@mastra/mcp-docs-server 1.2.26-alpha.1 → 1.2.26-alpha.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.docs/docs/agents/overview.md +1 -1
- package/.docs/docs/agents/processors.md +21 -0
- package/.docs/docs/deployment/mastra-server.md +8 -2
- package/.docs/docs/evals/datasets.md +5 -1
- package/.docs/docs/guides/context-engineering.md +1 -1
- package/.docs/docs/harness/background-tasks.md +30 -24
- package/.docs/docs/harness/signals.md +39 -0
- package/.docs/docs/index.md +1 -1
- package/.docs/docs/memory/message-history.md +6 -2
- package/.docs/docs/subagents.md +25 -0
- package/.docs/integrations/agentic-ui/ai-sdk-ui.md +7 -0
- package/.docs/integrations/file-storage/amazon-s3.md +7 -1
- package/.docs/integrations/file-storage/archil.md +3 -3
- package/.docs/integrations/frameworks/electron.md +1 -1
- package/.docs/integrations/sandboxes/cloudflare-sandbox.md +2 -0
- package/.docs/integrations/sandboxes/daytona.md +33 -0
- package/.docs/integrations/sandboxes/docker.md +13 -0
- package/.docs/integrations/voice/livekit.md +26 -2
- package/.docs/models/gateways/merge-gateway.md +6 -1
- package/.docs/models/gateways/netlify.md +2 -1
- package/.docs/models/gateways/openrouter.md +8 -2
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/above.md +1 -1
- package/.docs/models/providers/baseten.md +2 -1
- package/.docs/models/providers/bothub.md +2 -1
- package/.docs/models/providers/cline-pass.md +18 -17
- package/.docs/models/providers/cortecs.md +3 -3
- package/.docs/models/providers/deepinfra.md +6 -6
- package/.docs/models/providers/edenai.md +18 -4
- package/.docs/models/providers/empiriolabs.md +3 -1
- package/.docs/models/providers/fireworks-ai.md +2 -1
- package/.docs/models/providers/greenpt.md +2 -1
- package/.docs/models/providers/huggingface.md +4 -1
- package/.docs/models/providers/hyper.md +6 -5
- package/.docs/models/providers/kilo.md +15 -10
- package/.docs/models/providers/llmgateway-providers.md +5 -2
- package/.docs/models/providers/llmgateway.md +3 -1
- package/.docs/models/providers/nan.md +1 -1
- package/.docs/models/providers/nano-gpt.md +13 -4
- package/.docs/models/providers/ofox.md +30 -3
- package/.docs/models/providers/ollama-cloud.md +2 -1
- package/.docs/models/providers/pioneer.md +11 -2
- package/.docs/models/providers/requesty.md +2 -2
- package/.docs/models/providers/volcengine-coding-plan.md +3 -1
- package/.docs/reference/agents/agent.md +16 -0
- package/.docs/reference/agents/generate.md +2 -0
- package/.docs/reference/client-js/datasets.md +1 -1
- package/.docs/reference/configuration.md +2 -2
- package/.docs/reference/datasets/purgeItem.md +3 -3
- package/.docs/reference/index.md +3 -0
- package/.docs/reference/memory/cloneThread.md +2 -0
- package/.docs/reference/memory/copyThread.md +65 -0
- package/.docs/reference/memory/memory-class.md +2 -1
- package/.docs/reference/memory/recall.md +51 -0
- package/.docs/reference/memory/updateThreadResourceId.md +46 -0
- package/.docs/reference/processors/agents-md-injector.md +55 -0
- package/.docs/reference/processors/processor-interface.md +2 -0
- package/.docs/reference/pubsub/redis-streams.md +6 -0
- package/.docs/reference/pubsub/valkey-streams.md +6 -0
- package/.docs/reference/streaming/agents/stream.md +30 -0
- package/.docs/reference/workspace/filesystem.md +72 -0
- package/package.json +5 -5
|
@@ -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 365 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -46,8 +46,11 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
46
46
|
| `~google/gemini-flash-latest` |
|
|
47
47
|
| `~google/gemini-pro-latest` |
|
|
48
48
|
| `~moonshotai/kimi-latest` |
|
|
49
|
-
| `~openai/gpt-latest`
|
|
49
|
+
| `~openai/gpt-astra-latest` |
|
|
50
|
+
| `~openai/gpt-luna-latest` |
|
|
50
51
|
| `~openai/gpt-mini-latest` |
|
|
52
|
+
| `~openai/gpt-sol-latest` |
|
|
53
|
+
| `~openai/gpt-terra-latest` |
|
|
51
54
|
| `~x-ai/grok-latest` |
|
|
52
55
|
| `~z-ai/glm-flash-latest` |
|
|
53
56
|
| `~z-ai/glm-latest` |
|
|
@@ -147,6 +150,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
147
150
|
| `inclusionai/ling-3.0-flash-fin` |
|
|
148
151
|
