@mastra/mcp-docs-server 1.2.27-alpha.17 → 1.2.27-alpha.19

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.
@@ -6,214 +6,214 @@
6
6
 
7
7
  List of required environment variables for each model provider and gateway supported by Mastra's [model router](https://mastra.ai/models).
8
8
 
9
- | Name | Model prefix | Environment variables |
10
- | ---------------------------------------------------------------------------------------------- | -------------------------- | ----------------------------------------------------------------------------------------------------- |
11
- | [302.AI](https://mastra.ai/models/providers/302ai) | `302ai/*` | `302AI_API_KEY` |
12
- | [Abacus](https://mastra.ai/models/providers/abacus) | `abacus/*` | `ABACUS_API_KEY` |
13
- | [abliteration.ai](https://mastra.ai/models/providers/abliteration-ai) | `abliteration-ai/*` | `ABLIT_KEY` |
14
- | [above.dev](https://mastra.ai/models/providers/above) | `above/*` | `ABOVE_API_KEY` |
15
- | [AgentRouter](https://mastra.ai/models/providers/agentrouter) | `agentrouter/*` | `AGENTROUTER_API_KEY` |
16
- | [Agnes AI](https://mastra.ai/models/providers/agnes) | `agnes/*` | `AGNES_API_KEY` |
17
- | [AI-ROUTER](https://mastra.ai/models/providers/ai-router) | `ai-router/*` | `AI_ROUTER_API_KEY` |
18
- | [ai&](https://mastra.ai/models/providers/aiand) | `aiand/*` | `AIAND_API_KEY` |
19
- | [AI21 Labs](https://mastra.ai/models/providers/ai21) | `ai21/*` | `AI21_API_KEY` |
20
- | [ainetcafe](https://mastra.ai/models/providers/ainetcafe) | `ainetcafe/*` | `AINETCAFE_API_KEY` |
21
- | [Aixy](https://mastra.ai/models/providers/aixy) | `aixy/*` | `AIXY_API_KEY` |
22
- | [AKI.IO](https://mastra.ai/models/providers/aki-io) | `aki-io/*` | `AKI_IO_API_KEY` |
23
- | [Alibaba](https://mastra.ai/models/providers/alibaba) | `alibaba/*` | `DASHSCOPE_API_KEY` |
24
- | [Alibaba (China)](https://mastra.ai/models/providers/alibaba-cn) | `alibaba-cn/*` | `DASHSCOPE_API_KEY` |
25
- | [Alibaba Coding Plan](https://mastra.ai/models/providers/alibaba-coding-plan) | `alibaba-coding-plan/*` | `ALIBABA_CODING_PLAN_API_KEY` |
26
- | [Alibaba Coding Plan (China)](https://mastra.ai/models/providers/alibaba-coding-plan-cn) | `alibaba-coding-plan-cn/*` | `ALIBABA_CODING_PLAN_API_KEY` |
27
- | [Alibaba Token Plan](https://mastra.ai/models/providers/alibaba-token-plan) | `alibaba-token-plan/*` | `ALIBABA_TOKEN_PLAN_API_KEY` |
28
- | [Alibaba Token Plan (China)](https://mastra.ai/models/providers/alibaba-token-plan-cn) | `alibaba-token-plan-cn/*` | `ALIBABA_TOKEN_PLAN_API_KEY` |
29
- | [Ambient](https://mastra.ai/models/providers/ambient) | `ambient/*` | `AMBIENT_API_KEY` |
30
- | [AMD](https://mastra.ai/models/providers/amd) | `amd/*` | `AMD_API_KEY` |
31
- | [Anthropic](https://mastra.ai/models/providers/anthropic) | `anthropic/*` | `ANTHROPIC_API_KEY` |
32
- | [AnyAPI](https://mastra.ai/models/providers/anyapi) | `anyapi/*` | `ANYAPI_API_KEY` |
33
- | [Arcee](https://mastra.ai/models/providers/arcee) | `arcee/*` | `ARCEE_API_KEY` |
34
- | [Atomic Chat](https://mastra.ai/models/providers/atomic-chat) | `atomic-chat/*` | `ATOMIC_CHAT_API_KEY` |
35
- | [Auriko](https://mastra.ai/models/providers/auriko) | `auriko/*` | `AURIKO_API_KEY` |
36
- | [Bailing](https://mastra.ai/models/providers/bailing) | `bailing/*` | `BAILING_API_TOKEN` |
37
- | [Baseten](https://mastra.ai/models/providers/baseten) | `baseten/*` | `BASETEN_API_KEY` |
38
- | [Berget.AI](https://mastra.ai/models/providers/berget) | `berget/*` | `BERGET_API_KEY` |
39
- | [Blue Claw](https://mastra.ai/models/providers/blueclaw) | `blueclaw/*` | `BLUECLAW_API_KEY` |
40
- | [Bothub](https://mastra.ai/models/providers/bothub) | `bothub/*` | `BOTHUB_API_KEY` |
41
- | [Cerebras](https://mastra.ai/models/providers/cerebras) | `cerebras/*` | `CEREBRAS_API_KEY` |
42
- | [Charm Hyper](https://mastra.ai/models/providers/hyper) | `hyper/*` | `HYPER_API_KEY` |
43
- | [Chutes](https://mastra.ai/models/providers/chutes) | `chutes/*` | `CHUTES_API_KEY` |
44
- | [Clarifai](https://mastra.ai/models/providers/clarifai) | `clarifai/*` | `CLARIFAI_PAT` |
45
- | [Claudinio](https://mastra.ai/models/providers/claudinio) | `claudinio/*` | `CLAUDINIO_API_KEY` |
46
- | [ClinePass](https://mastra.ai/models/providers/cline-pass) | `cline-pass/*` | `CLINE_API_KEY` |
47
- | [CloudFerro Sherlock](https://mastra.ai/models/providers/cloudferro-sherlock) | `cloudferro-sherlock/*` | `CLOUDFERRO_SHERLOCK_API_KEY` |
48
- | [Cloudflare Workers AI](https://mastra.ai/models/providers/cloudflare-workers-ai) | `cloudflare-workers-ai/*` | `CLOUDFLARE_ACCOUNT_ID`, `CLOUDFLARE_API_KEY` |
49
- | [CoralBricks](https://mastra.ai/models/providers/coralbricks) | `coralbricks/*` | `CORAL_API_KEY` |
50
- | [CoreWeave](https://mastra.ai/models/providers/wandb) | `wandb/*` | `WANDB_API_KEY` |
51
- | [Cortecs](https://mastra.ai/models/providers/cortecs) | `cortecs/*` | `CORTECS_API_KEY` |
52
- | [CrofAI](https://mastra.ai/models/providers/crof) | `crof/*` | `CROF_API_KEY` |
53
- | [CrossModel](https://mastra.ai/models/providers/crossmodel) | `crossmodel/*` | `CROSSMODEL_API_KEY` |
54
- | [Crusoe](https://mastra.ai/models/providers/crusoe) | `crusoe/*` | `CRUSOE_API_KEY` |
55
- | [D.Run (China)](https://mastra.ai/models/providers/drun) | `drun/*` | `DRUN_API_KEY` |
56
- | [DaoXE](https://mastra.ai/models/providers/daoxe) | `daoxe/*` | `DAOXE_API_KEY` |
57
- | [Databricks](https://mastra.ai/models/providers/databricks) | `databricks/*` | `DATABRICKS_HOST`, `DATABRICKS_TOKEN` |
58
- | [Deep Infra](https://mastra.ai/models/providers/deepinfra) | `deepinfra/*` | `DEEPINFRA_API_KEY` |
59
- | [DeepSeek](https://mastra.ai/models/providers/deepseek) | `deepseek/*` | `DEEPSEEK_API_KEY` |
60
- | [DevPass (LLM Gateway)](https://mastra.ai/models/providers/llmgateway) | `llmgateway/*` | `LLMGATEWAY_API_KEY` |
61
- | [DigitalOcean](https://mastra.ai/models/providers/digitalocean) | `digitalocean/*` | `DIGITALOCEAN_ACCESS_TOKEN` |
62
- | [DInference](https://mastra.ai/models/providers/dinference) | `dinference/*` | `DINFERENCE_API_KEY` |
63
- | [EBCloud](https://mastra.ai/models/providers/ebcloud) | `ebcloud/*` | `EBCLOUD_API_KEY` |
64
- | [Echo](https://mastra.ai/models/providers/echo) | `echo/*` | `ECHO_API_KEY` |
65
- | [Eden AI](https://mastra.ai/models/providers/edenai) | `edenai/*` | `EDENAI_API_KEY` |
66
- | [EmpirioLabs AI](https://mastra.ai/models/providers/empiriolabs) | `empiriolabs/*` | `EMPIRIOLABS_API_KEY` |
67
- | [evroc](https://mastra.ai/models/providers/evroc) | `evroc/*` | `EVROC_API_KEY` |
68
- | [FastRouter](https://mastra.ai/models/providers/fastrouter) | `fastrouter/*` | `FASTROUTER_API_KEY` |
69
- | [Fireworks AI](https://mastra.ai/models/providers/fireworks-ai) | `fireworks-ai/*` | `FIREWORKS_API_KEY` |
70
- | [FreeModel](https://mastra.ai/models/providers/freemodel) | `freemodel/*` | `FREEMODEL_API_KEY` |
71
- | [Friendli](https://mastra.ai/models/providers/friendli) | `friendli/*` | `FRIENDLI_TOKEN` |
72
- | [FrogBot](https://mastra.ai/models/providers/frogbot) | `frogbot/*` | `FROGBOT_API_KEY` |
73
- | [GMI Cloud](https://mastra.ai/models/providers/gmicloud) | `gmicloud/*` | `GMICLOUD_API_KEY` |
74
- | [Google](https://mastra.ai/models/providers/google) | `google/*` | `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY` |
75
- | [GreenPT](https://mastra.ai/models/providers/greenpt) | `greenpt/*` | `GREENPT_API_KEY` |
76
- | [Groq](https://mastra.ai/models/providers/groq) | `groq/*` | `GROQ_API_KEY` |
77
- | [Helicone](https://mastra.ai/models/providers/helicone) | `helicone/*` | `HELICONE_API_KEY` |
78
- | [Hetzner](https://mastra.ai/models/providers/hetzner) | `hetzner/*` | `HETZNER_API_KEY` |
79
- | [HPC-AI](https://mastra.ai/models/providers/hpc-ai) | `hpc-ai/*` | `HPC_AI_API_KEY` |
80
- | [Hugging Face](https://mastra.ai/models/providers/huggingface) | `huggingface/*` | `HF_TOKEN` |
81
- | [iFlow](https://mastra.ai/models/providers/iflowcn) | `iflowcn/*` | `IFLOW_API_KEY` |
82
- | [Impossibl](https://mastra.ai/models/providers/impossibl) | `impossibl/*` | `IMPOSSIBL_API_KEY` |
83
- | [Inception](https://mastra.ai/models/providers/inception) | `inception/*` | `INCEPTION_API_KEY` |
84
- | [Inceptron](https://mastra.ai/models/providers/inceptron) | `inceptron/*` | `INCEPTRON_API_KEY` |
85
- | [Inco](https://mastra.ai/models/providers/inco) | `inco/*` | `INCO_API_KEY` |
86
- | [Infer by Flow7](https://mastra.ai/models/providers/infer) | `infer/*` | `INFER_API_KEY` |
87
- | [Inference](https://mastra.ai/models/providers/inference) | `inference/*` | `INFERENCE_API_KEY` |
88
- | [InferX](https://mastra.ai/models/providers/inferx) | `inferx/*` | `INFERX_API_KEY` |
89
- | [Infomaniak](https://mastra.ai/models/providers/infomaniak) | `infomaniak/*` | `INFOMANIAK_PRODUCT_ID`, `INFOMANIAK_API_KEY` |
90
- | [IO.NET](https://mastra.ai/models/providers/io-net) | `io-net/*` | `IOINTELLIGENCE_API_KEY` |
91
- | [IteraCompute](https://mastra.ai/models/providers/iteracompute) | `iteracompute/*` | `ITERACOMPUTE_API_KEY` |
92
- | [Jalapeno Cloud](https://mastra.ai/models/providers/jalapeno) | `jalapeno/*` | `JALAPENO_API_KEY` |
93
- | [Jiekou.AI](https://mastra.ai/models/providers/jiekou) | `jiekou/*` | `JIEKOU_API_KEY` |
