 |
|
|
101
100
|
| `llmgateway/gpt-4o-mini-transcribe` | 16K | | | | | | $1 | $5 |
|
|
102
|
-
| `llmgateway/gpt-4o-search-preview` | 128K | | | | | | $3 | $10 |
|
|
103
101
|
| `llmgateway/gpt-4o-transcribe` | 16K | | | | | | $3 | $10 |
|
|
104
102
|
| `llmgateway/gpt-5` | 400K | | | | | | $1 | $10 |
|
|
105
103
|
| `llmgateway/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
@@ -198,7 +196,7 @@ for await (const chunk of stream) {
|
|
|
198
196
|
| `llmgateway/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.38 | $2 |
|
|
199
197
|
| `llmgateway/qwen3-coder-flash` | 1.0M | | | | | | $0.30 | $2 |
|
|
200
198
|
| `llmgateway/qwen3-coder-next` | 262K | | | | | | $0.11 | $0.68 |
|
|
201
|
-
| `llmgateway/qwen3-coder-plus` | 1.0M | | | | | | $
|
|
199
|
+
| `llmgateway/qwen3-coder-plus` | 1.0M | | | | | | $1 | $5 |
|
|
202
200
|
| `llmgateway/qwen3-max` | 262K | | | | | | $0.84 | $3 |
|
|
203
201
|
| `llmgateway/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
|
|
204
202
|
| `llmgateway/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
|
|
@@ -211,7 +209,7 @@ for await (const chunk of stream) {
|
|
|
211
209
|
| `llmgateway/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
|
|
212
210
|
| `llmgateway/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
|
|
213
211
|
| `llmgateway/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
|
|
214
|
-
| `llmgateway/qwen3.6-plus` |
|
|
212
|
+
| `llmgateway/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
|
|
215
213
|
| `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
|
|
216
214
|
| `llmgateway/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
|
|
217
215
|
| `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# NanoGPT
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 601 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
|
|
8
8
|
|
|
@@ -46,7 +46,6 @@ for await (const chunk of stream) {
|
|
|
46
46
|
| `nano-gpt/alibaba/qwen3.6-flash` | 992K | | | | | | $0.19 | $1 |
|
|
47
47
|
| `nano-gpt/amazon/nova-2-lite-v1` | 1.0M | | | | | | $0.51 | $4 |
|
|
48
48
|
| `nano-gpt/amazon/nova-lite-v1` | 300K | | | | | | $0.06 | $0.24 |
|
|
49
|
-
| `nano-gpt/amazon/nova-micro-v1` | 128K | | | | | | $0.04 | $0.14 |
|
|
50
49
|
| `nano-gpt/amazon/nova-pro-v1` | 300K | | | | | | $0.80 | $3 |
|
|
51
50
|
| `nano-gpt/anthracite-org/magnum-v2-72b` | 16K | | | | | | $2 | $3 |
|
|
52
51
|
| `nano-gpt/anthracite-org/magnum-v4-72b` | 16K | | | | | | $2 | $3 |
|
|
@@ -152,6 +151,7 @@ for await (const chunk of stream) {
|
|
|
152
151
|
| `nano-gpt/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
153
152
|
| `nano-gpt/deepseek/deepseek-v4-flash-0731:thinking` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
154
153
|
| `nano-gpt/deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
154
|
+
| `nano-gpt/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
155
155
|
| `nano-gpt/deepseek/deepseek-v4-flash:thinking` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
156
156
|
| `nano-gpt/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $1 | $2 |
|
|
157
157
|
| `nano-gpt/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -210,6 +210,7 @@ for await (const chunk of stream) {
|
|
|
210
210
|
| `nano-gpt/Gemma-4-31B-Cognitive-Unshackled` | 262K | | | | | | $0.31 | $0.31 |
|
|
211
211
|
| `nano-gpt/Gemma-4-31B-DarkIdol` | 262K | | | | | | $0.31 | $0.31 |
|
|
212
212
|
| `nano-gpt/Gemma-4-31B-GarnetV2` | 262K | | | | | | $0.31 | $0.31 |
|
|
213
|
+
| `nano-gpt/Gemma-4-31B-MeroMero-v2` | 66K | | | | | | $0.08 | $0.33 |
|
|
213
214
|
| `nano-gpt/Gemma-4-31B-Queen` | 262K | | | | | | $0.31 | $0.31 |
|
|
214
215
|
| `nano-gpt/gemma-4-e2b-it` | 131K | | | | | | $0.02 | $0.10 |
|
|
215
216
|
| `nano-gpt/gemma-4-e4b-it` | 131K | | | | | | $0.04 | $0.20 |
|
|
@@ -239,12 +240,13 @@ for await (const chunk of stream) {
|
|
|
239
240
|
| `nano-gpt/google/gemini-3.5-flash-thinking` | 1.0M | | | | | | $2 | $9 |
|
|
240
241
|
| `nano-gpt/google/gemini-3.6-flash` | 1.0M | | | | | | $0.75 | $4 |
|
|
241
242
|
| `nano-gpt/google/gemini-3.7-flash` | 1.0M | | | | | | $0.38 | $2 |
|
|
242
|
-
| `nano-gpt/google/gemini-flash-latest` | 1.0M | | | | | | $0.