| `inclusionai/ling-3.0-flash-fin:free` |
|
|
149
152
|
| `inclusionai/ling-3.0-flash-sante:free` |
|
|
153
|
+
| `inclusionai/ling-3.0-flash-vl` |
|
|
150
154
|
| `inclusionai/ling-3.0-flash-vl:free` |
|
|
151
155
|
| `kwaipilot/kat-coder-pro-v2` |
|
|
152
156
|
| `kwaipilot/kat-coder-pro-v2.5` |
|
|
@@ -350,7 +354,9 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
350
354
|
| `rekaai/reka-flash-3` |
|
|
351
355
|
| `relace/relace-apply-3` |
|
|
352
356
|
| `relace/relace-search` |
|
|
357
|
+
| `sakana/fugu-max` |
|
|
353
358
|
| `sakana/fugu-ultra` |
|
|
359
|
+
| `sakana/fugu-ultra-v2` |
|
|
354
360
|
| `sakana/sakana-namazu` |
|
|
355
361
|
| `sao10k/l3-lunaris-8b` |
|
|
356
362
|
| `sao10k/l3.1-euryale-70b` |
|
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 7245 models from 200 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -38,7 +38,7 @@ for await (const chunk of stream) {
|
|
|
38
38
|
|
|
39
39
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
40
|
| ------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
-
| `above/deepseek-v4-flash` | 1.0M | | | | | | $0.
|
|
41
|
+
| `above/deepseek-v4-flash` | 1.0M | | | | | | $0.17 | $0.66 |
|
|
42
42
|
| `above/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.24 | $0.73 |
|
|
43
43
|
| `above/deepseek-v4-pro` | 1.0M | | | | | | $0.73 | $2 |
|
|
44
44
|
| `above/glm-5.2` | 1.0M | | | | | | $2 | $5 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Baseten
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 23 Baseten models through Mastra's model router. Authentication is handled automatically using the `BASETEN_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Baseten documentation](https://docs.baseten.co).
|
|
10
10
|
|
|
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `baseten/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.13 | $0.26 |
|
|
42
42
|
| `baseten/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $3 |
|
|
43
43
|
| `baseten/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
44
|
+
| `baseten/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
44
45
|
| `baseten/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.60 | $3 |
|
|
45
46
|
| `baseten/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.95 | $4 |
|
|
46
47
|
| `baseten/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Bothub
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 8 Bothub models through Mastra's model router. Authentication is handled automatically using the `BOTHUB_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Bothub documentation](https://bothub.ru/models).
|
|
10
10
|
|
|
@@ -44,6 +44,7 @@ for await (const chunk of stream) {
|
|
|
44
44
|
| `bothub/glm-5.3` | 1.0M | | | | | | $2 | $5 |
|
|
45
45
|
| `bothub/glm-5.3-flash` | 1.0M | | | | | | $0.12 | $0.44 |
|
|
46
46
|
| `bothub/gpt-5.6-luna` | 1.1M | | | | | | $0.06 | $0.37 |
|
|
47
|
+
| `bothub/muse-spark-1.3-contributor` | 1.0M | | | | | | $0.10 | $0.20 |
|
|
47
48
|
| `bothub/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
|
|
48
49
|
|
|
49
50
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# ClinePass
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 15 ClinePass models through Mastra's model router. Authentication is handled automatically using the `CLINE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [ClinePass documentation](https://docs.cline.bot/getting-started/clinepass).
|
|
10
10
|
|
|
@@ -36,22 +36,23 @@ for await (const chunk of stream) {
|
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
39
|
-
| Model
|
|
40
|
-
|
|
|
41
|
-
| `cline-pass/cline-pass/deepseek-v4-flash`
|
|
42
|
-
| `cline-pass/cline-pass/deepseek-v4-pro`
|
|
43
|
-
| `cline-pass/cline-pass/
|
|
44
|
-
| `cline-pass/cline-pass/glm-5.
|
|
45
|
-
| `cline-pass/cline-pass/glm-5.3
|
|
46
|
-
| `cline-pass/cline-pass/
|
|
47
|
-
| `cline-pass/cline-pass/kimi-k2.
|
|
48
|
-
| `cline-pass/cline-pass/kimi-
|
|
49
|
-
| `cline-pass/cline-pass/
|
|
50
|
-
| `cline-pass/cline-pass/mimo-v2.5
|
|
51
|
-
| `cline-pass/cline-pass/
|
|
52
|
-
| `cline-pass/cline-pass/
|
|
53
|
-
| `cline-pass/cline-pass/qwen3.7-
|
|
54
|
-
| `cline-pass/cline-pass/qwen3.