94
- | [Kenari](https://mastra.ai/models/providers/kenari) | `kenari/*` | `KENARI_API_KEY` |
95
- | [Kilo Gateway](https://mastra.ai/models/providers/kilo) | `kilo/*` | `KILO_API_KEY` |
96
- | [Kimi For Coding (kimi.ai)](https://mastra.ai/models/providers/kimi-code-plan-global) | `kimi-code-plan-global/*` | `KIMI_API_KEY` |
97
- | [Kimi For Coding (kimi.com)](https://mastra.ai/models/providers/kimi-code-plan-cn) | `kimi-code-plan-cn/*` | `KIMI_API_KEY` |
98
- | [klokintegration.se](https://mastra.ai/models/providers/klokintegration) | `klokintegration/*` | `KLOKINTEGRATION_API_KEY` |
99
- | [Kosmik Compute](https://mastra.ai/models/providers/kosmik) | `kosmik/*` | `KOSMIK_API_KEY` |
100
- | [KUAE Cloud Coding Plan](https://mastra.ai/models/providers/kuae-cloud-coding-plan) | `kuae-cloud-coding-plan/*` | `KUAE_API_KEY` |
101
- | [Lilac](https://mastra.ai/models/providers/lilac) | `lilac/*` | `LILAC_API_KEY` |
102
- | [Llama](https://mastra.ai/models/providers/llama) | `llama/*` | `LLAMA_API_KEY` |
103
- | [LLM Gateway](https://mastra.ai/models/providers/llmgateway-providers) | `llmgateway-providers/*` | `LLMGATEWAY_API_KEY` |
104
- | [LLM Tech](https://mastra.ai/models/providers/llmtech) | `llmtech/*` | `LLMTECH_API_KEY` |
105
- | [LLMTR](https://mastra.ai/models/providers/llmtr) | `llmtr/*` | `LLMTR_API_KEY` |
106
- | [LMStudio](https://mastra.ai/models/providers/lmstudio) | `lmstudio/*` | `LMSTUDIO_API_KEY` |
107
- | [LongCat](https://mastra.ai/models/providers/longcat) | `longcat/*` | `LONGCAT_API_KEY` |
108
- | [LucidQuery](https://mastra.ai/models/providers/lucidquery) | `lucidquery/*` | `LUCIDQUERY_API_KEY` |
109
- | [Lynkr](https://mastra.ai/models/providers/lynkr) | `lynkr/*` | `LYNKR_API_KEY` |
110
- | [Meganova](https://mastra.ai/models/providers/meganova) | `meganova/*` | `MEGANOVA_API_KEY` |
111
- | [Melious](https://mastra.ai/models/providers/melious) | `melious/*` | `MELIOUS_API_KEY` |
112
- | [Meta](https://mastra.ai/models/providers/meta) | `meta/*` | `META_MODEL_API_KEY` |
113
- | [MiniMax (minimax.io)](https://mastra.ai/models/providers/minimax) | `minimax/*` | `MINIMAX_API_KEY` |
114
- | [MiniMax (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn) | `minimax-cn/*` | `MINIMAX_API_KEY` |
115
- | [MiniMax Token Plan (minimax.io)](https://mastra.ai/models/providers/minimax-coding-plan) | `minimax-coding-plan/*` | `MINIMAX_API_KEY` |
116
- | [MiniMax Token Plan (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn-coding-plan) | `minimax-cn-coding-plan/*` | `MINIMAX_API_KEY` |
117
- | [Mistral](https://mastra.ai/models/providers/mistral) | `mistral/*` | `MISTRAL_API_KEY` |
118
- | [Mixlayer](https://mastra.ai/models/providers/mixlayer) | `mixlayer/*` | `MIXLAYER_API_KEY` |
119
- | [Moark](https://mastra.ai/models/providers/moark) | `moark/*` | `MOARK_API_KEY` |
120
- | [Modal](https://mastra.ai/models/providers/modal) | `modal/*` | `MODAL_PROXY_TOKEN` |
121
- | [Model Oracle AI](https://mastra.ai/models/providers/model-oracle-ai) | `model-oracle-ai/*` | `MODEL_ORACLE_API_KEY` |
122
- | [Modelis](https://mastra.ai/models/providers/modelis) | `modelis/*` | `MODELIS_API_KEY` |
123
- | [ModelScope](https://mastra.ai/models/providers/modelscope) | `modelscope/*` | `MODELSCOPE_API_KEY` |
124
- | [Moonshot AI](https://mastra.ai/models/providers/moonshotai) | `moonshotai/*` | `MOONSHOT_API_KEY` |
125
- | [Moonshot AI (China)](https://mastra.ai/models/providers/moonshotai-cn) | `moonshotai-cn/*` | `MOONSHOT_API_KEY` |
126
- | [Morph](https://mastra.ai/models/providers/morph) | `morph/*` | `MORPH_API_KEY` |
127
- | [NaN](https://mastra.ai/models/providers/nan) | `nan/*` | `NAN_API_KEY` |
128
- | [NanoGPT](https://mastra.ai/models/providers/nano-gpt) | `nano-gpt/*` | `NANO_GPT_API_KEY` |
129
- | [NEAR AI Cloud](https://mastra.ai/models/providers/nearai) | `nearai/*` | `NEARAI_API_KEY` |
130
- | [Nebius Token Factory](https://mastra.ai/models/providers/nebius) | `nebius/*` | `NEBIUS_API_KEY` |
131
- | [NeoSmith](https://mastra.ai/models/providers/neosmith) | `neosmith/*` | `NEOSMITH_API_KEY` |
132
- | [Neuralwatt](https://mastra.ai/models/providers/neuralwatt) | `neuralwatt/*` | `NEURALWATT_API_KEY` |
133
- | [Nova](https://mastra.ai/models/providers/nova) | `nova/*` | `NOVA_API_KEY` |
134
- | [NovitaAI](https://mastra.ai/models/providers/novita-ai) | `novita-ai/*` | `NOVITA_API_KEY` |
135
- | [Nvidia](https://mastra.ai/models/providers/nvidia) | `nvidia/*` | `NVIDIA_API_KEY` |
136
- | [OCI Generative AI](https://mastra.ai/models/providers/oci) | `oci/*` | `OCI_GENAI_API_KEY` |
137
- | [Ofox](https://mastra.ai/models/providers/ofox) | `ofox/*` | `OFOX_API_KEY` |
138
- | [Ollama Cloud](https://mastra.ai/models/providers/ollama-cloud) | `ollama-cloud/*` | `OLLAMA_API_KEY` |
139
- | [OpenAI](https://mastra.ai/models/providers/openai) | `openai/*` | `OPENAI_API_KEY` |
140
- | [OpenCode Go](https://mastra.ai/models/providers/opencode-go) | `opencode-go/*` | `OPENCODE_API_KEY` |
141
- | [OpenCode Zen](https://mastra.ai/models/providers/opencode) | `opencode/*` | `OPENCODE_API_KEY` |
142
- | [OpenReason](https://mastra.ai/models/providers/openreason) | `openreason/*` | `OPENREASON_API_KEY` |
143
- | [Opper](https://mastra.ai/models/providers/opper) | `opper/*` | `OPPER_API_KEY` |
144
- | [OrcaRouter](https://mastra.ai/models/providers/orcarouter) | `orcarouter/*` | `ORCAROUTER_API_KEY` |
145
- | [OVHcloud AI Endpoints](https://mastra.ai/models/providers/ovhcloud) | `ovhcloud/*` | `OVHCLOUD_API_KEY` |
146
- | [Pendra](https://mastra.ai/models/providers/pendra) | `pendra/*` | `PENDRA_API_KEY` |
147
- | [Perplexity](https://mastra.ai/models/providers/perplexity) | `perplexity/*` | `PERPLEXITY_API_KEY` |
148
- | [Perplexity Agent](https://mastra.ai/models/providers/perplexity-agent) | `perplexity-agent/*` | `PERPLEXITY_API_KEY` |
149
- | [Pioneer](https://mastra.ai/models/providers/pioneer) | `pioneer/*` | `PIONEER_API_KEY` |
150
- | [Poe](https://mastra.ai/models/providers/poe) | `poe/*` | `POE_API_KEY` |
151
- | [Poolside](https://mastra.ai/models/providers/poolside) | `poolside/*` | `POOLSIDE_API_KEY` |
152
- | [Privatemode AI](https://mastra.ai/models/providers/privatemode-ai) | `privatemode-ai/*` | `PRIVATEMODE_API_KEY` |
153
- | [QiHang](https://mastra.ai/models/providers/qihang-ai) | `qihang-ai/*` | `QIHANG_API_KEY` |
154
- | [Qiniu](https://mastra.ai/models/providers/qiniu-ai) | `qiniu-ai/*` | `QINIU_API_KEY` |
155
- | [Regolo AI](https://mastra.ai/models/providers/regolo-ai) | `regolo-ai/*` | `REGOLO_API_KEY` |
156
- | [Requesty](https://mastra.ai/models/providers/requesty) | `requesty/*` | `REQUESTY_API_KEY` |
157
- | [routing.run](https://mastra.ai/models/providers/routing-run) | `routing-run/*` | `ROUTING_RUN_API_KEY` |
158
- | [RunInfra](https://mastra.ai/models/providers/runinfra) | `runinfra/*` | `RUNINFRA_GATEWAY_KEY` |
159
- | [Sakana AI](https://mastra.ai/models/providers/sakana) | `sakana/*` | `SAKANA_API_KEY` |
160
- | [Sarvam AI](https://mastra.ai/models/providers/sarvam) | `sarvam/*` | `SARVAM_API_KEY` |
161
- | [Scaleway](https://mastra.ai/models/providers/scaleway) | `scaleway/*` | `SCALEWAY_API_KEY` |
162
- | [SCNet Token Plan](https://mastra.ai/models/providers/scnet-token-plan) | `scnet-token-plan/*` | `SCNET_API_KEY` |
163
- | [SCX.ai](https://mastra.ai/models/providers/scx-ai) | `scx-ai/*` | `SCX_API_KEY` |
164
- | [SenseNova (China)](https://mastra.ai/models/providers/sensenova) | `sensenova/*` | `SENSENOVA_API_KEY` |
165
- | [SiliconFlow](https://mastra.ai/models/providers/siliconflow) | `siliconflow/*` | `SILICONFLOW_API_KEY` |
166
- | [SiliconFlow (China)](https://mastra.ai/models/providers/siliconflow-cn) | `siliconflow-cn/*` | `SILICONFLOW_CN_API_KEY` |
167
- | [Snowflake Cortex](https://mastra.ai/models/providers/snowflake-cortex) | `snowflake-cortex/*` | `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_CORTEX_PAT` |
168
- | [STACKIT](https://mastra.ai/models/providers/stackit) | `stackit/*` | `STACKIT_API_KEY` |
169
- | [Standard Compute](https://mastra.ai/models/providers/standardcompute) | `standardcompute/*` | `STANDARDCOMPUTE_API_KEY` |
170
- | [StepFun (China)](https://mastra.ai/models/providers/stepfun) | `stepfun/*` | `STEPFUN_API_KEY` |
171
- | [StepFun (Global)](https://mastra.ai/models/providers/stepfun-ai) | `stepfun-ai/*` | `STEPFUN_API_KEY` |
172
- | [StepFun Step Plan (China)](https://mastra.ai/models/providers/stepfun-step-plan) | `stepfun-step-plan/*` | `STEPFUN_API_KEY` |
173
- | [StepFun Step Plan (Global)](https://mastra.ai/models/providers/stepfun-ai-step-plan) | `stepfun-ai-step-plan/*` | `STEPFUN_API_KEY` |
174
- | [Subconscious](https://mastra.ai/models/providers/subconscious) | `subconscious/*` | `SUBCONSCIOUS_API_KEY` |
175
- | [submodel](https://mastra.ai/models/providers/submodel) | `submodel/*` | `SUBMODEL_INSTAGEN_ACCESS_KEY` |
176
- | [Synthetic](https://mastra.ai/models/providers/synthetic) | `synthetic/*` | `SYNTHETIC_API_KEY` |
177
- | [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan) | `tencent-coding-plan/*` | `TENCENT_CODING_PLAN_API_KEY` |
178
- | [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan) | `tencent-token-plan/*` | `TENCENT_TOKEN_PLAN_API_KEY` |