|
|
243
|
+
| `nano-gpt/google/gemini-flash-latest` | 1.0M | | | | | | $0.38 | $2 |
|
|
243
244
|
| `nano-gpt/google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.30 | $3 |
|
|
244
245
|
| `nano-gpt/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
245
|
-
| `nano-gpt/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.
|
|
246
|
+
| `nano-gpt/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.08 | $0.33 |
|
|
246
247
|
| `nano-gpt/google/gemma-4-26b-a4b-it:thinking` | 262K | | | | | | $0.13 | $0.40 |
|
|
247
|
-
| `nano-gpt/google/gemma-4-
|
|
248
|
+
| `nano-gpt/google/gemma-4-26b-a4b-uncensored` | 131K | | | | | | $0.08 | $0.33 |
|
|
249
|
+
| `nano-gpt/google/gemma-4-31b-it` | 262K | | | | | | $0.08 | $0.33 |
|
|
248
250
|
| `nano-gpt/google/gemma-4-31b-it:thinking` | 262K | | | | | | $0.10 | $0.35 |
|
|
249
251
|
| `nano-gpt/Gryphe/MythoMax-L2-13b` | 4K | | | | | | $0.10 | $0.10 |
|
|
250
252
|
| `nano-gpt/hermes-high` | 1.0M | | | | | | $5 | $25 |
|
|
@@ -424,6 +426,7 @@ for await (const chunk of stream) {
|
|
|
424
426
|
| `nano-gpt/openai/o4-mini-high` | 200K | | | | | | $1 | $4 |
|
|
425
427
|
| `nano-gpt/ornith-ai/ornith-1.5-35b-a3b` | 262K | | | | | | $0.10 | $0.40 |
|
|
426
428
|
| `nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking` | 262K | | | | | | $0.10 | $0.40 |
|
|
429
|
+
| `nano-gpt/ornith-ai/ornith-1.5-9b` | 131K | | | | | | $0.05 | $0.10 |
|
|
427
430
|
| `nano-gpt/pamanseau/OpenReasoning-Nemotron-32B` | 33K | | | | | | $0.10 | $0.40 |
|
|
428
431
|
| `nano-gpt/perceptron/perceptron-mk1` | 33K | | | | | | $0.15 | $2 |
|
|
429
432
|
| `nano-gpt/perplexity-academic-researcher` | 127K | | | | | | $2 | $8 |
|
|
@@ -462,7 +465,9 @@ for await (const chunk of stream) {
|
|
|
462
465
|
| `nano-gpt/qwen/qwen3.5-plus` | 984K | | | | | | $0.40 | $2 |
|
|
463
466
|
| `nano-gpt/qwen/qwen3.5-plus-thinking` | 984K | | | | | | $0.40 | $2 |
|
|
464
467
|
| `nano-gpt/qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.11 | $0.80 |
|
|
468
|
+
| `nano-gpt/qwen/qwen3.6-35b-a3b-uncensored` | 66K | | | | | | $0.15 | $0.50 |
|
|
465
469
|
| `nano-gpt/qwen/Qwen3.6-35B-A3B:thinking` | 262K | | | | | | $0.11 | $0.80 |
|
|
470
|
+
| `nano-gpt/qwen/qwen3.8-27b-uncensored` | 131K | | | | | | $0.18 | $0.50 |
|
|
466
471
|
| `nano-gpt/qwen25-vl-72b-instruct` | 32K | | | | | | $0.70 | $0.70 |
|
|
467
472
|
| `nano-gpt/qwen3-30b-a3b-instruct-2507` | 256K | | | | | | $0.20 | $0.50 |
|
|
468
473
|
| `nano-gpt/qwen3-coder-30b-a3b-instruct` | 128K | | | | | | $0.10 | $0.40 |
|
|
@@ -514,6 +519,7 @@ for await (const chunk of stream) {
|
|
|
514
519
|
| `nano-gpt/soob3123/amoral-gemma3-27B-v2` | 33K | | | | | | $0.30 | $0.30 |
|
|
515
520
|
| `nano-gpt/soob3123/GrayLine-Qwen3-8B` | 16K | | | | | | $0.30 | $0.30 |