|
|
39
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
|
+
| ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
|
+
| `cline-pass/cline-pass/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
42
|
+
| `cline-pass/cline-pass/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
43
|
+
| `cline-pass/cline-pass/deepseek-v4.1-flash` | 1.0M | | | | | | $0.15 | $0.60 |
|
|
44
|
+
| `cline-pass/cline-pass/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
45
|
+
| `cline-pass/cline-pass/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
46
|
+
| `cline-pass/cline-pass/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
47
|
+
| `cline-pass/cline-pass/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
48
|
+
| `cline-pass/cline-pass/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
49
|
+
| `cline-pass/cline-pass/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
50
|
+
| `cline-pass/cline-pass/mimo-v2.5` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
51
|
+
| `cline-pass/cline-pass/mimo-v2.5-pro` | 1.0M | | | | | | $2 | $3 |
|
|
52
|
+
| `cline-pass/cline-pass/minimax-m3` | 1.0M | | | | | | $0.30 | $1 |
|
|
53
|
+
| `cline-pass/cline-pass/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
|
|
54
|
+
| `cline-pass/cline-pass/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
|
|
55
|
+
| `cline-pass/cline-pass/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
55
56
|
|
|
56
57
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
57
58
|
|
|
@@ -52,7 +52,7 @@ for await (const chunk of stream) {
|
|
|
52
52
|
| `cortecs/codestral-2508` | 256K | | | | | | $0.33 | $1 |
|
|
53
53
|
| `cortecs/deepseek-r1-0528` | 164K | | | | | | $0.65 | $3 |
|
|
54
54
|
| `cortecs/deepseek-v3.2` | 164K | | | | | | $0.30 | $0.49 |
|
|
55
|
-
| `cortecs/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
55
|
+
| `cortecs/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.09 | $0.17 |
|
|
56
56
|
| `cortecs/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
57
57
|
| `cortecs/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
|
|
58
58
|
| `cortecs/devstral-2512` | 256K | | | | | | $0.48 | $2 |
|
|
@@ -73,7 +73,7 @@ for await (const chunk of stream) {
|
|
|
73
73
|
| `cortecs/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
74
74
|
| `cortecs/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
75
75
|
| `cortecs/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
76
|
-
| `cortecs/glm-5.3-flash` | 1.0M | | | | | | $0.
|
|
76
|
+
| `cortecs/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.35 |
|
|
77
77
|
| `cortecs/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
|
|
78
78
|
| `cortecs/gpt-4.1` | 1.0M | | | | | | $2 | $9 |
|
|
79
79
|
| `cortecs/gpt-4.1-mini` | 1.0M | | | | | | $0.43 | $2 |
|
|
@@ -139,7 +139,7 @@ for await (const chunk of stream) {
|
|
|
139
139
|
| `cortecs/qwen3.6-27b` | 262K | | | | | | $0.45 | $3 |
|
|
140
140
|
| `cortecs/qwen3.6-35b-a3b` | 262K | | | | | | $0.17 | $0.56 |
|
|
141
141
|
| `cortecs/qwen3.8-2.4t-a95b` | 262K | | | | | | $3 | $6 |
|
|
142
|
-
| `cortecs/qwen3.8-27b` | 262K | | | | | | $0.
|
|
142
|
+
| `cortecs/qwen3.8-27b` | 262K | | | | | | $0.10 | $0.40 |
|
|
143
143
|
| `cortecs/qwen3.8-flash-next` | 262K | | | | | | $0.20 | $0.50 |
|
|
144
144
|
| `cortecs/qwen3guard-gen-0.6b` | 32K | | | | | | — | — |
|
|
145
145
|
| `cortecs/qwen3guard-gen-8b` | 32K | | | | | | — | — |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Deep Infra
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 67 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
|
|
|
@@ -49,14 +49,16 @@ for await (const chunk of stream) {
|
|
|
49
49
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
50
50
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
51
51
|
| `deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
52
|
-
| `deepinfra/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.