179
- | [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub) | `tencent-tokenhub/*` | `TENCENT_TOKENHUB_API_KEY` |
180
- | [TensorX](https://mastra.ai/models/providers/tensorx) | `tensorx/*` | `TENSORX_API_KEY` |
181
- | [The Grid AI](https://mastra.ai/models/providers/the-grid-ai) | `the-grid-ai/*` | `THEGRID_API_KEY` |
182
- | [Thinking Machines](https://mastra.ai/models/providers/thinkingmachines) | `thinkingmachines/*` | `TINKER_API_KEY` |
183
- | [Tinfoil](https://mastra.ai/models/providers/tinfoil) | `tinfoil/*` | `TINFOIL_API_KEY` |
184
- | [Together AI](https://mastra.ai/models/providers/togetherai) | `togetherai/*` | `TOGETHER_API_KEY` |
185
- | [TokenGo](https://mastra.ai/models/providers/tokengo) | `tokengo/*` | `TOKENGO_API_KEY` |
186
- | [TokenRouter](https://mastra.ai/models/providers/tokenrouter) | `tokenrouter/*` | `TOKENROUTER_API_KEY` |
187
- | [TrustedRouter](https://mastra.ai/models/providers/trustedrouter) | `trustedrouter/*` | `TRUSTEDROUTER_API_KEY` |
188
- | [Umans AI](https://mastra.ai/models/providers/umans-ai) | `umans-ai/*` | `UMANS_AI_API_KEY` |
189
- | [Umans AI Coding Plan](https://mastra.ai/models/providers/umans-ai-coding-plan) | `umans-ai-coding-plan/*` | `UMANS_AI_CODING_PLAN_API_KEY` |
190
- | [UnoRouter](https://mastra.ai/models/providers/unorouter) | `unorouter/*` | `UNOROUTER_API_KEY` |
191
- | [Upstage](https://mastra.ai/models/providers/upstage) | `upstage/*` | `UPSTAGE_API_KEY` |
192
- | [Vancine](https://mastra.ai/models/providers/vancine) | `vancine/*` | `VANCINE_API_KEY` |
193
- | [Vispark](https://mastra.ai/models/providers/vispark) | `vispark/*` | `VISPARK_LAB_API_KEY` |
194
- | [Vivgrid](https://mastra.ai/models/providers/vivgrid) | `vivgrid/*` | `VIVGRID_API_KEY` |
195
- | [Volcengine Ark](https://mastra.ai/models/providers/volcengine) | `volcengine/*` | `ARK_API_KEY` |
196
- | [Volcengine Ark Coding Plan](https://mastra.ai/models/providers/volcengine-coding-plan) | `volcengine-coding-plan/*` | `ARK_CODING_PLAN_API_KEY` |
197
- | [Vultr](https://mastra.ai/models/providers/vultr) | `vultr/*` | `VULTR_API_KEY` |
198
- | [Wafer](https://mastra.ai/models/providers/wafer.ai) | `wafer.ai/*` | `WAFER_API_KEY` |
199
- | [Wallaby](https://mastra.ai/models/providers/wallaby) | `wallaby/*` | `WALLABY_API_KEY` |
200
- | [xAI](https://mastra.ai/models/providers/xai) | `xai/*` | `XAI_API_KEY` |
201
- | [Xiaomi](https://mastra.ai/models/providers/xiaomi) | `xiaomi/*` | `XIAOMI_API_KEY` |
202
- | [Xiaomi Token Plan (China)](https://mastra.ai/models/providers/xiaomi-token-plan-cn) | `xiaomi-token-plan-cn/*` | `XIAOMI_API_KEY` |
203
- | [Xiaomi Token Plan (Europe)](https://mastra.ai/models/providers/xiaomi-token-plan-ams) | `xiaomi-token-plan-ams/*` | `XIAOMI_API_KEY` |
204
- | [Xiaomi Token Plan (Singapore)](https://mastra.ai/models/providers/xiaomi-token-plan-sgp) | `xiaomi-token-plan-sgp/*` | `XIAOMI_API_KEY` |
205
- | [Xpersona](https://mastra.ai/models/providers/xpersona) | `xpersona/*` | `XPERSONA_API_KEY` |
206
- | [Z.AI](https://mastra.ai/models/providers/zai) | `zai/*` | `ZHIPU_API_KEY` |
207
- | [Z.AI Coding Plan](https://mastra.ai/models/providers/zai-coding-plan) | `zai-coding-plan/*` | `ZHIPU_API_KEY` |
208
- | [Zeldoc](https://mastra.ai/models/providers/zeldoc) | `zeldoc/*` | `ZELDOC_API_KEY` |
209
- | [Zenifra](https://mastra.ai/models/providers/zenifra) | `zenifra/*` | `ZENIFRA_AI_KEY` |
210
- | [ZenMux](https://mastra.ai/models/providers/zenmux) | `zenmux/*` | `ZENMUX_API_KEY` |
211
- | [Zhipu AI](https://mastra.ai/models/providers/zhipuai) | `zhipuai/*` | `ZHIPU_API_KEY` |
212
- | [Zhipu AI Coding Plan](https://mastra.ai/models/providers/zhipuai-coding-plan) | `zhipuai-coding-plan/*` | `ZHIPU_API_KEY` |
213
- | [Azure OpenAI](https://mastra.ai/models/gateways/azure-openai) (Gateway) | `azure-openai/*` | `AZURE_API_KEY`, `AZURE_TENANT_ID`, `AZURE_CLIENT_ID`, `AZURE_CLIENT_SECRET`, `AZURE_SUBSCRIPTION_ID` |
214
- | [Mastra](https://mastra.ai/models/gateways/mastra) (Gateway) | `mastra/*` | `MASTRA_GATEWAY_API_KEY` |
215
- | [Merge Gateway](https://mastra.ai/models/gateways/merge-gateway) (Gateway) | `merge-gateway/*` | `MERGE_GATEWAY_API_KEY` |
216
- | [Neon](https://mastra.ai/models/gateways/neon) (Gateway) | `neon/*` | `NEON_AI_GATEWAY_BASE_URL`, `NEON_AI_GATEWAY_TOKEN` |
217
- | [Netlify](https://mastra.ai/models/gateways/netlify) (Gateway) | `netlify/*` | `NETLIFY_TOKEN`, `NETLIFY_SITE_ID` |
218
- | [OpenRouter](https://mastra.ai/models/gateways/openrouter) (Gateway) | `openrouter/*` | `OPENROUTER_API_KEY` |
219
- | [Vercel](https://mastra.ai/models/gateways/vercel) (Gateway) | `vercel/*` | `AI_GATEWAY_API_KEY` |
9
+ | Name | Model prefix | Environment variables |
10
+ | -------------------------------------------------------------------------------------------- | -------------------------- | ----------------------------------------------------------------------------------------------------- |
11
+ | [302.AI](https://mastra.ai/models/providers/302ai) | `302ai/*` | `302AI_API_KEY` |
12
+ | [Abacus](https://mastra.ai/models/providers/abacus) | `abacus/*` | `ABACUS_API_KEY` |
13
+ | [abliteration.ai](https://mastra.ai/models/providers/abliteration-ai) | `abliteration-ai/*` | `ABLIT_KEY` |
14
+ | [above.dev](https://mastra.ai/models/providers/above) | `above/*` | `ABOVE_API_KEY` |
15
+ | [AgentRouter](https://mastra.ai/models/providers/agentrouter) | `agentrouter/*` | `AGENTROUTER_API_KEY` |
16
+ | [Agnes AI](https://mastra.ai/models/providers/agnes) | `agnes/*` | `AGNES_API_KEY` |
17
+ | [AI-ROUTER](https://mastra.ai/models/providers/ai-router) | `ai-router/*` | `AI_ROUTER_API_KEY` |
18
+ | [ai&](https://mastra.ai/models/providers/aiand) | `aiand/*` | `AIAND_API_KEY` |
19
+ | [AI21 Labs](https://mastra.ai/models/providers/ai21) | `ai21/*` | `AI21_API_KEY` |
20
+ | [ainetcafe](https://mastra.ai/models/providers/ainetcafe) | `ainetcafe/*` | `AINETCAFE_API_KEY` |
21
+ | [Aixy](https://mastra.ai/models/providers/aixy) | `aixy/*` | `AIXY_API_KEY` |
22
+ | [AKI.IO](https://mastra.ai/models/providers/aki-io) | `aki-io/*` | `AKI_IO_API_KEY` |
23
+ | [Alibaba](https://mastra.ai/models/providers/alibaba) | `alibaba/*` | `DASHSCOPE_API_KEY` |
24
+ | [Alibaba (China)](https://mastra.ai/models/providers/alibaba-cn) | `alibaba-cn/*` | `DASHSCOPE_API_KEY` |
25
+ | [Alibaba Coding Plan](https://mastra.ai/models/providers/alibaba-coding-plan) | `alibaba-coding-plan/*` | `ALIBABA_CODING_PLAN_API_KEY` |
26
+ | [Alibaba Coding Plan (China)](https://mastra.ai/models/providers/alibaba-coding-plan-cn) | `alibaba-coding-plan-cn/*` | `ALIBABA_CODING_PLAN_API_KEY` |
27
+ | [Alibaba Token Plan](https://mastra.ai/models/providers/alibaba-token-plan) | `alibaba-token-plan/*` | `ALIBABA_TOKEN_PLAN_API_KEY` |
28
+ | [Alibaba Token Plan (China)](https://mastra.ai/models/providers/alibaba-token-plan-cn) | `alibaba-token-plan-cn/*` | `ALIBABA_TOKEN_PLAN_API_KEY` |
29
+ | [Ambient](https://mastra.ai/models/providers/ambient) | `ambient/*` | `AMBIENT_API_KEY` |
30
+ | [AMD](https://mastra.ai/models/providers/amd) | `amd/*` | `AMD_API_KEY` |
31
+ | [Anthropic](https://mastra.ai/models/providers/anthropic) | `anthropic/*` | `ANTHROPIC_API_KEY` |
32
+ | [AnyAPI](https://mastra.ai/models/providers/anyapi) | `anyapi/*` | `ANYAPI_API_KEY` |
33
+ | [Arcee](https://mastra.ai/models/providers/arcee) | `arcee/*` | `ARCEE_API_KEY` |
34
+ | [Atomic Chat](https://mastra.ai/models/providers/atomic-chat) | `atomic-chat/*` | `ATOMIC_CHAT_API_KEY` |
35
+ | [Auriko](https://mastra.ai/models/providers/auriko) | `auriko/*` | `AURIKO_API_KEY` |
36
+ | [Bailing](https://mastra.ai/models/providers/bailing) | `bailing/*` | `BAILING_API_TOKEN` |
37
+ | [Baseten](https://mastra.ai/models/providers/baseten) | `baseten/*` | `BASETEN_API_KEY` |
38
+ | [Berget.AI](https://mastra.ai/models/providers/berget) | `berget/*` | `BERGET_API_KEY` |
39
+ | [Blue Claw](https://mastra.ai/models/providers/blueclaw) | `blueclaw/*` | `BLUECLAW_API_KEY` |
40
+ | [Bothub](https://mastra.ai/models/providers/bothub) | `bothub/*` | `BOTHUB_API_KEY` |
41
+ | [Cerebras](https://mastra.ai/models/providers/cerebras) | `cerebras/*` | `CEREBRAS_API_KEY` |
42
+ | [Charm Hyper](https://mastra.ai/models/providers/hyper) | `hyper/*` | `HYPER_API_KEY` |
43
+ | [Chutes](https://mastra.ai/models/providers/chutes) | `chutes/*` | `CHUTES_API_KEY` |
44
+ | [Clarifai](https://mastra.ai/models/providers/clarifai) | `clarifai/*` | `CLARIFAI_PAT` |
45
+ | [Claudinio](https://mastra.ai/models/providers/claudinio) | `claudinio/*` | `CLAUDINIO_API_KEY` |
46
+ | [ClinePass](https://mastra.ai/models/providers/cline-pass) | `cline-pass/*` | `CLINE_API_KEY` |
47
+ | [CloudFerro Sherlock](https://mastra.ai/models/providers/cloudferro-sherlock) | `cloudferro-sherlock/*` | `CLOUDFERRO_SHERLOCK_API_KEY` |
48
+ | [Cloudflare Workers AI](https://mastra.ai/models/providers/cloudflare-workers-ai) | `cloudflare-workers-ai/*` | `CLOUDFLARE_ACCOUNT_ID`, `CLOUDFLARE_API_KEY` |
49
+ | [CoralBricks](https://mastra.ai/models/providers/coralbricks) | `coralbricks/*` | `CORAL_API_KEY` |
50
+ | [CoreWeave](https://mastra.ai/models/providers/wandb) | `wandb/*` | `WANDB_API_KEY` |