|
|
516
521
|
| `nano-gpt/soob3123/Veiled-Calla-12B` | 33K | | | | | | $0.30 | $0.30 |
|
|
522
|
+
| `nano-gpt/stealth/ox-alpha` | 1.0M | | | | | | $0.05 | $0.05 |
|
|
517
523
|
| `nano-gpt/Steelskull/L3.3-Cu-Mai-R1-70b` | 16K | | | | | | $0.49 | $0.49 |
|
|
518
524
|
| `nano-gpt/Steelskull/L3.3-Electra-R1-70b` | 16K | | | | | | $0.70 | $0.70 |
|
|
519
525
|
| `nano-gpt/Steelskull/L3.3-MS-Evayale-70B` | 16K | | | | | | $0.49 | $0.49 |
|
|
@@ -577,7 +583,7 @@ for await (const chunk of stream) {
|
|
|
577
583
|
| `nano-gpt/upstage/solar-pro-3` | 128K | | | | | | $0.15 | $0.60 |
|
|
578
584
|
| `nano-gpt/upstage/solar-pro4` | 524K | | | | | | $0.03 | $0.12 |
|
|
579
585
|
| `nano-gpt/upstage/solar-pro4:thinking` | 524K | | | | | | $0.03 | $0.12 |
|
|
580
|
-
| `nano-gpt/venice-uncensored` | 128K | | | | | | $0.40 | $
|
|
586
|
+
| `nano-gpt/venice-uncensored` | 128K | | | | | | $0.40 | $2 |
|
|
581
587
|
| `nano-gpt/VongolaChouko/Starcannon-Unleashed-12B-v1.0` | 16K | | | | | | $0.49 | $0.49 |
|
|
582
588
|
| `nano-gpt/x-ai/grok-4.20` | 2.0M | | | | | | $2 | $6 |
|
|
583
589
|
| `nano-gpt/x-ai/grok-4.20-multi-agent` | 2.0M | | | | | | $2 | $6 |
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Nvidia
|
|
4
4
|
|
|
5
|
-
Access
|
|
5
|
+
Access 102 Nvidia models through Mastra's model router. Authentication is handled automatically using the `NVIDIA_API_KEY` environment variable.
|
|
6
6
|
|
|
7
7
|
Learn more in the [Nvidia documentation](https://docs.api.nvidia.com/nim/).
|
|
8
8
|
|
|
@@ -44,6 +44,7 @@ for await (const chunk of stream) {
|
|
|
44
44
|
| `nvidia/black-forest-labs/flux.1-dev` | 4K | | | | | | — | — |
|
|
45
45
|
| `nvidia/bytedance/seed-oss-36b-instruct` | 262K | | | | | | — | — |
|
|
46
46
|
| `nvidia/deepseek-ai/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
47
|
+
| `nvidia/deepseek-ai/deepseek-v4-flash-0731` | 1.0M | | | | | | — | — |
|
|
47
48
|
| `nvidia/deepseek-ai/deepseek-v4-pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
48
49
|
| `nvidia/google/gemma-2-2b-it` | 128K | | | | | | — | — |
|
|
49
50
|
| `nvidia/google/gemma-3-12b-it` | 131K | | | | | | — | — |
|
|
@@ -78,6 +79,7 @@ for await (const chunk of stream) {
|
|
|
78
79
|
| `nvidia/mistralai/mistral-small-4-119b-2603` | 128K | | | | | | — | — |
|
|
79
80
|
| `nvidia/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | — | — |
|
|
80
81
|
| `nvidia/mistralai/mixtral-8x7b-instruct` | 33K | | | | | | — | — |
|
|
82
|
+
| `nvidia/moonshotai/kimi-k3` | 1.0M | | | | | | — | — |
|
|
81
83
|
| `nvidia/nvidia/active-speaker-detection` | — | | | | | | — | — |
|
|
82
84
|
| `nvidia/nvidia/bevformer` | 128K | | | | | | — | — |
|
|
83
85
|
| `nvidia/nvidia/cosmos-predict1-5b` | — | | | | | | — | — |
|