|
|
52
|
+
| `deepinfra/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.20 | $0.60 |
|
|
53
|
+
| `deepinfra/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
|
|
54
|
+
| `deepinfra/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
55
|
+
| `deepinfra/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
53
56
|
| `deepinfra/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.07 | $0.34 |
|
|
54
57
|
| `deepinfra/google/gemma-4-31B-it` | 262K | | | | | | $0.13 | $0.38 |
|
|
55
58
|
| `deepinfra/google/gemma-4-E4B-it` | 131K | | | | | | $0.02 | $0.10 |
|
|
56
59
|
| `deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo` | 131K | | | | | | $0.10 | $0.32 |
|
|
57
60
|
| `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M | | | | | | $0.20 | $0.80 |
|
|
58
61
|
| `deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct` | 328K | | | | | | $0.10 | $0.30 |
|
|
59
|
-
| `deepinfra/MiniMaxAI/MiniMax-M2.7` | 197K | | | | | | $0.25 | $1 |
|
|
60
62
|
| `deepinfra/MiniMaxAI/MiniMax-M3` | 524K | | | | | | $0.28 | $1 |
|
|
61
63
|
| `deepinfra/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.75 | $4 |
|
|
62
64
|
| `deepinfra/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.68 | $3 |
|
|
@@ -86,12 +88,10 @@ for await (const chunk of stream) {
|
|
|
86
88
|
| `deepinfra/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
|
|
87
89
|
| `deepinfra/thinkingmachines/Inkling` | 524K | | | | | | $0.95 | $4 |
|
|
88
90
|
| `deepinfra/thinkingmachines/Inkling-Small` | 524K | | | | | | $0.45 | $1 |
|
|
89
|
-
| `deepinfra/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.
|
|
91
|
+
| `deepinfra/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.14 | $0.28 |
|
|
90
92
|
| `deepinfra/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
91
93
|
| `deepinfra/zai-org/GLM-4.6` | 203K | | | | | | $0.50 | $2 |
|
|
92
94
|
| `deepinfra/zai-org/GLM-4.7` | 203K | | | | | | $0.40 | $2 |
|
|
93
|
-
| `deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
94
|
-
| `deepinfra/zai-org/GLM-5` | 203K | | | | | | $0.60 | $2 |
|
|
95
95
|
| `deepinfra/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
96
96
|
| `deepinfra/zai-org/GLM-5.2` | 1.0M | | | | | | $0.75 | $2 |
|
|
97
97
|
| `deepinfra/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Eden AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 274 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
|
|
|
@@ -44,10 +44,18 @@ for await (const chunk of stream) {
|
|
|
44
44
|
| `edenai/amazon/amazon.nova-micro-v1:0@us` | 128K | | | | | | $0.04 | $0.14 |
|
|
45
45
|
| `edenai/amazon/amazon.nova-pro-v1:0` | 300K | | | | | | $0.80 | $3 |
|
|
46
46
|
| `edenai/amazon/amazon.nova-pro-v1:0@us` | 300K | | | | | | $0.80 | $3 |
|
|
47
|
+
| `edenai/amazon/google.gemma-3-12b-it` | 128K | | | | | | $0.09 | $0.29 |
|
|
48
|
+
| `edenai/amazon/google.gemma-3-12b-it@us` | 128K | | | | | | $0.09 | $0.29 |
|
|
49
|
+
| `edenai/amazon/google.gemma-3-27b-it` | 128K | | | | | | $0.23 | $0.38 |
|
|
50
|
+
| `edenai/amazon/google.gemma-3-27b-it@us` | 128K | | | | | | $0.23 | $0.38 |
|
|
51
|
+
| `edenai/amazon/google.gemma-3-4b-it` | 128K | | | | | | $0.04 | $0.08 |
|
|
52
|
+
| `edenai/amazon/google.gemma-3-4b-it@us` | 128K | | | | | | $0.04 | $0.08 |
|
|
47
53
|
| `edenai/amazon/mistral.pixtral-large-2502-v1:0` | 128K | | | | | | $2 | $6 |
|
|
48
54
|
| `edenai/amazon/mistral.pixtral-large-2502-v1:0@us` | 128K | | | | | | $2 | $6 |
|
|
49
55
|
| `edenai/amazon/moonshot.kimi-k2-thinking` | 128K | | | | | | $0.60 | $3 |
|
|
50
56
|
| `edenai/amazon/moonshotai.kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
|
|
57
|
+
| `edenai/amazon/openai.gpt-oss-safeguard-20b` | 128K | | | | | | $0.07 | $0.20 |
|
|
58
|
+
| `edenai/amazon/openai.gpt-oss-safeguard-20b@us` | 128K | | | | | | $0.07 | $0.20 |
|
|
51
59
|
| `edenai/amazon/zai.glm-4.7-flash` | 200K | | | | | | $0.07 | $0.40 |
|
|
52
60
|
| `edenai/amazon/zai.glm-4.7-flash@us` | 200K | | | | | | $0.07 | $0.40 |
|
|
53
61
|
| `edenai/anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
|
|
@@ -94,7 +102,10 @@ for await (const chunk of stream) {
|
|
|
94
102
|
| `edenai/deepinfra/deepseek-ai/DeepSeek-V3-0324` | 164K | | | | | | $0.24 | $0.90 |
|
|
95
103
|
| `edenai/deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.06 | $0.18 |
|
|
96
104
|
| `edenai/deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
97
|
-
| `edenai/deepinfra/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.