51
+ | [Cortecs](https://mastra.ai/models/providers/cortecs) | `cortecs/*` | `CORTECS_API_KEY` |
52
+ | [CrofAI](https://mastra.ai/models/providers/crof) | `crof/*` | `CROF_API_KEY` |
53
+ | [CrossModel](https://mastra.ai/models/providers/crossmodel) | `crossmodel/*` | `CROSSMODEL_API_KEY` |
54
+ | [Crusoe](https://mastra.ai/models/providers/crusoe) | `crusoe/*` | `CRUSOE_API_KEY` |
55
+ | [D.Run (China)](https://mastra.ai/models/providers/drun) | `drun/*` | `DRUN_API_KEY` |
56
+ | [DaoXE](https://mastra.ai/models/providers/daoxe) | `daoxe/*` | `DAOXE_API_KEY` |
57
+ | [Databricks](https://mastra.ai/models/providers/databricks) | `databricks/*` | `DATABRICKS_HOST`, `DATABRICKS_TOKEN` |
58
+ | [Deep Infra](https://mastra.ai/models/providers/deepinfra) | `deepinfra/*` | `DEEPINFRA_API_KEY` |
59
+ | [DeepSeek](https://mastra.ai/models/providers/deepseek) | `deepseek/*` | `DEEPSEEK_API_KEY` |
60
+ | [DevPass (LLM Gateway)](https://mastra.ai/models/providers/llmgateway) | `llmgateway/*` | `LLMGATEWAY_API_KEY` |
61
+ | [DigitalOcean](https://mastra.ai/models/providers/digitalocean) | `digitalocean/*` | `DIGITALOCEAN_ACCESS_TOKEN` |
62
+ | [DInference](https://mastra.ai/models/providers/dinference) | `dinference/*` | `DINFERENCE_API_KEY` |
63
+ | [EBCloud](https://mastra.ai/models/providers/ebcloud) | `ebcloud/*` | `EBCLOUD_API_KEY` |
64
+ | [Echo](https://mastra.ai/models/providers/echo) | `echo/*` | `ECHO_API_KEY` |
65
+ | [Eden AI](https://mastra.ai/models/providers/edenai) | `edenai/*` | `EDENAI_API_KEY` |
66
+ | [EmpirioLabs AI](https://mastra.ai/models/providers/empiriolabs) | `empiriolabs/*` | `EMPIRIOLABS_API_KEY` |
67
+ | [evroc](https://mastra.ai/models/providers/evroc) | `evroc/*` | `EVROC_API_KEY` |
68
+ | [FastRouter](https://mastra.ai/models/providers/fastrouter) | `fastrouter/*` | `FASTROUTER_API_KEY` |
69
+ | [Fireworks AI](https://mastra.ai/models/providers/fireworks-ai) | `fireworks-ai/*` | `FIREWORKS_API_KEY` |
70
+ | [FreeModel](https://mastra.ai/models/providers/freemodel) | `freemodel/*` | `FREEMODEL_API_KEY` |
71
+ | [Friendli](https://mastra.ai/models/providers/friendli) | `friendli/*` | `FRIENDLI_TOKEN` |
72
+ | [FrogBot](https://mastra.ai/models/providers/frogbot) | `frogbot/*` | `FROGBOT_API_KEY` |
73
+ | [GMI Cloud](https://mastra.ai/models/providers/gmicloud) | `gmicloud/*` | `GMICLOUD_API_KEY` |
74
+ | [Google](https://mastra.ai/models/providers/google) | `google/*` | `GOOGLE_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY` |
75
+ | [GreenPT](https://mastra.ai/models/providers/greenpt) | `greenpt/*` | `GREENPT_API_KEY` |
76
+ | [Groq](https://mastra.ai/models/providers/groq) | `groq/*` | `GROQ_API_KEY` |
77
+ | [Helicone](https://mastra.ai/models/providers/helicone) | `helicone/*` | `HELICONE_API_KEY` |
78
+ | [Hetzner](https://mastra.ai/models/providers/hetzner) | `hetzner/*` | `HETZNER_API_KEY` |
79
+ | [HPC-AI](https://mastra.ai/models/providers/hpc-ai) | `hpc-ai/*` | `HPC_AI_API_KEY` |
80
+ | [Hugging Face](https://mastra.ai/models/providers/huggingface) | `huggingface/*` | `HF_TOKEN` |
81
+ | [iFlow](https://mastra.ai/models/providers/iflowcn) | `iflowcn/*` | `IFLOW_API_KEY` |
82
+ | [Impossibl](https://mastra.ai/models/providers/impossibl) | `impossibl/*` | `IMPOSSIBL_API_KEY` |
83
+ | [Inception](https://mastra.ai/models/providers/inception) | `inception/*` | `INCEPTION_API_KEY` |
84
+ | [Inceptron](https://mastra.ai/models/providers/inceptron) | `inceptron/*` | `INCEPTRON_API_KEY` |
85
+ | [Inco](https://mastra.ai/models/providers/inco) | `inco/*` | `INCO_API_KEY` |
86
+ | [Infer by Flow7](https://mastra.ai/models/providers/infer) | `infer/*` | `INFER_API_KEY` |
87
+ | [Inference](https://mastra.ai/models/providers/inference) | `inference/*` | `INFERENCE_API_KEY` |
88
+ | [InferX](https://mastra.ai/models/providers/inferx) | `inferx/*` | `INFERX_API_KEY` |
89
+ | [Infomaniak](https://mastra.ai/models/providers/infomaniak) | `infomaniak/*` | `INFOMANIAK_PRODUCT_ID`, `INFOMANIAK_API_KEY` |
90
+ | [IO.NET](https://mastra.ai/models/providers/io-net) | `io-net/*` | `IOINTELLIGENCE_API_KEY` |
91
+ | [IteraCompute](https://mastra.ai/models/providers/iteracompute) | `iteracompute/*` | `ITERACOMPUTE_API_KEY` |
92
+ | [Jalapeno Cloud](https://mastra.ai/models/providers/jalapeno) | `jalapeno/*` | `JALAPENO_API_KEY` |
93
+ | [Jiekou.AI](https://mastra.ai/models/providers/jiekou) | `jiekou/*` | `JIEKOU_API_KEY` |
94
+ | [Kenari](https://mastra.ai/models/providers/kenari) | `kenari/*` | `KENARI_API_KEY` |
95
+ | [Kilo Gateway](https://mastra.ai/models/providers/kilo) | `kilo/*` | `KILO_API_KEY` |
96
+ | [Kimi For Coding (kimi.ai)](https://mastra.ai/models/providers/kimi-code-plan-global) | `kimi-code-plan-global/*` | `KIMI_API_KEY` |
97
+ | [Kimi For Coding (kimi.com)](https://mastra.ai/models/providers/kimi-code-plan-cn) | `kimi-code-plan-cn/*` | `KIMI_API_KEY` |
98
+ | [klokintegration.se](https://mastra.ai/models/providers/klokintegration) | `klokintegration/*` | `KLOKINTEGRATION_API_KEY` |
99
+ | [Kosmik Compute](https://mastra.ai/models/providers/kosmik) | `kosmik/*` | `KOSMIK_API_KEY` |
100
+ | [KUAE Cloud Coding Plan](https://mastra.ai/models/providers/kuae-cloud-coding-plan) | `kuae-cloud-coding-plan/*` | `KUAE_API_KEY` |
101
+ | [Lilac](https://mastra.ai/models/providers/lilac) | `lilac/*` | `LILAC_API_KEY` |
102
+ | [Llama](https://mastra.ai/models/providers/llama) | `llama/*` | `LLAMA_API_KEY` |
103
+ | [LLM Gateway](https://mastra.ai/models/providers/llmgateway-providers) | `llmgateway-providers/*` | `LLMGATEWAY_API_KEY` |
104
+ | [LLM Tech](https://mastra.ai/models/providers/llmtech) | `llmtech/*` | `LLMTECH_API_KEY` |
105
+ | [LLMTR](https://mastra.ai/models/providers/llmtr) | `llmtr/*` | `LLMTR_API_KEY` |
106
+ | [LMStudio](https://mastra.ai/models/providers/lmstudio) | `lmstudio/*` | `LMSTUDIO_API_KEY` |
107
+ | [LongCat](https://mastra.ai/models/providers/longcat) | `longcat/*` | `LONGCAT_API_KEY` |
108
+ | [LucidQuery](https://mastra.ai/models/providers/lucidquery) | `lucidquery/*` | `LUCIDQUERY_API_KEY` |
109
+ | [Lynkr](https://mastra.ai/models/providers/lynkr) | `lynkr/*` | `LYNKR_API_KEY` |
110
+ | [Meganova](https://mastra.ai/models/providers/meganova) | `meganova/*` | `MEGANOVA_API_KEY` |
111
+ | [Melious](https://mastra.ai/models/providers/melious) | `melious/*` | `MELIOUS_API_KEY` |
112
+ | [Meta](https://mastra.ai/models/providers/meta) | `meta/*` | `META_MODEL_API_KEY` |
113
+ | [MiniMax (minimax.cn)](https://mastra.ai/models/providers/minimax-cn) | `minimax-cn/*` | `MINIMAX_API_KEY` |
114
+ | [MiniMax (minimax.io)](https://mastra.ai/models/providers/minimax) | `minimax/*` | `MINIMAX_API_KEY` |
115
+ | [MiniMax Token Plan (minimax.cn)](https://mastra.ai/models/providers/minimax-cn-coding-plan) | `minimax-cn-coding-plan/*` | `MINIMAX_API_KEY` |
116
+ | [MiniMax Token Plan (minimax.io)](https://mastra.ai/models/providers/minimax-coding-plan) | `minimax-coding-plan/*` | `MINIMAX_API_KEY` |
117
+ | [Mistral](https://mastra.ai/models/providers/mistral) | `mistral/*` | `MISTRAL_API_KEY` |
118
+ | [Mixlayer](https://mastra.ai/models/providers/mixlayer) | `mixlayer/*` | `MIXLAYER_API_KEY` |
119
+ | [Moark](https://mastra.ai/models/providers/moark) | `moark/*` | `MOARK_API_KEY` |
120
+ | [Modal](https://mastra.ai/models/providers/modal) | `modal/*` | `MODAL_PROXY_TOKEN` |
121
+ | [Model Oracle AI](https://mastra.ai/models/providers/model-oracle-ai) | `model-oracle-ai/*` | `MODEL_ORACLE_API_KEY` |
122
+ | [Modelis](https://mastra.ai/models/providers/modelis) | `modelis/*` | `MODELIS_API_KEY` |
123
+ | [ModelScope](https://mastra.ai/models/providers/modelscope) | `modelscope/*` | `MODELSCOPE_API_KEY` |
124
+ | [Moonshot AI](https://mastra.ai/models/providers/moonshotai) | `moonshotai/*` | `MOONSHOT_API_KEY` |
125
+ | [Moonshot AI (China)](https://mastra.ai/models/providers/moonshotai-cn) | `moonshotai-cn/*` | `MOONSHOT_API_KEY` |
126
+ | [Morph](https://mastra.ai/models/providers/morph) | `morph/*` | `MORPH_API_KEY` |
127
+ | [NaN](https://mastra.ai/models/providers/nan) | `nan/*` | `NAN_API_KEY` |
128
+ | [NanoGPT](https://mastra.ai/models/providers/nano-gpt) | `nano-gpt/*` | `NANO_GPT_API_KEY` |
129
+ | [NEAR AI Cloud](https://mastra.ai/models/providers/nearai) | `nearai/*` | `NEARAI_API_KEY` |
130
+ | [Nebius Token Factory](https://mastra.ai/models/providers/nebius) | `nebius/*` | `NEBIUS_API_KEY` |
131
+ | [NeoSmith](https://mastra.ai/models/providers/neosmith) | `neosmith/*` | `NEOSMITH_API_KEY` |
132
+ | [Neuralwatt](https://mastra.ai/models/providers/neuralwatt) | `neuralwatt/*` | `NEURALWATT_API_KEY` |
133
+ | [Nova](https://mastra.ai/models/providers/nova) | `nova/*` | `NOVA_API_KEY` |
134
+ | [NovitaAI](https://mastra.ai/models/providers/novita-ai) | `novita-ai/*` | `NOVITA_API_KEY` |
135
+ | [Nvidia](https://mastra.ai/models/providers/nvidia) | `nvidia/*` | `NVIDIA_API_KEY` |
136
+ | [OCI Generative AI](https://mastra.ai/models/providers/oci) | `oci/*` | `OCI_GENAI_API_KEY` |
137
+ | [Ofox](https://mastra.ai/models/providers/ofox) | `ofox/*` | `OFOX_API_KEY` |
138
+ | [Ollama Cloud](https://mastra.ai/models/providers/ollama-cloud) | `ollama-cloud/*` | `OLLAMA_API_KEY` |
