@mastra/mcp-docs-server 1.1.35-alpha.2 → 1.1.35-alpha.26
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/course/03-agent-memory/18-advanced-configuration-semantic-recall.md +48 -4
- package/.docs/docs/agents/background-tasks.md +62 -2
- package/.docs/docs/agents/processors.md +35 -3
- package/.docs/docs/agents/response-caching.md +148 -0
- package/.docs/docs/agents/signals.md +151 -0
- package/.docs/docs/agents/using-tools.md +8 -0
- package/.docs/docs/browser/agent-browser.md +15 -0
- package/.docs/docs/browser/stagehand.md +25 -1
- package/.docs/docs/editor/tools.md +1 -1
- package/.docs/docs/index.md +2 -2
- package/.docs/docs/mastra-platform/configuration.md +1 -1
- package/.docs/docs/mastra-platform/overview.md +1 -1
- package/.docs/docs/memory/observational-memory.md +63 -14
- package/.docs/docs/memory/overview.md +2 -1
- package/.docs/docs/memory/semantic-recall.md +68 -6
- package/.docs/docs/observability/logging.md +2 -2
- package/.docs/docs/observability/metrics/overview.md +4 -4
- package/.docs/docs/observability/overview.md +6 -6
- package/.docs/docs/observability/tracing/bridges/otel.md +25 -0
- package/.docs/docs/observability/tracing/exporters/arize.md +5 -5
- package/.docs/docs/observability/tracing/exporters/braintrust.md +37 -0
- package/.docs/docs/observability/tracing/exporters/langfuse.md +21 -0
- package/.docs/docs/observability/tracing/exporters/{cloud.md → mastra-platform.md} +28 -26
- package/.docs/docs/observability/tracing/exporters/{default.md → mastra-storage.md} +56 -19
- package/.docs/docs/observability/tracing/exporters/otel.md +79 -2
- package/.docs/docs/observability/tracing/overview.md +30 -29
- package/.docs/docs/observability/tracing/processors/sensitive-data-filter.md +6 -6
- package/.docs/docs/server/mastra-server.md +30 -19
- package/.docs/docs/studio/observability.md +4 -4
- package/.docs/docs/studio/overview.md +4 -0
- package/.docs/docs/voice/overview.md +84 -0
- package/.docs/docs/workflows/suspend-and-resume.md +28 -1
- package/.docs/guides/deployment/inngest.md +29 -8
- package/.docs/guides/guide/web-search.md +7 -7
- package/.docs/guides/migrations/mastra-cloud.md +6 -6
- package/.docs/guides/migrations/upgrade-to-v1/tracing.md +19 -17
- package/.docs/models/gateways/azure-openai.md +94 -23
- package/.docs/models/gateways/netlify.md +3 -1
- package/.docs/models/gateways/openrouter.md +5 -1
- package/.docs/models/gateways/vercel.md +2 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/chutes.md +23 -54
- package/.docs/models/providers/databricks.md +96 -0
- package/.docs/models/providers/deepinfra.md +2 -1
- package/.docs/models/providers/deepseek.md +3 -1
- package/.docs/models/providers/digitalocean.md +10 -2
- package/.docs/models/providers/firepass.md +71 -0
- package/.docs/models/providers/google.md +3 -2
- package/.docs/models/providers/kilo.md +5 -3
- package/.docs/models/providers/kiro.md +110 -0
- package/.docs/models/providers/llmgateway.md +8 -2
- package/.docs/models/providers/nebius.md +37 -55
- package/.docs/models/providers/novita-ai.md +5 -5
- package/.docs/models/providers/nvidia.md +59 -49
- package/.docs/models/providers/ollama-cloud.md +1 -1
- package/.docs/models/providers/openai.md +2 -0
- package/.docs/models/providers/opencode-go.md +2 -4
- package/.docs/models/providers/opencode.md +44 -43
- package/.docs/models/providers/poe.md +4 -1
- package/.docs/models/providers/qiniu-ai.md +2 -2
- package/.docs/models/providers/sarvam.md +72 -0
- package/.docs/models/providers/wafer.ai.md +2 -1
- package/.docs/models/providers/xiaomi-token-plan-ams.md +6 -5
- package/.docs/models/providers/xiaomi-token-plan-cn.md +6 -5
- package/.docs/models/providers/xiaomi-token-plan-sgp.md +6 -5
- package/.docs/models/providers/xiaomi.md +2 -2
- package/.docs/models/providers/zenmux.md +1 -1
- package/.docs/models/providers.md +3 -0
- package/.docs/reference/agents/agent.md +85 -0
- package/.docs/reference/browser/agent-browser.md +37 -11
- package/.docs/reference/browser/stagehand-browser.md +35 -9
- package/.docs/reference/cli/mastra.md +464 -0
- package/.docs/reference/client-js/agents.md +115 -1
- package/.docs/reference/client-js/responses.md +4 -0
- package/.docs/reference/configuration.md +6 -6
- package/.docs/reference/editor/tool-provider.md +3 -3
- package/.docs/reference/harness/harness-class.md +23 -8
- package/.docs/reference/index.md +6 -0
- package/.docs/reference/memory/observational-memory.md +11 -1
- package/.docs/reference/observability/metrics/automatic-metrics.md +2 -4
- package/.docs/reference/observability/tracing/bridges/datadog.md +2 -2
- package/.docs/reference/observability/tracing/bridges/otel.md +26 -4
- package/.docs/reference/observability/tracing/configuration.md +6 -3
- package/.docs/reference/observability/tracing/exporters/arize.md +1 -1
- package/.docs/reference/observability/tracing/exporters/braintrust.md +2 -0
- package/.docs/reference/observability/tracing/exporters/cloud-exporter.md +3 -1