|
|
105
|
+
| `edenai/deepinfra/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.20 | $0.60 |
|
|
106
|
+
| `edenai/deepinfra/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
|
|
107
|
+
| `edenai/deepinfra/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
108
|
+
| `edenai/deepinfra/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
98
109
|
| `edenai/deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct` | 131K | | | | | | $0.34 | $0.34 |
|
|
99
110
|
| `edenai/deepinfra/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.10 | $0.32 |
|
|
100
111
|
| `edenai/deepinfra/meta-llama/Llama-Guard-3-8B` | 131K | | | | | | $0.06 | $0.06 |
|
|
@@ -146,8 +157,9 @@ for await (const chunk of stream) {
|
|
|
146
157
|
| `edenai/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
147
158
|
| `edenai/groq/openai/gpt-oss-120b` | 131K | | | | | | $0.15 | $0.60 |
|
|
148
159
|
| `edenai/groq/openai/gpt-oss-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
149
|
-
| `edenai/
|
|
150
|
-
| `edenai/ionos/
|
|
160
|
+
| `edenai/groq/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
|
|
161
|
+
| `edenai/ionos/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.75 | $0.75 |
|
|
162
|
+
| `edenai/ionos/openai/gpt-oss-120b` | 131K | | | | | | $0.17 | $0.75 |
|
|
151
163
|
| `edenai/minimax/MiniMax-M2` | 205K | | | | | | $0.30 | $1 |
|
|
152
164
|
| `edenai/minimax/MiniMax-M2.1` | 205K | | | | | | $0.30 | $1 |
|
|
153
165
|
| `edenai/minimax/MiniMax-M2.5` | 205K | | | | | | $0.30 | $1 |
|
|
@@ -171,6 +183,7 @@ for await (const chunk of stream) {
|
|
|
171
183
|
| `edenai/moonshot/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
172
184
|
| `edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
173
185
|
| `edenai/nebius/deepseek-ai/DeepSeek-V4-Pro-0813` | 979K | | | | | | $1 | $4 |
|
|
186
|
+
| `edenai/nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
|
|
174
187
|
| `edenai/nebius/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.13 | $0.40 |
|
|
175
188
|
| `edenai/nebius/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.30 | $0.90 |
|
|
176
189
|
| `edenai/nebius/nvidia/Nemotron-3-Ultra-550b-a55b` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -243,6 +256,7 @@ for await (const chunk of stream) {
|
|
|
243
256
|
| `edenai/qwen/qwen3.8-max-0902` | 1.0M | | | | | | $2 | $6 |
|
|
244
257
|
| `edenai/qwen/qwq-plus` | 131K | | | | | | $0.80 | $2 |
|
|
245
258
|
| `edenai/scaleway/deepseek-v4-flash-0731` | 256K | | | | | | $0.46 | $0.93 |
|
|
259
|
+
| `edenai/scaleway/gemma-3-27b-it` | 40K | | | | | | $0.29 | $0.57 |
|
|
246
260
|
| `edenai/scaleway/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.70 |
|
|
247
261
|
| `edenai/scaleway/llama-3.3-70b-instruct` | 128K | | | | | | $1 | $1 |
|
|
248
262
|
| `edenai/tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# EmpirioLabs AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 60 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
|
|
10
10
|
|
|
@@ -45,6 +45,8 @@ for await (const chunk of stream) {
|
|
|
45
45
|
| `empiriolabs/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
46
46
|
| `empiriolabs/fugu-ultra-v1-0` | 1.0M | | | | | | $8 | $45 |
|
|
47
47
|
| `empiriolabs/fugu-ultra-v1-1` | 1.0M | | | | | | $5 | $30 |
|
|
48
|
+
| `empiriolabs/fugu-ultra-v2-0` | 1.0M | | | | | | $5 | $30 |
|
|
49
|
+
| `empiriolabs/gemma-3-27b` | 128K | | | | | | — | — |
|
|
48
50
|
| `empiriolabs/gemma-4-26b-a4b` | 262K | | | | | | $0.05 | $0.29 |
|
|
49
51
|
| `empiriolabs/glm-4-5-flash` | 200K | | | | | | — | — |
|
|
50
52
|
| `empiriolabs/glm-4-6v-flash` | 128K | | | | | | — | — |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Fireworks AI
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 23 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
|
|
10
10
|
|
|
@@ -41,6 +41,7 @@ for await (const chunk of stream) {
|
|
|
41
41
|
| `fireworks-ai/accounts/fireworks/models/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
42
42
|
| `fireworks-ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
43
43
|
| `fireworks-ai/accounts/fireworks/models/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
44
|
+
| `fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash` | 1.0M | | | | | | $0.22 | $0.66 |
|
|
44
45
|
| `fireworks-ai/accounts/fireworks/models/glm-5p2` | 1.0M | | | | | | $1 | $4 |
|
|
45
46
|
| `fireworks-ai/accounts/fireworks/models/glm-5p3` | 1.0M | | | | | | $1 | $4 |
|
|
46
47
|
| `fireworks-ai/accounts/fireworks/models/glm-5p3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# GreenPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 40 GreenPT models through Mastra's model router. Authentication is handled automatically using the `GREENPT_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [GreenPT documentation](https://docs.greenpt.ai).