139
+ | [OpenAI](https://mastra.ai/models/providers/openai) | `openai/*` | `OPENAI_API_KEY` |
140
+ | [OpenCode Go](https://mastra.ai/models/providers/opencode-go) | `opencode-go/*` | `OPENCODE_API_KEY` |
141
+ | [OpenCode Zen](https://mastra.ai/models/providers/opencode) | `opencode/*` | `OPENCODE_API_KEY` |
142
+ | [OpenReason](https://mastra.ai/models/providers/openreason) | `openreason/*` | `OPENREASON_API_KEY` |
143
+ | [Opper](https://mastra.ai/models/providers/opper) | `opper/*` | `OPPER_API_KEY` |
144
+ | [OrcaRouter](https://mastra.ai/models/providers/orcarouter) | `orcarouter/*` | `ORCAROUTER_API_KEY` |
145
+ | [OVHcloud AI Endpoints](https://mastra.ai/models/providers/ovhcloud) | `ovhcloud/*` | `OVHCLOUD_API_KEY` |
146
+ | [Pendra](https://mastra.ai/models/providers/pendra) | `pendra/*` | `PENDRA_API_KEY` |
147
+ | [Perplexity](https://mastra.ai/models/providers/perplexity) | `perplexity/*` | `PERPLEXITY_API_KEY` |
148
+ | [Perplexity Agent](https://mastra.ai/models/providers/perplexity-agent) | `perplexity-agent/*` | `PERPLEXITY_API_KEY` |
149
+ | [Pioneer](https://mastra.ai/models/providers/pioneer) | `pioneer/*` | `PIONEER_API_KEY` |
150
+ | [Poe](https://mastra.ai/models/providers/poe) | `poe/*` | `POE_API_KEY` |
151
+ | [Poolside](https://mastra.ai/models/providers/poolside) | `poolside/*` | `POOLSIDE_API_KEY` |
152
+ | [Privatemode AI](https://mastra.ai/models/providers/privatemode-ai) | `privatemode-ai/*` | `PRIVATEMODE_API_KEY` |
153
+ | [QiHang](https://mastra.ai/models/providers/qihang-ai) | `qihang-ai/*` | `QIHANG_API_KEY` |
154
+ | [Qiniu](https://mastra.ai/models/providers/qiniu-ai) | `qiniu-ai/*` | `QINIU_API_KEY` |
155
+ | [Regolo AI](https://mastra.ai/models/providers/regolo-ai) | `regolo-ai/*` | `REGOLO_API_KEY` |
156
+ | [Requesty](https://mastra.ai/models/providers/requesty) | `requesty/*` | `REQUESTY_API_KEY` |
157
+ | [routing.run](https://mastra.ai/models/providers/routing-run) | `routing-run/*` | `ROUTING_RUN_API_KEY` |
158
+ | [RunInfra](https://mastra.ai/models/providers/runinfra) | `runinfra/*` | `RUNINFRA_GATEWAY_KEY` |
159
+ | [Sakana AI](https://mastra.ai/models/providers/sakana) | `sakana/*` | `SAKANA_API_KEY` |
160
+ | [Sarvam AI](https://mastra.ai/models/providers/sarvam) | `sarvam/*` | `SARVAM_API_KEY` |
161
+ | [Scaleway](https://mastra.ai/models/providers/scaleway) | `scaleway/*` | `SCALEWAY_API_KEY` |
162
+ | [SCNet Token Plan](https://mastra.ai/models/providers/scnet-token-plan) | `scnet-token-plan/*` | `SCNET_API_KEY` |
163
+ | [SCX.ai](https://mastra.ai/models/providers/scx-ai) | `scx-ai/*` | `SCX_API_KEY` |
164
+ | [SenseNova (China)](https://mastra.ai/models/providers/sensenova) | `sensenova/*` | `SENSENOVA_API_KEY` |
165
+ | [SiliconFlow](https://mastra.ai/models/providers/siliconflow) | `siliconflow/*` | `SILICONFLOW_API_KEY` |
166
+ | [SiliconFlow (China)](https://mastra.ai/models/providers/siliconflow-cn) | `siliconflow-cn/*` | `SILICONFLOW_CN_API_KEY` |
167
+ | [Snowflake Cortex](https://mastra.ai/models/providers/snowflake-cortex) | `snowflake-cortex/*` | `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_CORTEX_PAT` |
168
+ | [STACKIT](https://mastra.ai/models/providers/stackit) | `stackit/*` | `STACKIT_API_KEY` |
169
+ | [Standard Compute](https://mastra.ai/models/providers/standardcompute) | `standardcompute/*` | `STANDARDCOMPUTE_API_KEY` |
170
+ | [StepFun (China)](https://mastra.ai/models/providers/stepfun) | `stepfun/*` | `STEPFUN_API_KEY` |
171
+ | [StepFun (Global)](https://mastra.ai/models/providers/stepfun-ai) | `stepfun-ai/*` | `STEPFUN_API_KEY` |
172
+ | [StepFun Step Plan (China)](https://mastra.ai/models/providers/stepfun-step-plan) | `stepfun-step-plan/*` | `STEPFUN_API_KEY` |
173
+ | [StepFun Step Plan (Global)](https://mastra.ai/models/providers/stepfun-ai-step-plan) | `stepfun-ai-step-plan/*` | `STEPFUN_API_KEY` |
174
+ | [Subconscious](https://mastra.ai/models/providers/subconscious) | `subconscious/*` | `SUBCONSCIOUS_API_KEY` |
175
+ | [submodel](https://mastra.ai/models/providers/submodel) | `submodel/*` | `SUBMODEL_INSTAGEN_ACCESS_KEY` |
176
+ | [Synthetic](https://mastra.ai/models/providers/synthetic) | `synthetic/*` | `SYNTHETIC_API_KEY` |
177
+ | [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan) | `tencent-coding-plan/*` | `TENCENT_CODING_PLAN_API_KEY` |
178
+ | [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan) | `tencent-token-plan/*` | `TENCENT_TOKEN_PLAN_API_KEY` |
179
+ | [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub) | `tencent-tokenhub/*` | `TENCENT_TOKENHUB_API_KEY` |
180
+ | [TensorX](https://mastra.ai/models/providers/tensorx) | `tensorx/*` | `TENSORX_API_KEY` |
181
+ | [The Grid AI](https://mastra.ai/models/providers/the-grid-ai) | `the-grid-ai/*` | `THEGRID_API_KEY` |
182
+ | [Thinking Machines](https://mastra.ai/models/providers/thinkingmachines) | `thinkingmachines/*` | `TINKER_API_KEY` |
183
+ | [Tinfoil](https://mastra.ai/models/providers/tinfoil) | `tinfoil/*` | `TINFOIL_API_KEY` |
184
+ | [Together AI](https://mastra.ai/models/providers/togetherai) | `togetherai/*` | `TOGETHER_API_KEY` |
185
+ | [TokenGo](https://mastra.ai/models/providers/tokengo) | `tokengo/*` | `TOKENGO_API_KEY` |
186
+ | [TokenRouter](https://mastra.ai/models/providers/tokenrouter) | `tokenrouter/*` | `TOKENROUTER_API_KEY` |
187
+ | [TrustedRouter](https://mastra.ai/models/providers/trustedrouter) | `trustedrouter/*` | `TRUSTEDROUTER_API_KEY` |
188
+ | [Umans AI](https://mastra.ai/models/providers/umans-ai) | `umans-ai/*` | `UMANS_AI_API_KEY` |
189
+ | [Umans AI Coding Plan](https://mastra.ai/models/providers/umans-ai-coding-plan) | `umans-ai-coding-plan/*` | `UMANS_AI_CODING_PLAN_API_KEY` |
190
+ | [UnoRouter](https://mastra.ai/models/providers/unorouter) | `unorouter/*` | `UNOROUTER_API_KEY` |
191
+ | [Upstage](https://mastra.ai/models/providers/upstage) | `upstage/*` | `UPSTAGE_API_KEY` |
192
+ | [Vancine](https://mastra.ai/models/providers/vancine) | `vancine/*` | `VANCINE_API_KEY` |
193
+ | [Vispark](https://mastra.ai/models/providers/vispark) | `vispark/*` | `VISPARK_LAB_API_KEY` |
194
+ | [Vivgrid](https://mastra.ai/models/providers/vivgrid) | `vivgrid/*` | `VIVGRID_API_KEY` |
195
+ | [Volcengine Ark](https://mastra.ai/models/providers/volcengine) | `volcengine/*` | `ARK_API_KEY` |
196
+ | [Volcengine Ark Coding Plan](https://mastra.ai/models/providers/volcengine-coding-plan) | `volcengine-coding-plan/*` | `ARK_CODING_PLAN_API_KEY` |
197
+ | [Vultr](https://mastra.ai/models/providers/vultr) | `vultr/*` | `VULTR_API_KEY` |
198
+ | [Wafer](https://mastra.ai/models/providers/wafer.ai) | `wafer.ai/*` | `WAFER_API_KEY` |
199
+ | [Wallaby](https://mastra.ai/models/providers/wallaby) | `wallaby/*` | `WALLABY_API_KEY` |
200
+ | [xAI](https://mastra.ai/models/providers/xai) | `xai/*` | `XAI_API_KEY` |
201
+ | [Xiaomi](https://mastra.ai/models/providers/xiaomi) | `xiaomi/*` | `XIAOMI_API_KEY` |
202
+ | [Xiaomi Token Plan (China)](https://mastra.ai/models/providers/xiaomi-token-plan-cn) | `xiaomi-token-plan-cn/*` | `XIAOMI_API_KEY` |
203
+ | [Xiaomi Token Plan (Europe)](https://mastra.ai/models/providers/xiaomi-token-plan-ams) | `xiaomi-token-plan-ams/*` | `XIAOMI_API_KEY` |
204
+ | [Xiaomi Token Plan (Singapore)](https://mastra.ai/models/providers/xiaomi-token-plan-sgp) | `xiaomi-token-plan-sgp/*` | `XIAOMI_API_KEY` |
205
+ | [Xpersona](https://mastra.ai/models/providers/xpersona) | `xpersona/*` | `XPERSONA_API_KEY` |
206
+ | [Z.AI](https://mastra.ai/models/providers/zai) | `zai/*` | `ZHIPU_API_KEY` |
207
+ | [Z.AI Coding Plan](https://mastra.ai/models/providers/zai-coding-plan) | `zai-coding-plan/*` | `ZHIPU_API_KEY` |
208
+ | [Zeldoc](https://mastra.ai/models/providers/zeldoc) | `zeldoc/*` | `ZELDOC_API_KEY` |
209
+ | [Zenifra](https://mastra.ai/models/providers/zenifra) | `zenifra/*` | `ZENIFRA_AI_KEY` |
210
+ | [ZenMux](https://mastra.ai/models/providers/zenmux) | `zenmux/*` | `ZENMUX_API_KEY` |
211
+ | [Zhipu AI](https://mastra.ai/models/providers/zhipuai) | `zhipuai/*` | `ZHIPU_API_KEY` |
212
+ | [Zhipu AI Coding Plan](https://mastra.ai/models/providers/zhipuai-coding-plan) | `zhipuai-coding-plan/*` | `ZHIPU_API_KEY` |
213
+ | [Azure OpenAI](https://mastra.ai/models/gateways/azure-openai) (Gateway) | `azure-openai/*` | `AZURE_API_KEY`, `AZURE_TENANT_ID`, `AZURE_CLIENT_ID`, `AZURE_CLIENT_SECRET`, `AZURE_SUBSCRIPTION_ID` |
214
+ | [Mastra](https://mastra.ai/models/gateways/mastra) (Gateway) | `mastra/*` | `MASTRA_GATEWAY_API_KEY` |
215
+ | [Merge Gateway](https://mastra.ai/models/gateways/merge-gateway) (Gateway) | `merge-gateway/*` | `MERGE_GATEWAY_API_KEY` |
216
+ | [Neon](https://mastra.ai/models/gateways/neon) (Gateway) | `neon/*` | `NEON_AI_GATEWAY_BASE_URL`, `NEON_AI_GATEWAY_TOKEN` |
217
+ | [Netlify](https://mastra.ai/models/gateways/netlify) (Gateway) | `netlify/*` | `NETLIFY_TOKEN`, `NETLIFY_SITE_ID` |
218
+ | [OpenRouter](https://mastra.ai/models/gateways/openrouter) (Gateway) | `openrouter/*` | `OPENROUTER_API_KEY` |
219
+ | [Vercel](https://mastra.ai/models/gateways/vercel) (Gateway) | `vercel/*` | `AI_GATEWAY_API_KEY` |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
6
6
 