- package/.docs/reference/observability/tracing/exporters/console-exporter.md +2 -2
- package/.docs/reference/observability/tracing/exporters/default-exporter.md +7 -1
- package/.docs/reference/observability/tracing/exporters/mastra-platform-exporter.md +263 -0
- package/.docs/reference/observability/tracing/exporters/mastra-storage-exporter.md +194 -0
- package/.docs/reference/observability/tracing/exporters/otel.md +12 -8
- package/.docs/reference/observability/tracing/instances.md +2 -2
- package/.docs/reference/observability/tracing/interfaces.md +37 -2
- package/.docs/reference/observability/tracing/processors/sensitive-data-filter.md +22 -0
- package/.docs/reference/observability/tracing/span-filtering.md +2 -2
- package/.docs/reference/processors/prefill-error-handler.md +3 -3
- package/.docs/reference/processors/processor-interface.md +74 -12
- package/.docs/reference/processors/provider-history-compat.md +132 -0
- package/.docs/reference/processors/response-cache.md +114 -0
- package/.docs/reference/processors/tool-call-filter.md +28 -0
- package/.docs/reference/storage/clickhouse.md +8 -8
- package/.docs/reference/storage/cloudflare-d1.md +1 -1
- package/.docs/reference/storage/cloudflare.md +1 -1
- package/.docs/reference/storage/composite.md +1 -1
- package/.docs/reference/storage/convex.md +1 -1
- package/.docs/reference/storage/dsql.md +428 -0
- package/.docs/reference/storage/duckdb.md +3 -3
- package/.docs/reference/storage/dynamodb.md +1 -1
- package/.docs/reference/storage/lance.md +1 -1
- package/.docs/reference/storage/libsql.md +1 -1
- package/.docs/reference/storage/postgresql.md +1 -1
- package/.docs/reference/storage/upstash.md +1 -1
- package/.docs/reference/streaming/ChunkType.md +44 -0
- package/.docs/reference/streaming/agents/stream.md +18 -2
- package/.docs/reference/tools/brightdata.md +167 -0
- package/.docs/reference/tools/create-tool.md +46 -0
- package/.docs/reference/tools/mcp-client.md +47 -0
- package/.docs/reference/voice/inworld.md +133 -0
- package/.docs/reference/workflows/workflow-state-reader.md +113 -0
- package/CHANGELOG.md +92 -0
- package/package.json +4 -4
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OpenRouter
|
|
2
2
|
|
|
3
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
3
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 189 models through Mastra's model router.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
6
6
|
|
|
@@ -172,6 +172,8 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
172
172
|
| `poolside/laguna-xs.2:free` |
|
|
173
173
|
| `prime-intellect/intellect-3` |
|
|
174
174
|
| `qwen/qwen-2.5-coder-32b-instruct` |
|
|
175
|
+
| `qwen/qwen-3.6-27b` |
|
|
176
|
+
| `qwen/qwen-plus` |
|
|
175
177
|
| `qwen/qwen2.5-vl-72b-instruct` |
|
|
176
178
|
| `qwen/qwen3-235b-a22b-07-25` |
|
|
177
179
|
| `qwen/qwen3-235b-a22b-thinking-2507` |
|
|
@@ -180,6 +182,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
180
182
|
| `qwen/qwen3-coder` |
|
|
181
183
|
| `qwen/qwen3-coder-30b-a3b-instruct` |
|
|
182
184
|
| `qwen/qwen3-coder-flash` |
|
|
185
|
+
| `qwen/qwen3-coder-plus` |
|
|
183
186
|
| `qwen/qwen3-coder:exacto` |
|
|
184
187
|
| `qwen/qwen3-max` |
|
|
185
188
|
| `qwen/qwen3-next-80b-a3b-instruct` |
|
|
@@ -192,6 +195,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
192
195
|
| `sourceful/riverflow-v2-max-preview` |
|
|
193
196
|
| `sourceful/riverflow-v2-standard-preview` |
|
|
194
197
|
| `stepfun/step-3.5-flash` |
|
|
198
|
+
| `tencent/hy3-preview` |
|
|
195
199
|
| `x-ai/grok-3` |
|
|
196
200
|
| `x-ai/grok-3-beta` |
|
|
197
201
|
| `x-ai/grok-3-mini` |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Vercel
|
|
2
2
|
|
|
3
|
-
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
3
|
+
Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 247 models through Mastra's model router.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
|
|
6
6
|
|
|
@@ -113,6 +113,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
113
113
|
| `google/gemini-3-pro-image` |
|
|
114
114
|
| `google/gemini-3-pro-preview` |
|
|
115
115
|
| `google/gemini-3.1-flash-image-preview` |
|
|
116
|
+
| `google/gemini-3.1-flash-lite` |
|
|
116
117
|
| `google/gemini-3.1-flash-lite-preview` |
|
|
117
118
|
| `google/gemini-3.1-pro-preview` |
|
|
118
119
|
| `google/gemini-embedding-001` |
|
package/.docs/models/index.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Model Providers
|
|
2
2
|
|
|
3
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
3
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3895 models from 110 providers through a single API.
|
|
4
4
|
|
|
5
5
|
## Features
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Chutes
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 39 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
|
|
|
@@ -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: "chutes/MiniMaxAI/MiniMax-M2.