|
|
10
10
|
|
|
@@ -39,6 +39,7 @@ for await (const chunk of stream) {
|
|
|
39
39
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
40
40
|
| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
41
|
| `greenpt/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.16 | $0.40 |
|
|
42
|
+
| `greenpt/deepseek-v4.1-flash` | 1.0M | | | | | | $0.26 | $1 |
|
|
42
43
|
| `greenpt/devstral-2-123b-instruct-2512` | 200K | | | | | | $0.57 | $3 |
|
|
43
44
|
| `greenpt/gemma-3-27b-it` | 40K | | | | | | $0.34 | $0.68 |
|
|
44
45
|
| `greenpt/gemma4` | 262K | | | | | | $0.57 | $2 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Hugging Face
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 77 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Hugging Face documentation](https://huggingface.co).
|
|
10
10
|
|
|
@@ -50,6 +50,9 @@ for await (const chunk of stream) {
|
|
|
50
50
|
| `huggingface/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $0.43 | $0.87 |
|
|
51
51
|
| `huggingface/deepseek-ai/DeepSeek-V4-Pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
52
52
|
| `huggingface/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
53
|
+
| `huggingface/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
|
|
54
|
+
| `huggingface/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
|
|
55
|
+
| `huggingface/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
|
|
53
56
|
| `huggingface/google/gemma-4-26B-A4B-it` | 262K | | | | | | $0.13 | $0.40 |
|
|
54
57
|
| `huggingface/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
55
58
|
| `huggingface/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.06 | $0.06 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Charm Hyper
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 34 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
|
|
10
10
|
|
|
@@ -42,13 +42,14 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
|
|
43
43
|
| `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
|
|
44
44
|
| `hyper/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
45
|
-
| `hyper/
|
|
45
|
+
| `hyper/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
46
|
+
| `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.10 | $0.36 |
|
|
46
47
|
| `hyper/glm-5` | 203K | | | | | | $0.86 | $3 |
|
|
47
48
|
| `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
48
49
|
| `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
|
|
49
50
|
| `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
|
|
50
51
|
| `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
|
|
51
|
-
| `hyper/gpt-oss-120b` | 128K | | | | | | $0.
|
|
52
|
+
| `hyper/gpt-oss-120b` | 128K | | | | | | $0.17 | $0.66 |
|
|
52
53
|
| `hyper/inkling` | 1.0M | | | | | | $1 | $4 |
|
|
53
54
|
| `hyper/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
54
55
|
| `hyper/kimi-k2.5` | 262K | | | | | | $0.56 | $3 |
|
|
@@ -56,8 +57,8 @@ for await (const chunk of stream) {
|
|
|
56
57
|
| `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
|
|
57
58
|
| `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
|
|
58
59
|
| `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
|
|
59
|
-
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.
|
|
60
|
-
| `hyper/minimax-m2.7` | 262K | | | | | | $0.
|
|
60
|
+
| `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.26 | $0.84 |
|
|
61
|
+
| `hyper/minimax-m2.7` | 262K | | | | | | $0.40 | $1 |
|
|
61
62
|
| `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
|
|
62
63
|
| `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.45 | $2 |
|
|
63
64
|
| `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 373 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 +45,15 @@ 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 | | | | | | $2 | $
|
|
49
|
-
| `kilo/~openai/gpt-latest`
|
|
48
|
+
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $8 |
|
|
49
|
+
| `kilo/~openai/gpt-astra-latest` | 1.1M | | | | | | $10 | $50 |
|
|
50
|
+
| `kilo/~openai/gpt-luna-latest` | 1.1M | | | | | | $0.20 | $1 |
|
|
50
51
|
| `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
|
|
52
|
+
| `kilo/~openai/gpt-sol-latest` | 1.1M | | | | | | $2 | $10 |
|
|
53
|
+
| `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
|
|
51
54
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
52
55
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
53
|
-
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.