7
- Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 372 models through Mastra's model router.
7
+ Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 375 models through Mastra's model router.
8
8
 
9
9
  Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
10
10
 
@@ -234,6 +234,7 @@ ANTHROPIC_API_KEY=ant-...
234
234
  | `mistral/mistral-medium-3.5` |
235
235
  | `mistral/mistral-nemo` |
236
236
  | `mistral/mistral-small` |
237
+ | `mixedbread/toast-1` |
237
238
  | `moonshotai/kimi-k2` |
238
239
  | `moonshotai/kimi-k2-thinking` |
239
240
  | `moonshotai/kimi-k2.5` |
@@ -337,6 +338,8 @@ ANTHROPIC_API_KEY=ant-...
337
338
  | `poolside/laguna-s-2.1-free` |
338
339
  | `prodia/flux-fast-schnell` |
339
340
  | `quiverai/arrow-1.1` |
341
+ | `quiverai/arrow-2` |
342
+ | `quiverai/arrow-2-telos` |
340
343
  | `recraft/recraft-v2` |
341
344
  | `recraft/recraft-v3` |
342
345
  | `recraft/recraft-v4` |
@@ -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 7359 models from 209 providers through a single API.
7
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7369 models from 209 providers through a single API.
8
8
 
9
9
  ## Features
10
10
 
@@ -55,7 +55,7 @@ for await (const chunk of stream) {
55
55
  | `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
56
56
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
57
57
  | `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
58
- | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.89 | $3 |
58
+ | `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.84 | $3 |
59
59
  | `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
60
60
  | `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
61
61
  | `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
@@ -379,7 +379,7 @@ for await (const chunk of stream) {
379
379
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
380
380
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
381
381
  | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
382
- | `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
382
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
383
383
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
384
384
  | `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
385
385
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
6
6
 
7
- Access 404 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
7
+ Access 402 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
 
@@ -415,8 +415,6 @@ for await (const chunk of stream) {
415
415
  | `llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.22 | $2 |
416
416
  | `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
417
417
  | `llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
418
- | `llmgateway-providers/vichar-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
419
- | `llmgateway-providers/vichar-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
420
418
  | `llmgateway-providers/xai/grok-4` | 256K | | | | | | $3 | $15 |
421
419
  | `llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning` | 2.0M | | | | | | $2 | $6 |
422
420
  | `llmgateway-providers/xai/grok-4-20-beta-0309-reasoning` | 2.0M | | | | | | $2 | $6 |
@@ -2,11 +2,11 @@
2
2
 
3
3
  > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
4
4
 
5
- # ![MiniMax Token Plan (minimaxi.com) logo](https://models.dev/logos/minimax-cn-coding-plan.svg)MiniMax Token Plan (minimaxi.com)
5
+ # ![MiniMax Token Plan (minimax.cn) logo](https://models.dev/logos/minimax-cn-coding-plan.svg)MiniMax Token Plan (minimax.cn)
6
6
 
7
- Access 7 MiniMax Token Plan (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
7
+ Access 7 MiniMax Token Plan (minimax.cn) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
8
8
 
9
- Learn more in the [MiniMax Token Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/token-plan/intro).
9
+ Learn more in the [MiniMax Token Plan (minimax.cn) documentation](https://platform.minimaxi.com/docs/token-plan/intro).
10
10
 
11
11
  ```bash
12
12
  MINIMAX_API_KEY=your-api-key
@@ -32,7 +32,7 @@ for await (const chunk of stream) {
32
32
  }
33
33
  ```
34
34
 
35
- > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Token Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/token-plan/intro) for details.
35
+ > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Token Plan (minimax.cn) documentation](https://platform.minimaxi.com/docs/token-plan/intro) for details.
36
36
 
37
37
  ## Models
38
38
 
@@ -57,7 +57,7 @@ const agent = new Agent({
57
57
  id: "custom-agent",
58
58
  name: "custom-agent",
59
59
  model: {
60
- url: "https://api.minimaxi.com/anthropic/v1",
60
+ url: "https://api.minimax.cn/anthropic/v1",
61
61
  id: "minimax-cn-coding-plan/MiniMax-M2",
62
62
  apiKey: process.env.MINIMAX_API_KEY,
63
63
  headers: {
@@ -2,11 +2,11 @@
2
2
 
3
3
  > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
4
4
 
5
- # ![MiniMax (minimaxi.com) logo](https://models.dev/logos/minimax-cn.svg)MiniMax (minimaxi.com)
5
+ # ![MiniMax (minimax.cn) logo](https://models.dev/logos/minimax-cn.svg)MiniMax (minimax.cn)
6
6
 
7
- Access 7 MiniMax (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
7
+ Access 7 MiniMax (minimax.cn) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
8
8
 
9
- Learn more in the [MiniMax (minimaxi.com) documentation](https://platform.minimaxi.com/docs/guides/quickstart).
9
+ Learn more in the [MiniMax (minimax.cn) documentation](https://platform.minimaxi.com/docs/guides/quickstart).
10
10
 
11
11
  ```bash
12
12
  MINIMAX_API_KEY=your-api-key
@@ -32,7 +32,7 @@ for await (const chunk of stream) {
32
32
  }
33
33
  ```
34
34
 
35
- > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax (minimaxi.com) documentation](https://platform.minimaxi.com/docs/guides/quickstart) for details.
35
+ > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax (minimax.cn) documentation](https://platform.minimaxi.com/docs/guides/quickstart) for details.
36
36
 
37
37
  ## Models
38
38
 
@@ -57,7 +57,7 @@ const agent = new Agent({
57
57
  id: "custom-agent",
58
58
  name: "custom-agent",
59
59
  model: {
60
- url: "https://api.minimaxi.com/anthropic/v1",
60
+ url: "https://api.minimax.cn/anthropic/v1",
61
61
  id: "minimax-cn/MiniMax-M2",
62
62
  apiKey: process.env.MINIMAX_API_KEY,
63
63
  headers: {
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![NanoGPT logo](https://models.dev/logos/nano-gpt.svg)NanoGPT
6
6
 
7
- Access 572 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
7
+ Access 577 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
10
10
 
@@ -221,6 +221,7 @@ for await (const chunk of stream) {
221
221
  | `nano-gpt/glm-4.1v-thinking-flashx` | 64K | | | | | | $0.30 | $0.30 |
222
222
  | `nano-gpt/GLM-4.6-Derestricted-v5` | 131K | | | | | | $0.40 | $2 |
223
223
  | `nano-gpt/glm-z1-airx` | 32K | | | | | | $0.70 | $0.70 |
224
+ | `nano-gpt/google/diffusiongemma` | 262K | | | | | | $0.05 | $0.15 |
224
225
  | `nano-gpt/google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
225
226
  | `nano-gpt/google/gemini-3-flash-preview-thinking` | 1.0M | | | | | | $0.50 | $3 |
226
227
  | `nano-gpt/google/gemini-3.1-flash-lite` | 1.0M | | | | | | $0.25 | $2 |
@@ -238,6 +239,7 @@ for await (const chunk of stream) {
238
239
  | `nano-gpt/google/gemini-flash-lite-latest` | 1.0M | | | | | | $0.30 | $3 |
239
240
  | `nano-gpt/google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
240
241
  | `nano-gpt/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.12 | $0.38 |
242
+ | `nano-gpt/google/gemma-4-26b-a4b-it-cybersecurity` | 262K | | | | | | $0.11 | $0.33 |
241
243
  | `nano-gpt/google/gemma-4-26b-a4b-it:thinking` | 262K | | | | | | $0.13 | $0.40 |
242
244
  | `nano-gpt/google/gemma-4-31b-it` | 262K | | | | | | $0.10 | $0.45 |
243
245
  | `nano-gpt/google/gemma-4-31b-it:thinking` | 262K | | | | | | $0.10 | $0.35 |
@@ -351,6 +353,7 @@ for await (const chunk of stream) {
351
353
  | `nano-gpt/nvidia/nemotron-3-super-120b-a12b:thinking` | 262K | | | | | | $0.05 | $0.25 |
352
354
  | `nano-gpt/nvidia/nemotron-3-ultra-550b-a55b` | 1.0M | | | | | | $0.50 | $3 |
353
355
  | `nano-gpt/nvidia/nemotron-3-ultra-550b-a55b:thinking` | 1.0M | | | | | | $0.50 | $3 |
356
+ | `nano-gpt/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.05 | $0.15 |
354
357
  | `nano-gpt/nvidia/nemotron-3.5-lightning` | 1.0M | | | | | | $0.05 | $0.20 |
355
358
  | `nano-gpt/nvidia/nemotron-3.5-lightning:thinking` | 1.0M | | | | | | $0.05 | $0.20 |
356
359
  | `nano-gpt/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
@@ -468,12 +471,13 @@ for await (const chunk of stream) {
468
471
  | `nano-gpt/qwen/qwen3.7-plus` | 992K | | | | | | $0.40 | $2 |
469
472
  | `nano-gpt/qwen/qwen3.7-plus:thinking` | 984K | | | | | | $0.40 | $2 |
470
473
  | `nano-gpt/qwen/qwen3.8-27b` | 262K | | | | | | $0.15 | $0.70 |
474
+ | `nano-gpt/qwen/qwen3.8-27b-cybersecurity` | 262K | | | | | | $0.10 | $0.60 |
471
475
  | `nano-gpt/qwen/qwen3.8-27b-fable` | 524K | | | | | | $0.25 | $2 |
472
476
  | `nano-gpt/qwen/qwen3.8-27b-obliterated` | 524K | | | | | | $0.25 | $2 |
473
477
  | `nano-gpt/qwen/qwen3.8-27b-obliterated:thinking` | 524K | | | | | | $0.25 | $2 |
474
478
  | `nano-gpt/qwen/qwen3.8-27b-queen` | 524K | | | | | | $0.25 | $2 |
475
- | `nano-gpt/qwen/qwen3.8-27b-uncensored` | 524K | | | | | | $0.25 | $2 |
476
- | `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking` | 524K | | | | | | $0.25 | $2 |
479
+ | `nano-gpt/qwen/qwen3.8-27b-uncensored` | 524K | | | | | | $0.20 | $2 |
480
+ | `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking` | 524K | | | | | | $0.20 | $2 |
477
481
  | `nano-gpt/qwen/qwen3.8-27b:thinking` | 262K | | | | | | $0.15 | $0.70 |
478
482
  | `nano-gpt/qwen/qwen3.8-flash` | 992K | | | | | | $0.14 | $0.42 |
479
483
  | `nano-gpt/qwen/qwen3.8-max` | 991K | | | | | | $2 | $6 |
@@ -605,6 +609,7 @@ for await (const chunk of stream) {
605
609
  | `nano-gpt/z-ai/glm-5.2:thinking` | 1.0M | | | | | | $0.42 | $1 |
606
610
  | `nano-gpt/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $3 |
607
611
  | `nano-gpt/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.07 | $0.25 |
612
+ | `nano-gpt/z-ai/glm-5.3-flash-cybersecurity` | 1.0M | | | | | | $0.15 | $0.50 |
608
613
  | `nano-gpt/z-ai/glm-5.3-flash-uncensored` | 1.0M | | | | | | $0.20 | $0.80 |
609
614
  | `nano-gpt/z-ai/glm-5.3:thinking` | 1.0M | | | | | | $1 | $3 |
610
615
  | `nano-gpt/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![Nebius Token Factory logo](https://models.dev/logos/nebius.svg)Nebius Token Factory
6
6
 