|
|
18
|
+
model: "chutes/MiniMaxAI/MiniMax-M2.5-TEE"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -34,76 +34,45 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `chutes/
|
|
38
|
-
| `chutes/chutesai/Mistral-Small-3.2-24B-Instruct-2506` | 131K | | | | | | $0.06 | $0.18 |
|
|
39
|
-
| `chutes/deepseek-ai/DeepSeek-R1-0528-TEE` | 164K | | | | | | $0.40 | $2 |
|
|
37
|
+
| `chutes/deepseek-ai/DeepSeek-R1-0528-TEE` | 164K | | | | | | $0.45 | $2 |
|
|
40
38
|
| `chutes/deepseek-ai/DeepSeek-R1-Distill-Llama-70B` | 131K | | | | | | $0.03 | $0.11 |
|
|
41
|
-
| `chutes/deepseek-ai/DeepSeek-
|
|
42
|
-
| `chutes/deepseek-ai/DeepSeek-V3`
|
|
43
|
-
| `chutes/deepseek-ai/DeepSeek-V3-0324-TEE` | 164K | | | | | | $0.19 | $0.87 |
|
|
44
|
-
| `chutes/deepseek-ai/DeepSeek-V3.1-TEE` | 164K | | | | | | $0.20 | $0.80 |
|
|
45
|
-
| `chutes/deepseek-ai/DeepSeek-V3.1-Terminus-TEE` | 164K | | | | | | $0.23 | $0.90 |
|
|
46
|
-
| `chutes/deepseek-ai/DeepSeek-V3.2-Speciale-TEE` | 164K | | | | | | $0.27 | $0.41 |
|
|
39
|
+
| `chutes/deepseek-ai/DeepSeek-V3-0324-TEE` | 164K | | | | | | $0.25 | $1 |
|
|
40
|
+
| `chutes/deepseek-ai/DeepSeek-V3.1-TEE` | 164K | | | | | | $0.27 | $1 |
|
|
47
41
|
| `chutes/deepseek-ai/DeepSeek-V3.2-TEE` | 131K | | | | | | $0.28 | $0.42 |
|
|
48
|
-
| `chutes/
|
|
49
|
-
| `chutes/MiniMaxAI/MiniMax-M2.5-TEE` | 197K | | | | | | $0.
|
|
50
|
-
| `chutes/
|
|
51
|
-
| `chutes/
|
|
52
|
-
| `chutes/moonshotai/Kimi-K2-Instruct-0905` | 262K | | | | | | $0.39 | $2 |
|
|
53
|
-
| `chutes/moonshotai/Kimi-K2-Thinking-TEE` | 262K | | | | | | $0.40 | $2 |
|
|
54
|
-
| `chutes/moonshotai/Kimi-K2.5-TEE` | 262K | | | | | | $0.60 | $3 |
|
|
55
|
-
| `chutes/moonshotai/Kimi-K2.6-TEE` | 262K | | | | | | $0.44 | $2 |
|
|
42
|
+
| `chutes/google/gemma-4-31B-turbo-TEE` | 131K | | | | | | $0.13 | $0.38 |
|
|
43
|
+
| `chutes/MiniMaxAI/MiniMax-M2.5-TEE` | 197K | | | | | | $0.15 | $1 |
|
|
44
|
+
| `chutes/moonshotai/Kimi-K2.5-TEE` | 262K | | | | | | $0.44 | $2 |
|
|
45
|
+
| `chutes/moonshotai/Kimi-K2.6-TEE` | 262K | | | | | | $0.95 | $4 |
|
|
56
46
|
| `chutes/NousResearch/DeepHermes-3-Mistral-24B-Preview` | 33K | | | | | | $0.02 | $0.10 |
|
|
57
47
|
| `chutes/NousResearch/Hermes-4-14B` | 41K | | | | | | $0.01 | $0.05 |
|
|
58
|
-
| `chutes/
|
|
59
|
-
| `chutes/
|
|
60
|
-
| `chutes/NousResearch/Hermes-4.3-36B` | 33K | | | | | | $0.10 | $0.39 |
|
|
61
|
-
| `chutes/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16` | 262K | | | | | | $0.06 | $0.24 |
|
|
62
|
-
| `chutes/openai/gpt-oss-120b-TEE` | 131K | | | | | | $0.04 | $0.18 |
|
|
63
|
-
| `chutes/openai/gpt-oss-20b` | 131K | | | | | | $0.02 | $0.10 |
|
|
64
|
-
| `chutes/OpenGVLab/InternVL3-78B-TEE` | 33K | | | | | | $0.10 | $0.39 |
|
|
65
|
-
| `chutes/Qwen/Qwen2.5-72B-Instruct` | 33K | | | | | | $0.13 | $0.52 |
|
|
48
|
+
| `chutes/openai/gpt-oss-120b-TEE` | 131K | | | | | | $0.09 | $0.36 |
|
|
49
|
+
| `chutes/Qwen/Qwen2.5-72B-Instruct` | 33K | | | | | | $0.30 | $1 |
|
|
66
50
|
| `chutes/Qwen/Qwen2.5-Coder-32B-Instruct` | 33K | | | | | | $0.03 | $0.11 |
|
|
67
51
|
| `chutes/Qwen/Qwen2.5-VL-32B-Instruct` | 16K | | | | | | $0.05 | $0.22 |
|
|
68
|
-
| `chutes/Qwen/
|
|
69
|
-
| `chutes/Qwen/Qwen3-14B` | 41K | | | | | | $0.05 | $0.22 |
|
|
70
|