|
|
56
|
+
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.87 | $3 |
|
|
54
57
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
55
58
|
| `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
|
|
56
59
|
| `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
|
|
@@ -92,7 +95,7 @@ for await (const chunk of stream) {
|
|
|
92
95
|
| `kilo/cohere/command-r7b-12-2024` | 128K | | | | | | $0.04 | $0.15 |
|
|
93
96
|
| `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
|
|
94
97
|
| `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.26 | $1 |
|
|
95
|
-
| `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.
|
|
98
|
+
| `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.25 | $1 |
|
|
96
99
|
| `kilo/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.27 | $1 |
|
|
97
100
|
| `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
|
|
98
101
|
| `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
|
|
@@ -145,6 +148,7 @@ for await (const chunk of stream) {
|
|
|
145
148
|
| `kilo/inclusionai/ling-3.0-flash-fin` | 262K | | | | | | $0.06 | $0.18 |
|
|
146
149
|
| `kilo/inclusionai/ling-3.0-flash-fin:free` | 262K | | | | | | — | — |
|
|
147
150
|
| `kilo/inclusionai/ling-3.0-flash-sante:free` | 262K | | | | | | — | — |
|
|
151
|
+
| `kilo/inclusionai/ling-3.0-flash-vl` | 131K | | | | | | $0.06 | $0.18 |
|
|
148
152
|
| `kilo/inclusionai/ling-3.0-flash-vl:free` | 262K | | | | | | — | — |
|
|
149
153
|
| `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
|
|
150
154
|
| `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
|
|
@@ -215,13 +219,13 @@ for await (const chunk of stream) {
|
|
|
215
219
|
| `kilo/nousresearch/hermes-4-405b` | 131K | | | | | | $1 | $3 |
|
|
216
220
|
| `kilo/nvidia/nemotron-3-nano-30b-a3b` | 262K | | | | | | $0.05 | $0.20 |
|
|
217
221
|
| `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K | | | | | | — | — |
|
|
218
|
-
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.
|
|
222
|
+
| `kilo/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.08 | $0.45 |
|
|
219
223
|
| `kilo/nvidia/nemotron-3-super-120b-a12b:free` | 262K | | | | | | — | — |
|
|
220
224
|
| `kilo/nvidia/nemotron-3-ultra-550b-a55b` | 256K | | | | | | $0.50 | $2 |
|
|
221
225
|
| `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
|
|
222
226
|
| `kilo/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.20 | $0.20 |
|
|
223
227
|
| `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
|
|
224
|
-
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.
|
|
228
|
+
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.07 | $0.18 |
|
|
225
229
|
| `kilo/nvidia/nemotron-3.5-lightning:free` | 1.0M | | | | | | — | — |
|
|
226
230
|
| `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
227
231
|
| `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
|
|
@@ -309,7 +313,7 @@ for await (const chunk of stream) {
|
|
|
309
313
|
| `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
|
|
310
314
|
| `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
|
|
311
315
|
| `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
|
|
312
|
-
| `kilo/qwen/qwen3-30b-a3b-instruct-2507` |
|
|
316
|
+
| `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.13 | $0.52 |
|
|
313
317
|
| `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
|
|
314
318
|
| `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
|
|
315
319
|
| `kilo/qwen/qwen3-8b` | 131K | | | | | | $0.12 | $0.46 |
|
|
@@ -353,7 +357,9 @@ for await (const chunk of stream) {
|
|
|
353
357
|
| `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
|
|
354
358
|
| `kilo/relace/relace-apply-3` | 256K | | | | | | $0.85 | $1 |
|
|
355
359
|
| `kilo/relace/relace-search` | 256K | | | | | | $1 | $3 |
|
|
360
|
+
| `kilo/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
356
361
|
| `kilo/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
362
|
+
| `kilo/sakana/fugu-ultra-v2` | 1.0M | | | | | | $5 | $30 |
|
|
357
363
|
| `kilo/sakana/sakana-namazu` | 262K | | | | | | $0.95 | $4 |
|
|
358
364
|
| `kilo/sao10k/l3-lunaris-8b` | 8K | | | | | | $0.04 | $0.05 |
|
|
359
365
|
| `kilo/sao10k/l3.1-euryale-70b` | 131K | | | | | | $0.85 | $0.85 |
|
|
@@ -379,7 +385,6 @@ for await (const chunk of stream) {
|
|
|
379
385
|
| `kilo/thinkingmachines/inkling` | 1.0M | | | | | | $0.95 | $4 |
|
|
380
386
|
| `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
|
|
381
387
|
| `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
|
|
382
|
-
| `kilo/thinkingmachines/inkling:free` | 1.0M | | | | | | — | — |
|
|
383
388
|
| `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.35 | $0.65 |
|
|
384
389
|
| `kilo/upstage/solar-pro-3` | 131K | | | | | | $0.15 | $0.60 |
|
|
385
390
|
| `kilo/upstage/solar-pro4` | 524K | | | | | | $0.30 | $1 |
|
|
@@ -402,7 +407,7 @@ for await (const chunk of stream) {
|
|
|
402
407
|
| `kilo/z-ai/glm-5` | 198K | | | | | | $0.60 | $2 |
|
|
403
408
|
| `kilo/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
|
|
404
409
|
| `kilo/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
|
|
405
|
-
| `kilo/z-ai/glm-5.2` |
|
|
410
|
+
| `kilo/z-ai/glm-5.2` | 203K | | | | | | $1 | $4 |
|
|
406
411
|
| `kilo/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
407
412
|
| `kilo/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
408
413
|
| `kilo/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 377 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
|
|
|
@@ -166,7 +166,7 @@ for await (const chunk of stream) {
|
|
|
166
166
|
| `llmgateway-providers/cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
|
|
167
167
|
| `llmgateway-providers/cerebras/llama-3.3-70b-instruct` | 128K | | | | | | $0.85 | $1 |
|
|
168
168
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
169
|
-
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 1.