7
- Access 17 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
7
+ Access 20 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/).
10
10
 
@@ -40,6 +40,8 @@ for await (const chunk of stream) {
40
40
  | ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
41
  | `nebius/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
42
42
  | `nebius/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $2 | $4 |
43
+ | `nebius/deepseek-ai/DeepSeek-V4-Pro-0813` | 979K | | | | | | $1 | $4 |
44
+ | `nebius/deepseek-ai/DeepSeek-V4.1-Flash` | 1.0M | | | | | | $0.30 | $1 |
43
45
  | `nebius/google/gemma-3-27b-it` | 110K | | | | | | $0.10 | $0.30 |
44
46
  | `nebius/MiniMaxAI/MiniMax-M3` | 1.0M | | | | | | $0.30 | $1 |
45
47
  | `nebius/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
@@ -54,6 +56,7 @@ for await (const chunk of stream) {
54
56
  | `nebius/Qwen/Qwen3-Embedding-8B` | 41K | | | | | | $0.01 | — |
55
57
  | `nebius/Qwen/Qwen3.5-397B-A17B` | 262K | | | | | | $0.60 | $4 |
56
58
  | `nebius/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
59
+ | `nebius/zai-org/GLM-5.3` | 1.0M | | | | | | $1 | $4 |
57
60
  | `nebius/zai-org/GLM-5.3-Flash` | 1.0M | | | | | | $0.15 | $0.50 |
58
61
 
59
62
  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
  # ![TensorX logo](https://models.dev/logos/tensorx.svg)TensorX
6
6
 
7
- Access 26 TensorX models through Mastra's model router. Authentication is handled automatically using the `TENSORX_API_KEY` environment variable.
7
+ Access 25 TensorX models through Mastra's model router. Authentication is handled automatically using the `TENSORX_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [TensorX documentation](https://docs.tensorx.ai/).
10
10
 
@@ -19,7 +19,7 @@ const agent = new Agent({
19
19
  id: "my-agent",
20
20
  name: "My Agent",
21
21
  instructions: "You are a helpful assistant",
22
- model: "tensorx/deepseek/deepseek-chat-v3.1"
22
+ model: "tensorx/deepseek/deepseek-r1-0528"
23
23
  });
24
24
 
25
25
  // Generate a response
@@ -36,34 +36,33 @@ for await (const chunk of stream) {
36
36
 
37
37
  ## Models
38
38
 
39
- | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
- | ------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
- | `tensorx/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.20 | $0.80 |
42
- | `tensorx/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.66 | $3 |
43
- | `tensorx/deepseek/deepseek-v3.2` | 164K | | | | | | $0.30 | $0.50 |
44
- | `tensorx/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.15 | $0.30 |
45
- | `tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
46
- | `tensorx/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $4 |
47
- | `tensorx/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.50 | $2 |
48
- | `tensorx/minimax/minimax-m2.5` | 197K | | | | | | $0.30 | $1 |
49
- | `tensorx/minimax/minimax-m3` | 1.0M | | | | | | $0.40 | $2 |
50
- | `tensorx/moonshotai/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
51
- | `tensorx/moonshotai/kimi-k2.6` | 262K | | | | | | $1 | $4 |
52
- | `tensorx/moonshotai/kimi-k2.7-code` | 262K | | | | | | $1 | $5 |
53
- | `tensorx/moonshotai/kimi-k3` | 1.0M | | | | | | $3 | $15 |
54
- | `tensorx/nvidia/nemotron-3-super-120b-a12b` | 262K | | | | | | $0.30 | $0.90 |
55
- | `tensorx/openai/gpt-oss-120b` | 131K | | | | | | $0.04 | $0.20 |
56
- | `tensorx/qwen/qwen3-235b-a22b-2507` | 131K | | | | | | $0.07 | $0.46 |
57
- | `tensorx/qwen/qwen3-coder-30b-a3b-instruct` | 262K | | | | | | $0.06 | $0.25 |
58
- | `tensorx/qwen/qwen3-vl-235b-a22b-instruct` | 131K | | | | | | $0.21 | $2 |
59
- | `tensorx/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.50 | $4 |
60
- | `tensorx/qwen/qwen3.5-9b` | 262K | | | | | | $0.15 | $0.20 |
61
- | `tensorx/z-ai/glm-4.7` | 200K | | | | | | $0.60 | $2 |
62
- | `tensorx/z-ai/glm-5` | 203K | | | | | | $1 | $3 |
63
- | `tensorx/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
64
- | `tensorx/z-ai/glm-5.1` | 203K | | | | | | $1 | $4 |
65
- | `tensorx/z-ai/glm-5.2` | 1.0M | | | | | | $2 | $5 |
66
- | `tensorx/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
39
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
40
+ | ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
41
+ | `tensorx/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.66 | $3 |
42
+ | `tensorx/deepseek/deepseek-v3.2` | 164K | | | | | | $0.30 | $0.50 |
43
+ | `tensorx/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.25 | $0.30 |
44
+ | `tensorx/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $4 |
45
+ | `tensorx/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $2 | $4 |
46
+ | `tensorx/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.50 | $2 |
47
+ | `tensorx/minimax/minimax-m2.5` | 197K | | | | | | $0.30 | $1 |
48
+ | `tensorx/minimax/minimax-m3` | 1.0M | | | | | | $0.40 | $2 |
49
+ | `tensorx/moonshotai/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
50
+ | `tensorx/moonshotai/kimi-k2.6` | 262K | | | | | | $1 | $4 |
51
+ | `tensorx/moonshotai/kimi-k2.7-code` | 262K | | | | | | $1 | $5 |
52
+ | `tensorx/moonshotai/kimi-k3` | 1.0M | | | | | | $3 | $15 |
53
+ | `tensorx/qwen/qwen3-235b-a22b-2507` | 131K | | | | | | $0.07 | $0.46 |
54
+ | `tensorx/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.50 | $4 |
55
+ | `tensorx/qwen/qwen3.5-9b` | 262K | | | | | | $0.15 | $0.20 |
56
+ | `tensorx/qwen/qwen3.8-2.4t-a95b` | 262K | | | | | | $3 | $6 |
57
+ | `tensorx/qwen/qwen3.8-27b` | 262K | | | | | | $0.40 | $2 |
58
+ | `tensorx/qwen/qwen3.8-flash-next` | 262K | | | | | | $0.20 | $0.50 |
59
+ | `tensorx/z-ai/glm-5` | 203K | | | | | | $1 | $3 |
60
+ | `tensorx/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
61
+ | `tensorx/z-ai/glm-5.1` | 203K | | | | | | $1 | $4 |
62
+ | `tensorx/z-ai/glm-5.2` | 1.0M | | | | | | $2 | $5 |
63
+ | `tensorx/z-ai/glm-5.3` | 1.0M | | | | | | $2 | $5 |
64
+ | `tensorx/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.20 | $0.50 |
65
+ | `tensorx/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
67
66
 