-
| `chutes/Qwen/Qwen3-235B-A22B` | 41K | | | | | | $0.30 | $1 |
|
|
71
|
-
| `chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE` | 262K | | | | | | $0.08 | $0.55 |
|
|
52
|
+
| `chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE` | 262K | | | | | | $0.10 | $0.60 |
|
|
72
53
|
| `chutes/Qwen/Qwen3-235B-A22B-Thinking-2507` | 262K | | | | | | $0.11 | $0.60 |
|
|
73
54
|
| `chutes/Qwen/Qwen3-30B-A3B` | 41K | | | | | | $0.06 | $0.22 |
|
|
74
|
-
| `chutes/Qwen/Qwen3-
|
|
75
|
-
| `chutes/Qwen/Qwen3-
|
|
76
|
-
| `chutes/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE` | 262K | | | | | | $0.22 | $0.95 |
|
|
77
|
-
| `chutes/Qwen/Qwen3-Coder-Next` | 262K | | | | | | $0.07 | $0.30 |
|
|
55
|
+
| `chutes/Qwen/Qwen3-32B-TEE` | 41K | | | | | | $0.08 | $0.24 |
|
|
56
|
+
| `chutes/Qwen/Qwen3-Coder-Next-TEE` | 262K | | | | | | $0.12 | $0.75 |
|
|
78
57
|
| `chutes/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | | | | | | $0.10 | $0.80 |
|
|
79
|
-
| `chutes/Qwen/Qwen3-VL-235B-A22B-Instruct` | 262K | | | | | | $0.30 | $1 |
|
|
80
58
|
| `chutes/Qwen/Qwen3.5-397B-A17B-TEE` | 262K | | | | | | $0.39 | $2 |
|
|
59
|
+
| `chutes/Qwen/Qwen3.6-27B-TEE` | 262K | | | | | | $0.20 | $2 |
|
|
81
60
|
| `chutes/Qwen/Qwen3Guard-Gen-0.6B` | 33K | | | | | | $0.01 | $0.01 |
|
|
82
61
|
| `chutes/rednote-hilab/dots.ocr` | 131K | | | | | | $0.01 | $0.01 |
|
|
83
|
-
| `chutes/tngtech/DeepSeek-
|
|
84
|
-
| `chutes/tngtech/DeepSeek-TNG-R1T2-Chimera` | 164K | | | | | | $0.25 | $0.85 |
|
|
85
|
-
| `chutes/tngtech/TNG-R1T-Chimera-TEE` | 164K | | | | | | $0.25 | $0.85 |
|
|
86
|
-
| `chutes/tngtech/TNG-R1T-Chimera-Turbo` | 164K | | | | | | $0.22 | $0.60 |
|
|
62
|
+
| `chutes/tngtech/DeepSeek-TNG-R1T2-Chimera-TEE` | 164K | | | | | | $0.30 | $1 |
|
|
87
63
|
| `chutes/unsloth/gemma-3-12b-it` | 131K | | | | | | $0.03 | $0.10 |
|
|
88
|
-
| `chutes/unsloth/gemma-3-27b-it` | 128K | | | | | | $0.
|
|
64
|
+
| `chutes/unsloth/gemma-3-27b-it` | 128K | | | | | | $0.03 | $0.11 |
|
|
89
65
|
| `chutes/unsloth/gemma-3-4b-it` | 96K | | | | | | $0.01 | $0.03 |
|
|
90
|
-
| `chutes/unsloth/Llama-3.2-1B-Instruct` |
|
|
66
|
+
| `chutes/unsloth/Llama-3.2-1B-Instruct` | 16K | | | | | | $0.01 | $0.01 |
|
|
91
67
|
| `chutes/unsloth/Llama-3.2-3B-Instruct` | 16K | | | | | | $0.01 | $0.01 |
|
|
92
68
|
| `chutes/unsloth/Mistral-Nemo-Instruct-2407` | 131K | | | | | | $0.02 | $0.04 |
|
|
93
|
-
| `chutes/
|
|
94
|
-
| `chutes/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.09 | $0.29 |
|
|
95
|
-
| `chutes/zai-org/GLM-4.5-Air` | 131K | | | | | | $0.05 | $0.22 |
|
|
96
|
-
| `chutes/zai-org/GLM-4.5-FP8` | 131K | | | | | | $0.30 | $1 |
|
|
97
|
-
| `chutes/zai-org/GLM-4.5-TEE` | 131K | | | | | | $0.35 | $2 |
|
|
98
|
-
| `chutes/zai-org/GLM-4.6-FP8` | 203K | | | | | | $0.30 | $1 |
|
|
99
|
-
| `chutes/zai-org/GLM-4.6-TEE` | 203K | | | | | | $0.40 | $2 |
|
|
69
|
+
| `chutes/XiaomiMiMo/MiMo-V2-Flash-TEE` | 262K | | | | | | $0.09 | $0.29 |
|
|
100
70
|
| `chutes/zai-org/GLM-4.6V` | 131K | | | | | | $0.30 | $0.90 |
|
|
101
|
-
| `chutes/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.35 |
|
|
102
71
|
| `chutes/zai-org/GLM-4.7-FP8` | 203K | | | | | | $0.30 | $1 |
|
|
103
|
-
| `chutes/zai-org/GLM-4.7-TEE` | 203K | | | | | | $0.