|
|
169
|
+
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 1.1M | | | | | | $0.05 | $0.10 |
|
|
170
170
|
| `llmgateway-providers/consensusprotocol/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.25 |
|
|
171
171
|
| `llmgateway-providers/consensusprotocol/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
|
|
172
172
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
@@ -347,7 +347,9 @@ for await (const chunk of stream) {
|
|
|
347
347
|
| `llmgateway-providers/runware/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.14 |
|
|
348
348
|
| `llmgateway-providers/runware/kimi-k2.6` | 262K | | | | | | $0.60 | $3 |
|
|
349
349
|
| `llmgateway-providers/runware/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
350
|
+
| `llmgateway-providers/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
350
351
|
| `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
352
|
+
| `llmgateway-providers/sakana/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
|
|
351
353
|
| `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.80 | $3 |
|
|
352
354
|
| `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
353
355
|
| `llmgateway-providers/scx-ai-gp/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -386,6 +388,7 @@ for await (const chunk of stream) {
|
|
|
386
388
|
| `llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.22 | $2 |
|
|
387
389
|
| `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
|
|
388
390
|
| `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
|
|
391
|
+
| `llmgateway-providers/vichar-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
389
392
|
| `llmgateway-providers/vichar-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
|
|
390
393
|
| `llmgateway-providers/xai/grok-4` | 256K | | | | | | $3 | $15 |
|
|
391
394
|
| `llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# DevPass (LLM Gateway)
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 188 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
|
|
10
10
|
|
|
@@ -60,7 +60,9 @@ for await (const chunk of stream) {
|
|
|
60
60
|
| `llmgateway/deepseek-v4-pro` | 1.1M | | | | | | $0.43 | $0.87 |
|
|
61
61
|
| `llmgateway/deepseek-v4.1-flash` | 1.1M | | | | | | $0.15 | $0.60 |
|
|
62
62
|
| `llmgateway/ernie-4.5-vl-424b-a47b` | 123K | | | | | | $0.42 | $1 |
|
|
63
|
+
| `llmgateway/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
63
64
|
| `llmgateway/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
65
|
+
| `llmgateway/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
|
|
64
66
|
| `llmgateway/gemini-2.5-flash` | 1.0M | | | | | | $0.30 | $3 |
|
|
65
67
|
| `llmgateway/gemini-2.5-flash-lite` | 1.0M | | | | | | $0.10 | $0.40 |
|
|
66
68
|
| `llmgateway/gemini-2.5-pro` | 1.0M | | | | | | $1 | $10 |
|
|
@@ -40,7 +40,7 @@ for await (const chunk of stream) {
|
|
|
40
40
|
| ----------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
41
41
|
| `nan/deepseek-v4-flash` | 1.0M | | | | | | — | — |
|
|
42
42
|
| `nan/gemma4` | 262K | | | | | | — | — |
|
|
43
|
-
| `nan/glm5.
|
|
43
|
+
| `nan/glm5.3` | 1.0M | | | | | | — | — |
|
|
44
44
|
| `nan/glm5.3-flash` | 1.0M | | | | | | — | — |
|
|
45
45
|
| `nan/mimo-v2.5` | 1.0M | | | | | | — | — |
|
|
46
46
|
| `nan/qwen3.6` | 262K | | | | | | — | — |
|