68
67
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
69
68
 
@@ -77,7 +76,7 @@ const agent = new Agent({
77
76
  name: "custom-agent",
78
77
  model: {
79
78
  url: "https://api.tensorx.ai/v1",
80
- id: "tensorx/deepseek/deepseek-chat-v3.1",
79
+ id: "tensorx/deepseek/deepseek-r1-0528",
81
80
  apiKey: process.env.TENSORX_API_KEY,
82
81
  headers: {
83
82
  "X-Custom-Header": "value"
@@ -96,7 +95,7 @@ const agent = new Agent({
96
95
  const useAdvanced = requestContext.task === "complex";
97
96
  return useAdvanced
98
97
  ? "tensorx/z-ai/glm-5v-turbo"
99
- : "tensorx/deepseek/deepseek-chat-v3.1";
98
+ : "tensorx/deepseek/deepseek-r1-0528";
100
99
  }
101
100
  });
102
101
  ```
@@ -4,7 +4,7 @@
4
4
 
5
5
  # ![ZenMux logo](https://models.dev/logos/zenmux.svg)ZenMux
6
6
 
7
- Access 120 ZenMux models through Mastra's model router. Authentication is handled automatically using the `ZENMUX_API_KEY` environment variable.
7
+ Access 122 ZenMux models through Mastra's model router. Authentication is handled automatically using the `ZENMUX_API_KEY` environment variable.
8
8
 
9
9
  Learn more in the [ZenMux documentation](https://docs.zenmux.ai).
10
10
 
@@ -117,31 +117,38 @@ for await (const chunk of stream) {
117
117
  | `zenmux/volcengine/doubao-seed-2.0-lite` | 256K | | | | | | $0.09 | $0.51 |
118
118
  | `zenmux/volcengine/doubao-seed-2.0-mini` | 256K | | | | | | $0.03 | $0.28 |
119
119
  | `zenmux/volcengine/doubao-seed-2.0-pro` | 256K | | | | | | $0.45 | $2 |
120
- | `zenmux/x-ai/grok-4.2-fast` | 2.0M | | | | | | $3 | $9 |
121
- | `zenmux/x-ai/grok-4.2-fast-non-reasoning` | 2.0M | | | | | | $3 | $9 |
120
+ | `zenmux/x-ai/grok-4.2-fast` | 2.0M | | | | | | $2 | $6 |
121
+ | `zenmux/x-ai/grok-4.2-fast-non-reasoning` | 2.0M | | | | | | $2 | $6 |
122
122
  | `zenmux/x-ai/grok-4.3` | 1.0M | | | | | | $1 | $3 |
123
123
  | `zenmux/x-ai/grok-4.5` | 500K | | | | | | $2 | $6 |
124
+ | `zenmux/x-ai/grok-4.6` | 500K | | | | | | $2 | $6 |
124
125
  | `zenmux/x-ai/grok-build-0.1` | 256K | | | | | | $1 | $2 |
126
+ | `zenmux/x-ai/grok-imagine-image-2.0` | 66K | | | | | | — | — |
127
+ | `zenmux/x-ai/grok-voice-stt-1.0` | 15K | | | | | | — | — |
128
+ | `zenmux/x-ai/grok-voice-tts-1.0` | 15K | | | | | | — | — |
125
129
  | `zenmux/xiaomi/mimo-v2-flash` | 262K | | | | | | $0.10 | $0.30 |
126
130
  | `zenmux/xiaomi/mimo-v2-omni` | 265K | | | | | | $0.40 | $2 |
127
131
  | `zenmux/xiaomi/mimo-v2-pro` | 1.0M | | | | | | $1 | $3 |
128
132
  | `zenmux/xiaomi/mimo-v2.5` | 1.0M | | | | | | $0.40 | $2 |
129
133
  | `zenmux/xiaomi/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
130
- | `zenmux/z-ai/glm-4.5` | 128K | | | | | | $0.35 | $2 |
131
- | `zenmux/z-ai/glm-4.5-air` | 128K | | | | | | $0.11 | $0.56 |
132
- | `zenmux/z-ai/glm-4.6` | 200K | | | | | | $0.35 | $2 |
133
- | `zenmux/z-ai/glm-4.6v` | 200K | | | | | | $0.14 | $0.42 |
134
- | `zenmux/z-ai/glm-4.6v-flash` | 200K | | | | | | $0.02 | $0.21 |
134
+ | `zenmux/z-ai/glm-4.5` | 128K | | | | | | $0.29 | $1 |
135
+ | `zenmux/z-ai/glm-4.5-air` | 128K | | | | | | $0.12 | $0.29 |
136
+ | `zenmux/z-ai/glm-4.6` | 200K | | | | | | $0.29 | $1 |
137
+ | `zenmux/z-ai/glm-4.6v` | 200K | | | | | | $0.15 | $0.44 |
138
+ | `zenmux/z-ai/glm-4.6v-flash` | 200K | | | | | | $0.02 | $0.22 |
135
139
  | `zenmux/z-ai/glm-4.6v-flash-free` | 200K | | | | | | — | — |
136
- | `zenmux/z-ai/glm-4.7` | 200K | | | | | | $0.28 | $1 |
140
+ | `zenmux/z-ai/glm-4.7` | 200K | | | | | | $0.29 | $1 |
137
141
  | `zenmux/z-ai/glm-4.7-flash-free` | 200K | | | | | | — | — |
138
- | `zenmux/z-ai/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.42 |
142
+ | `zenmux/z-ai/glm-4.7-flashx` | 200K | | | | | | $0.07 | $0.44 |
139
143
  | `zenmux/z-ai/glm-5` | 200K | | | | | | $0.58 | $3 |
140
- | `zenmux/z-ai/glm-5-turbo` | 200K | | | | | | $0.88 | $3 |
144
+ | `zenmux/z-ai/glm-5-turbo` | 200K | | | | | | $0.73 | $3 |
141
145
  | `zenmux/z-ai/glm-5.1` | 200K | | | | | | $0.88 | $4 |
142
- | `zenmux/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $5 |
143
- | `zenmux/z-ai/glm-5.2-free` | 1.0M | | | | | | — | — |
146
+ | `zenmux/z-ai/glm-5.2` | 1.0M | | | | | | $0.98 | $3 |
147
+ | `zenmux/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
148
+ | `zenmux/z-ai/glm-5.3-flash` | 1.0M | | | | | | $0.15 | $0.50 |
149
+ | `zenmux/z-ai/glm-5.3-flashx` | 1.0M | | | | | | $0.38 | $1 |
144
150
  | `zenmux/z-ai/glm-5v-turbo` | 200K | | | | | | $0.73 | $3 |
151
+ | `zenmux/z-ai/glm-image` | 10K | | | | | | — | — |
145
152
 
146
153
  Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
147
154
 
@@ -173,7 +180,7 @@ const agent = new Agent({
173
180
  model: ({ requestContext }) => {
174
181
  const useAdvanced = requestContext.task === "complex";
175
182
  return useAdvanced
176
- ? "zenmux/z-ai/glm-5v-turbo"
183
+ ? "zenmux/z-ai/glm-image"
177
184
  : "zenmux/anthropic/claude-3.5-haiku";
178
185
  }
179
186
  });
@@ -111,10 +111,10 @@ Direct access to individual AI model providers. Each provider offers unique mode
111
111
  - [Meganova](https://mastra.ai/models/providers/meganova)
112
112
  - [Melious](https://mastra.ai/models/providers/melious)
113
113
  - [Meta](https://mastra.ai/models/providers/meta)
114
+ - [MiniMax (minimax.cn)](https://mastra.ai/models/providers/minimax-cn)
114
115
  - [MiniMax (minimax.io)](https://mastra.ai/models/providers/minimax)
115
- - [MiniMax (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn)
116
+ - [MiniMax Token Plan (minimax.cn)](https://mastra.ai/models/providers/minimax-cn-coding-plan)
116
117
  - [MiniMax Token Plan (minimax.io)](https://mastra.ai/models/providers/minimax-coding-plan)
117
- - [MiniMax Token Plan (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn-coding-plan)
118
118
  - [Mixlayer](https://mastra.ai/models/providers/mixlayer)
119
119
  - [Moark](https://mastra.ai/models/providers/moark)
120
120
  - [Modal](https://mastra.ai/models/providers/modal)
@@ -89,6 +89,8 @@ Results are scoped to the agent you call `listSuspendedRuns()` on because snapsh
89
89
 
90
90
  Run snapshots are only persisted while a run is waiting on input and are deleted when it finishes, so suspended runs are the only runs discoverable from storage. Suspended runs only survive restarts when the Mastra instance has a persistent [storage provider](https://mastra.ai/docs/storage) configured. With the default in-memory store, snapshots are lost on restart.
91
91
 
92
+ The `threadId` and `resourceId` filters are pushed down to the storage query where the adapter supports it. `@mastra/pg` and `@mastra/libsql` narrow matching runs inside the database instead of loading every suspended snapshot, and the in-memory store filters its in-memory records. Other storage adapters apply these filters in-process after fetching. Results are identical either way.
93
+
92
94
  ## Related
93
95
 
94
96
  - [Agent approval](https://mastra.ai/docs/agents/human-in-the-loop)
@@ -10,7 +10,7 @@ Use it when an agent may switch between model providers or reuse message history
10
10
 
11
11
  ## Usage example
12
12
 
13
- Add `ProviderHistoryCompat` to `inputProcessors` when you want all built-in compatibility rules available for an agent:
13
+ Add `ProviderHistoryCompat` to both lists when you want all built-in compatibility rules available for an agent. `inputProcessors` drives the preemptive rewrites, `errorProcessors` drives the reactive recovery:
14
14
 
15
15
  ```typescript
16
16
  import { Agent } from '@mastra/core/agent'
@@ -22,11 +22,19 @@ export const agent = new Agent({
22
22
  instructions: 'You are a helpful assistant.',
23
23
  model: 'anthropic/claude-sonnet-4-5',
24
24
  inputProcessors: [new ProviderHistoryCompat()],
25
+ errorProcessors: [new ProviderHistoryCompat()],
25
26
  })
26
27
  ```
27
28
 
28
29
  Mastra agents don't add this processor automatically. Add it explicitly when you need provider history compatibility rules, reactive API error recovery, custom rules, or predictable processor ordering.
29
30
 
31
+ The placement decides which half of the processor works:
32
+
33
+ - **Reactive rules need `errorProcessors`.** On the standard loop, `processAPIError` runs from any of the three lists, so an input-processor registration does repair the message list, but the retry it asks for is only honored when the agent has a retry budget, and that budget is left `undefined` unless the agent configures `errorProcessors` or sets `maxProcessorRetries` explicitly. Registered only as an input processor and without an explicit `maxProcessorRetries`, a reactive rule repairs the history and the request still fails. On the durable path the API-error pass additionally requires a non-empty `errorProcessors` list. If that list is empty, an input-processor registration can't trigger reactive recovery there at all, even with `maxProcessorRetries` set.
34
+ - **Preemptive rules need `inputProcessors`.** `processLLMRequest` runs over the input processors only, so prompt rewrites don't happen from the error list.
35
+
36
+ An agent that wants both registers the processor in both lists, as the example above does. Double registration can't cause a double retry: the runner stops at the first processor that asks for one, and each reactive rule bails once `retryCount` is above zero, so a repaired turn is attempted exactly once more.
37
+
30
38
  ## Constructor parameters
31
39
 
32
40
  **opts** (`{ additionalRules?: CompatRule[] }`): Configuration options for provider history compatibility rules.
@@ -47,13 +55,14 @@ Mastra agents don't add this processor automatically. Add it explicitly when you
47
55
 
48
56
  `ProviderHistoryCompat` includes these built-in compatibility rules:
49
57
 
50
- | Rule | Provider | Timing | Behavior |
51
- | ------------------------------------------- | -------------------- | --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
52
- | `anthropic-tool-id-format` | Anthropic | Reactive API error recovery | Rewrites tool call IDs that contain characters outside `[a-zA-Z0-9_-]` and retries the request. |
53
- | `cerebras-strip-reasoning-content` | Cerebras | Preemptive prompt rewrite | Removes assistant `reasoning` parts from the outbound prompt so they're not serialized as unsupported `reasoning_content` fields. |
54
- | `anthropic-strip-foreign-reasoning-content` | Anthropic | Preemptive prompt rewrite | Removes non-Anthropic assistant `reasoning` parts from the outbound prompt. Anthropic-native thinking history is preserved. |
55
- | `anthropic-strip-foreign-signed-reasoning` | Anthropic-compatible | Preemptive prompt rewrite | Drops signed thinking from the outbound prompt when its origin turn was stamped with a different provider (for example Kimi For Coding ↔ `anthropic/claude-sonnet-4-6`), since the receiving provider can't verify another provider's signature. Turns emptied of all content by the drop are removed from the prompt. Unstamped history is left untouched. |
56
- | `azure-system-reminder-transform` | Azure OpenAI | Preemptive prompt rewrite | Renames `<system-reminder>` wrappers in user text and system instructions to `<memory-context>` for the outbound request. Stored history remains unchanged. |
58
+ | Rule | Provider | Timing | Behavior |
59
+ | ------------------------------------------- | -------------------------------- | --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
60
+ | `anthropic-tool-id-format` | Anthropic | Reactive API error recovery | Rewrites tool call IDs that contain characters outside `[a-zA-Z0-9_-]` and retries the request. |
61
+ | `cerebras-strip-reasoning-content` | Cerebras | Preemptive prompt rewrite | Removes assistant `reasoning` parts from the outbound prompt so they're not serialized as unsupported `reasoning_content` fields. |
62
+ | `anthropic-strip-foreign-reasoning-content` | Anthropic | Preemptive prompt rewrite | Removes non-Anthropic assistant `reasoning` parts from the outbound prompt. Anthropic-native thinking history is preserved. |
63
+ | `anthropic-strip-foreign-signed-reasoning` | Anthropic-compatible | Preemptive prompt rewrite | Drops signed thinking from the outbound prompt when its origin turn was stamped with a different provider (for example Kimi For Coding ↔ `anthropic/claude-sonnet-4-6`), since the receiving provider can't verify another provider's signature. Turns emptied of all content by the drop are removed from the prompt. Unstamped history is left untouched. |
64
+ | `azure-system-reminder-transform` | Azure OpenAI | Preemptive prompt rewrite | Renames `<system-reminder>` wrappers in user text and system instructions to `<memory-context>` for the outbound request. Stored history remains unchanged. |
65
+ | `openai-orphan-item-id` | OpenAI, Azure OpenAI (Responses) | Reactive API error recovery | Recovers history that OpenAI rejects with `Item 'msg_…' of type 'message' was provided without its required 'reasoning' item`. Drops the Responses `itemId` from every item-bearing part of an assistant message that carries one but has no `reasoning` part, so the message replays by value instead of as an unsatisfiable `item_reference`, and retries. The repair is applied to the in-memory list for the current turn. |
57
66
 
58
67
  Preemptive rules run through `processLLMRequest` after Mastra converts messages to the model prompt format and before the prompt is sent to the provider. These rewrites affect only the current provider call.
59
68
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mastra/mcp-docs-server",
3
- "version": "1.2.27-alpha.17",
3
+ "version": "1.2.27-alpha.19",
4
4
  "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -27,7 +27,7 @@
27
27
  "@modelcontextprotocol/sdk": "^1.27.1",
28
28
  "local-pkg": "^1.1.2",
29
29
  "zod": "^4.6.4",
30
- "@mastra/core": "1.68.0-alpha.8"
30
+ "@mastra/core": "1.68.0-alpha.9"
31
31
  },
32
32
  "devDependencies": {
33
33
  "@hono/node-server": "^2.0.0",
@@ -42,9 +42,9 @@
42
42
  "tsx": "^4.23.1",
43
43
  "typescript": "^7.0.2",
44
44
  "vitest": "4.1.11",
45
+ "@internal/lint": "0.0.133",
45
46
  "@internal/types-builder": "0.0.108",
46
- "@mastra/core": "1.68.0-alpha.8",
47
- "@internal/lint": "0.0.133"
47
+ "@mastra/core": "1.68.0-alpha.9"
48
48
  },
49
49
  "homepage": "https://mastra.ai",
50
50
  "repository": {