|
|
72
|
+
| `chutes/zai-org/GLM-4.7-TEE` | 203K | | | | | | $0.39 | $2 |
|
|
104
73
|
| `chutes/zai-org/GLM-5-TEE` | 203K | | | | | | $0.95 | $3 |
|
|
105
74
|
| `chutes/zai-org/GLM-5-Turbo` | 203K | | | | | | $0.49 | $2 |
|
|
106
|
-
| `chutes/zai-org/GLM-5.1-TEE` | 203K | | | | | | $
|
|
75
|
+
| `chutes/zai-org/GLM-5.1-TEE` | 203K | | | | | | $1 | $4 |
|
|
107
76
|
|
|
108
77
|
## Advanced configuration
|
|
109
78
|
|
|
@@ -115,7 +84,7 @@ const agent = new Agent({
|
|
|
115
84
|
name: "custom-agent",
|
|
116
85
|
model: {
|
|
117
86
|
url: "https://llm.chutes.ai/v1",
|
|
118
|
-
id: "chutes/MiniMaxAI/MiniMax-M2.
|
|
87
|
+
id: "chutes/MiniMaxAI/MiniMax-M2.5-TEE",
|
|
119
88
|
apiKey: process.env.CHUTES_API_KEY,
|
|
120
89
|
headers: {
|
|
121
90
|
"X-Custom-Header": "value"
|
|
@@ -134,7 +103,7 @@ const agent = new Agent({
|
|
|
134
103
|
const useAdvanced = requestContext.task === "complex";
|
|
135
104
|
return useAdvanced
|
|
136
105
|
? "chutes/zai-org/GLM-5.1-TEE"
|
|
137
|
-
: "chutes/MiniMaxAI/MiniMax-M2.
|
|
106
|
+
: "chutes/MiniMaxAI/MiniMax-M2.5-TEE";
|
|
138
107
|
}
|
|
139
108
|
});
|
|
140
109
|
```
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
# Databricks
|
|
2
|
+
|
|
3
|
+
Access 25 Databricks models through Mastra's model router. Authentication is handled automatically using the `DATABRICKS_TOKEN` environment variable. Configure `DATABRICKS_HOST` as well.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
DATABRICKS_HOST=your-value
|
|
9
|
+
DATABRICKS_TOKEN=your-api-token
|
|
10
|
+
```
|
|
11
|
+
|
|
12
|
+
```typescript
|
|
13
|
+
import { Agent } from "@mastra/core/agent";
|
|
14
|
+
|
|
15
|
+
const agent = new Agent({
|
|
16
|
+
id: "my-agent",
|
|
17
|
+
name: "My Agent",
|
|
18
|
+
instructions: "You are a helpful assistant",
|
|
19
|
+
model: "databricks/databricks-claude-haiku-4-5"
|
|
20
|
+
});
|
|
21
|
+
|
|
22
|
+
// Generate a response
|
|
23
|
+
const response = await agent.generate("Hello!");
|
|
24
|
+
|
|
25
|
+
// Stream a response
|
|
26
|
+
const stream = await agent.stream("Tell me a story");
|
|
27
|
+
for await (const chunk of stream) {
|
|
28
|
+
console.log(chunk);
|
|
29
|
+
}
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/) for details.
|
|
33
|
+
|
|
34
|
+
## Models
|
|
35
|
+
|
|
36
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
37
|
+
| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
38
|
+
| `databricks/databricks-claude-haiku-4-5` | 200K | | | | | | $1 | $5 |
|
|
39
|
+
| `databricks/databricks-claude-opus-4-1` | 200K | | | | | | $15 | $75 |
|
|
40
|
+
| `databricks/databricks-claude-opus-4-5` | 200K | | | | | | $5 | $25 |
|
|
41
|
+
| `databricks/databricks-claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
|
|
42
|
+
| `databricks/databricks-claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
|
|
43
|
+
| `databricks/databricks-claude-sonnet-4` | 200K | | | | | | $3 | $15 |
|
|
44
|
+
| `databricks/databricks-claude-sonnet-4-5` | 200K | | | | | | $3 | $15 |
|
|
45
|
+
| `databricks/databricks-claude-sonnet-4-6` | 1.0M | | | | | | $3 | $15 |
|
|
46
|
+
| `databricks/databricks-gemini-2-5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
47
|
+
| `databricks/databricks-gemini-2-5-pro` | 1.0M | | | | | | $1 | $10 |
|
|
48
|
+
| `databricks/databricks-gemini-3-1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
|
|
49
|
+
| `databricks/databricks-gemini-3-1-pro` | 1.0M | | | | | | $2 | $12 |
|
|
50
|
+
| `databricks/databricks-gemini-3-flash` | 1.0M | | | | | | $0.50 | $3 |
|
|
51
|
+
| `databricks/databricks-gemini-3-pro` | 1.0M | | | | | | $2 | $12 |
|
|
52
|
+
| `databricks/databricks-gpt-5` | 400K | | | | | | $1 | $10 |
|
|
53
|
+
| `databricks/databricks-gpt-5-1` | 400K | | | | | | $1 | $10 |
|
|
54
|
+
| `databricks/databricks-gpt-5-2` | 400K | | | | | | $2 | $14 |
|
|
55
|
+
| `databricks/databricks-gpt-5-4` | 1.1M | | | | | | $3 | $15 |
|
|
56
|
+
| `databricks/databricks-gpt-5-4-mini` | 400K | | | | | | $0.75 | $5 |
|
|
57
|
+
| `databricks/databricks-gpt-5-4-nano` | 400K | | | | | | $0.20 | $1 |
|
|
58
|
+
| `databricks/databricks-gpt-5-5` | 1.1M | | | | | | $5 | $30 |
|
|
59
|
+
| `databricks/databricks-gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
60
|
+
| `databricks/databricks-gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
|
|
61
|
+
| `databricks/databricks-gpt-oss-120b` | 131K | | | | | | $0.07 | $0.28 |
|
|
62
|
+
| `databricks/databricks-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.20 |
|
|
63
|
+
|
|
64
|
+
## Advanced configuration
|
|
65
|
+
|
|
66
|
+
### Custom headers
|
|
67
|
+
|
|
68
|
+
```typescript
|
|
69
|
+
const agent = new Agent({
|
|
70
|
+
id: "custom-agent",
|
|
71
|
+
name: "custom-agent",
|
|
72
|
+
model: {
|
|
73
|
+
url: "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1",
|
|
74
|
+
id: "databricks/databricks-claude-haiku-4-5",
|
|
75
|
+
apiKey: process.env.DATABRICKS_TOKEN,
|
|
76
|
+
headers: {
|
|
77
|
+
"X-Custom-Header": "value"
|
|
78
|
+
}
|
|
79
|
+
}
|
|
80
|
+
});
|
|
81
|
+
```
|
|
82
|
+
|
|
83
|
+
### Dynamic model selection
|
|
84
|
+
|
|
85
|
+
```typescript
|
|
86
|
+
const agent = new Agent({
|
|
87
|
+
id: "dynamic-agent",
|
|
88
|
+
name: "Dynamic Agent",
|
|
89
|
+
model: ({ requestContext }) => {
|
|
90
|
+
const useAdvanced = requestContext.task === "complex";
|
|
91
|
+
return useAdvanced
|
|
92
|
+
? "databricks/databricks-gpt-oss-20b"
|
|
93
|
+
: "databricks/databricks-claude-haiku-4-5";
|
|
94
|
+
}
|
|
95
|
+
});
|
|
96
|
+
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Deep Infra
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 36 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
|
|
|
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| `deepinfra/anthropic/claude-4-opus` | 200K | | | | | | $17 | $83 |
|
|
37
37
|
| `deepinfra/deepseek-ai/DeepSeek-R1-0528` | 164K | | | | | | $0.50 | $2 |
|
|
38
38
|
| `deepinfra/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.26 | $0.38 |
|
|
39
|
+
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
39
40
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro` | 66K | | | | | | $2 | $3 |
|
|
40
41
|
| `deepinfra/google/gemma-4-26B-A4B-it` | 256K | | | | | | $0.07 | $0.34 |
|
|
41
42
|
| `deepinfra/google/gemma-4-31B-it` | 256K | | | | | | $0.13 | $0.38 |
|
|
@@ -87,4 +87,6 @@ const response = await agent.generate("Hello!", {
|
|
|
87
87
|
|
|
88
88
|
### Available Options
|
|
89
89
|
|
|
90
|
-
**thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
|
|
90
|
+
**thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
|
|
91
|
+
|
|
92
|
+
**reasoningEffort** (`"high" | "max" | undefined`)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# DigitalOcean
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 71 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/).
|
|
6
6
|
|
|
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
|
|
|
37
37
|
| `digitalocean/alibaba-qwen3-32b` | 131K | | | | | | $0.25 | $0.55 |
|
|
38
38
|
| `digitalocean/all-mini-lm-l6-v2` | 256 | | | | | | $0.01 | — |
|
|
39
39
|
| `digitalocean/anthropic-claude-4.1-opus` | 200K | | | | | | $15 | $75 |
|
|
40
|
+
| `digitalocean/anthropic-claude-4.5-haiku` | 200K | | | | | | $1 | $5 |
|
|
40
41
|
| `digitalocean/anthropic-claude-4.5-sonnet` | 1.0M | | | | | | $3 | $15 |
|
|
41
42
|
| `digitalocean/anthropic-claude-4.6-sonnet` | 1.0M | | | | | | $3 | $15 |
|
|
42
43
|
| `digitalocean/anthropic-claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
|
|
@@ -50,6 +51,7 @@ for await (const chunk of stream) {
|
|
|
50
51
|
| `digitalocean/bge-reranker-v2-m3` | 8K | | | | | | $0.01 | — |
|
|
51
52
|
| `digitalocean/deepseek-3.2` | 128K | | | | | | $0.50 | $2 |
|
|
52
53
|
| `digitalocean/deepseek-r1-distill-llama-70b` | 131K | | | | | | $0.99 | $0.99 |
|
|
54
|
+
| `digitalocean/deepseek-v3` | 164K | | | | | | — | — |
|
|
53
55
|
| `digitalocean/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
54
56
|
| `digitalocean/e5-large-v2` | 512 | | | | | | $0.02 | — |
|
|
55
57
|
| `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | — | | | | | | — | — |
|
|
@@ -60,12 +62,16 @@ for await (const chunk of stream) {
|
|
|
60
62
|
| `digitalocean/glm-5` | 203K | | | | | | $1 | $3 |
|
|
61
63
|
| `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
|
|
62
64
|
| `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
|
|
65
|
+
| `digitalocean/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
63
66
|
| `digitalocean/llama-4-maverick` | 1.0M | | | | | | $0.25 | $0.87 |
|
|
64
|
-
| `digitalocean/
|
|
67
|
+
| `digitalocean/llama3-8b-instruct` | 131K | | | | | | $0.20 | $0.20 |
|
|
65
68
|
| `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
|
|
66
69
|
| `digitalocean/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
70
|
+
| `digitalocean/ministral-3-8b-instruct-2512` | 262K | | | | | | — | — |
|
|
67
71
|
| `digitalocean/mistral-3-14B` | 262K | | | | | | $0.20 | $0.20 |
|
|
72
|
+
| `digitalocean/mistral-7b-instruct-v0.3` | 33K | | | | | | — | — |
|
|
68
73
|
| `digitalocean/multi-qa-mpnet-base-dot-v1` | 512 | | | | | | $0.01 | — |
|
|
74
|
+
| `digitalocean/nemotron-3-nano-30b` | 262K | | | | | | — | — |
|
|
69
75
|
| `digitalocean/nemotron-3-nano-omni` | 66K | | | | | | $0.50 | $0.90 |
|
|
70
76
|
| `digitalocean/nemotron-nano-12b-v2-vl` | 128K | | | | | | $0.20 | $0.60 |
|
|
71
77
|
| `digitalocean/nvidia-nemotron-3-super-120b` | 256K | | | | | | $0.30 | $0.65 |
|
|
@@ -86,11 +92,13 @@ for await (const chunk of stream) {
|
|
|
86
92
|
| `digitalocean/openai-gpt-5.5` | 1.0M | | | | | | $5 | $30 |
|
|
87
93
|
| `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
|
|
88
94
|
| `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
|
|
95
|
+
| `digitalocean/openai-gpt-image-2` | — | | | | | | — | — |
|
|
89
96
|
| `digitalocean/openai-gpt-oss-120b` | 131K | | | | | | $0.10 | $0.70 |
|
|
90
97
|
| `digitalocean/openai-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.45 |
|
|
91
98
|
| `digitalocean/openai-o1` | 200K | | | | | | $15 | $60 |
|
|
92
99
|
| `digitalocean/openai-o3` | 200K | | | | | | $2 | $8 |
|
|
93
100
|
| `digitalocean/openai-o3-mini` | 200K | | | | | | $1 | $4 |
|
|
101
|
+
| `digitalocean/qwen-2.5-14b-instruct` | 131K | | | | | | — | — |
|
|
94
102
|
| `digitalocean/qwen3-coder-flash` | 262K | | | | | | $0.45 | $2 |
|
|
95
103
|
| `digitalocean/qwen3-embedding-0.6b` | 8K | | | | | | $0.04 | — |
|
|
96
104
|
| `digitalocean/qwen3-tts-voicedesign` | 33K | | | | | | — | — |
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
# Fireworks (Firepass)
|
|
2
|
+
|
|
3
|
+
Access 1 Fireworks (Firepass) model through Mastra's model router. Authentication is handled automatically using the `FIREPASS_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
FIREPASS_API_KEY=your-api-key
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
```typescript
|
|
12
|
+
import { Agent } from "@mastra/core/agent";
|
|
13
|
+
|
|
14
|
+
const agent = new Agent({
|
|
15
|
+
id: "my-agent",
|
|
16
|
+
name: "My Agent",
|
|
17
|
+
instructions: "You are a helpful assistant",
|
|
18
|
+
model: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ----------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `firepass/accounts/fireworks/routers/kimi-k2p6-turbo` | 262K | | | | | | — | — |
|
|
38
|
+
|
|
39
|
+
## Advanced configuration
|
|
40
|
+
|
|
41
|
+
### Custom headers
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
const agent = new Agent({
|
|
45
|
+
id: "custom-agent",
|
|
46
|
+
name: "custom-agent",
|
|
47
|
+
model: {
|
|
48
|
+
url: "https://api.fireworks.ai/inference/v1/",
|
|
49
|
+
id: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo",
|
|
50
|
+
apiKey: process.env.FIREPASS_API_KEY,
|
|
51
|
+
headers: {
|
|
52
|
+
"X-Custom-Header": "value"
|
|
53
|
+
}
|
|
54
|
+
}
|
|
55
|
+
});
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
### Dynamic model selection
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "dynamic-agent",
|
|
63
|
+
name: "Dynamic Agent",
|
|
64
|
+
model: ({ requestContext }) => {
|
|
65
|
+
const useAdvanced = requestContext.task === "complex";
|
|
66
|
+
return useAdvanced
|
|
67
|
+
? "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
|
|
68
|
+
: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo";
|
|
69
|
+
}
|
|
70
|
+
});
|
|
71
|
+
```
|
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
# Google
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 38 Google models through Mastra's model router. Authentication is handled automatically using the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable.
|
|
4
4
|
|
|
5
|
-
Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/
|
|
5
|
+
Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
|
|
6
6
|
|
|
7
7
|
```bash
|
|
8
8
|
GOOGLE_GENERATIVE_AI_API_KEY=your-api-key
|
|
@@ -54,6 +54,7 @@ for await (const chunk of stream) {
|
|
|
54
54
|
| `google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
|
|
55
55
|
| `google/gemini-3-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
56
56
|
| `google/gemini-3.1-flash-image-preview` | 131K | | | | | | $0.25 | $60 |
|
|
57
|
+
| `google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
|
|
57
58
|
| `google/gemini-3.1-flash-lite-preview` | 1.0M | | | | | | $0.25 | $2 |
|
|
58
59
|
| `google/gemini-3.1-pro-preview` | 1.0M | | | | | | $2 | $12 |
|
|
59
60
|
| `google/gemini-3.1-pro-preview-customtools` | 1.0M | | | | | | $2 | $12 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Kilo Gateway
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 357 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
6
6
|
|
|
@@ -50,7 +50,6 @@ for await (const chunk of stream) {
|
|
|
50
50
|
| `kilo/alfredpros/codellama-7b-instruct-solidity` | 4K | | | | | | $0.80 | $1 |
|
|
51
51
|
| `kilo/alibaba/tongyi-deepresearch-30b-a3b` | 131K | | | | | | $0.09 | $0.45 |
|
|
52
52
|
| `kilo/allenai/olmo-3-32b-think` | 66K | | | | | | $0.15 | $0.50 |
|
|
53
|
-
| `kilo/allenai/olmo-3.1-32b-instruct` | 66K | | | | | | $0.20 | $0.60 |
|
|
54
53
|
| `kilo/alpindale/goliath-120b` | 6K | | | | | | $4 | $8 |
|
|
55
54
|
| `kilo/amazon/nova-2-lite-v1` | 1.0M | | | | | | $0.30 | $3 |
|
|
56
55
|
| `kilo/amazon/nova-lite-v1` | 300K | | | | | | $0.06 | $0.24 |
|
|
@@ -79,6 +78,7 @@ for await (const chunk of stream) {
|
|
|
79
78
|
| `kilo/arcee-ai/trinity-large-thinking` | 262K | | | | | | $0.22 | $0.85 |
|
|
80
79
|
| `kilo/arcee-ai/trinity-mini` | 131K | | | | | | $0.04 | $0.15 |
|
|
81
80
|
| `kilo/arcee-ai/virtuoso-large` | 131K | | | | | | $0.75 | $1 |
|
|
81
|
+
| `kilo/baidu/cobuddy:free` | 131K | | | | | | — | — |
|
|
82
82
|
| `kilo/baidu/ernie-4.5-21b-a3b` | 120K | | | | | | $0.07 | $0.28 |
|
|
83
83
|
| `kilo/baidu/ernie-4.5-21b-a3b-thinking` | 131K | | | | | | $0.07 | $0.28 |
|
|
84
84
|
| `kilo/baidu/ernie-4.5-300b-a47b` | 123K | | | | | | $0.28 | $1 |
|
|
@@ -161,6 +161,7 @@ for await (const chunk of stream) {
|
|
|
161
161
|
| `kilo/meta-llama/llama-guard-3-8b` | 131K | | | | | | $0.02 | $0.06 |
|
|
162
162
|
| `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
|
|
163
163
|
| `kilo/microsoft/phi-4` | 16K | | | | | | $0.06 | $0.14 |
|
|
164
|
+
| `kilo/microsoft/phi-4-mini-instruct` | 128K | | | | | | $0.08 | $0.35 |
|
|
164
165
|
| `kilo/microsoft/wizardlm-2-8x22b` | 66K | | | | | | $0.62 | $0.62 |
|
|
165
166
|
| `kilo/minimax/minimax-01` | 1.0M | | | | | | $0.20 | $1 |
|
|
166
167
|
| `kilo/minimax/minimax-m1` | 1.0M | | | | | | $0.40 | $2 |
|
|
@@ -182,6 +183,7 @@ for await (const chunk of stream) {
|
|
|
182
183
|
| `kilo/mistralai/mistral-large-2411` | 131K | | | | | | $2 | $6 |
|
|
183
184
|
| `kilo/mistralai/mistral-large-2512` | 262K | | | | | | $0.50 | $2 |
|
|
184
185
|
| `kilo/mistralai/mistral-medium-3` | 131K | | | | | | $0.40 | $2 |
|
|
186
|
+
| `kilo/mistralai/mistral-medium-3-5` | 262K | | | | | | $2 | $8 |
|
|
185
187
|
| `kilo/mistralai/mistral-medium-3.1` | 131K | | | | | | $0.40 | $2 |
|
|
186
188
|
| `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.02 | $0.04 |
|
|
187
189
|
| `kilo/mistralai/mistral-saba` | 33K | | | | | | $0.20 | $0.60 |
|
|
@@ -212,7 +214,6 @@ for await (const chunk of stream) {
|
|
|
212
214
|
| `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
|
|
213
215
|
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.10 | $0.50 |
|
|
214
216
|
| `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
|
|
215
|
-
| `kilo/nvidia/nemotron-nano-12b-v2-vl` | 131K | | | | | | $0.20 | $0.60 |
|
|
216
217
|
| `kilo/nvidia/nemotron-nano-9b-v2` | 131K | | | | | | $0.04 | $0.16 |
|
|
217
218
|
| `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
218
219
|
| `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
|
|
@@ -263,6 +264,7 @@ for await (const chunk of stream) {
|
|
|
263
264
|
| `kilo/openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
|
|
264
265
|
| `kilo/openai/gpt-audio` | 128K | | | | | | $3 | $10 |
|
|
265
266
|
| `kilo/openai/gpt-audio-mini` | 128K | | | | | | $0.60 | $2 |
|
|
267
|
+
| `kilo/openai/gpt-chat-latest` | 400K | | | | | | $5 | $30 |
|
|
266
268
|
| `kilo/openai/gpt-oss-120b` | 131K | | | | | | $0.04 | $0.19 |
|
|
267
269
|
| `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.03 | $0.14 |
|
|
268
270
|
| `kilo/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
|