Baltor Get started

Directory

Endpoints and local runtimes

194 hosted model services and 6 local runtimes: which API each speaks, how it takes a key, where its rate limits, prices and data rules are written, and how to set up OpenCode, Pi, Codex and Claude Code for it.

Hosted services

Services a person reviewed come first, in the order of the review, then the other services by name, then the local runtimes. Payment never changes the order or which services are listed.

A person read each of these services' documentation on the date its page shows.

183 more services that models.dev lists

These publish an OpenAI-compatible address. Their pages show only what models.dev records.

ServiceAddressModels
302.AIapi.302.ai/v1125
Abacusroutellm.abacus.ai/v1108
abliteration.aiapi.abliteration.ai/v13
above.devapi.above.dev/v110
AgentRouteragentrouter.org/v15
Agnes AIapihub.agnes-ai.com/v14
ai&api.aiand.com/v113
AI-ROUTERapi.ai-router.dev/v15
AI/ML APIapi.aimlapi.com/v1177
AI21 Labsapi.ai21.com/studio/v12
ainetcafemicroquickjs.com/v11
Aixyapi.aixy-gateway.com/v113
AKI.IOaki.io/v17
Alibabadashscope-intl.aliyuncs.com/compatible-mode/v159
Alibaba (China)dashscope.aliyuncs.com/compatible-mode/v191
Alibaba Coding Plancoding-intl.dashscope.aliyuncs.com/v110
Alibaba Coding Plan (China)coding.dashscope.aliyuncs.com/v110
Alibaba Token Plantoken-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v129
Alibaba Token Plan (China)token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v129
Ambientapi.ambient.xyz/v117
AMDdeveloper.amd.com.cn/radeon/api/v16
AnyAPIapi.anyapi.ai/v130
Arceeapi.arcee.ai/api/v17
Aurikoapi.auriko.ai/v115
Bailingapi.tbox.cn/api/llm/v12
Baseteninference.baseten.co/v126
Bee by HEOSSIapi.bee.heossi.com/bee6
Berget.AIapi.berget.ai/v16
Blue Clawopenai.blueclaw.network/v11
Bothubopenai.bothub.ru/v18
Boundlessapi.inference.boundless.network/v120
Charm Hyperhyper.charm.land/v123
Chutesllm.chutes.ai/v114
Clarifaiapi.clarifai.com/v2/ext/openai/v112
Claudinioapi.claudin.io/v12
ClinePassapi.cline.bot/api/v118
CloudFerro Sherlockapi-sherlock.cloudferro.com/openai/v15
Cloudflare Workers AIapi.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v128
CommandCodeapi.commandcode.ai/provider/v171
CoralBricksinference.coralbricks.ai/v11
CoreWeaveapi.inference.wandb.ai/v123
Cortecsapi.cortecs.ai/v1106
CrossModelapi.crossmodel.ai/v170
Crusoeapi.inference.crusoecloud.com/v111
D.Run (China)chat.d.run/v13
DaoXEdaoxe.com/v19
DeepSeekapi.deepseek.com4
DevPass (LLM Gateway)api.llmgateway.io/v1216
DigitalOceaninference.do-ai.run/v1103
DInferenceapi.dinference.com/v16
EBCloudmaas-api.ebcloud.com/v14
Echoecho.tracerml.ai/v11
Eden AIapi.edenai.run/v3343
EmpirioLabs AIapi.empiriolabs.ai/v163
engyapi.engy.ai/v19
evrocmodels.think.evroc.com/v116
FastRoutergo.fastrouter.ai/api/v147
Friendliapi.friendli.ai/serverless/v17
FrogBotapp.frogbot.ai/api/v126
GitHub Copilotapi.githubcopilot.com36
GMI Cloudapi.gmi-serving.com/v117
GreenPTapi.greenpt.ai/v140
Heliconeai-gateway.helicone.ai/v190
Hetznerinference.hetzner.com/api/v12
HPC-AIapi.hpc-ai.com/inference/v19
Hugging Facerouter.huggingface.co/v182
iFlowapis.iflow.cn/v114
Impossiblapi.impossibl.com/v176
Inceptionapi.inceptionlabs.ai/v14
Inceptronapi.inceptron.io/v14
Incoapi.inco.ai/v17
Inferenceinference.net/v19
InferXmodel.inferx.net/endpoints/v112
Infomaniakapi.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v110
IO.NETapi.intelligence.io.solutions/api/v117
IteraComputeapi.iteracompute.com/v110
Jalapeno Cloudapi.jalapeno-cloud.ai/v117
Jiekou.AIapi.jiekou.ai/openai61
Kenarikenari.id/v164
Kilo Gatewayapi.kilo.ai/api/gateway397
Kimi For Coding (kimi.ai)api.kimi.ai/coding/v14
Kimi For Coding (kimi.com)api.kimi.com/coding/v14
klokintegration.seapi-gw.klok.ipaas.se/proxy/kloker-key/v13
Kosmik Computeapi.koscompute.com/v11
KUAE Cloud Coding Plancoding-plan-endpoint.kuaecloud.net/v11
Lilacapi.getlilac.com/v14
Llamaapi.llama.com/compat/v17
LLM Gatewayapi.llmgateway.io/v1438
LLM Techapi.llmtech.eu/v11
LLMTRllmtr.com/v132
LongCatapi.longcat.chat/openai1
LowRouterapi.lowrouter.ai/v131
LucidQueryapi.lucidquery.com/v14
Meganovaapi.meganova.ai/v119
Meliousapi.melious.ai/v113
Mixlayermodels.mixlayer.ai/v15
Moarkmoark.com/v110
Modalinference.us-west.modal.direct/v14
Model Oracle AIapi.modeloracle.com/api/v115
Modelismodelishub.com/v19
ModelScopeapi-inference.modelscope.cn/v17
Moonshot AIapi.moonshot.ai/v14
Moonshot AI (China)api.moonshot.cn/v14
Morphapi.morphllm.com/v13
NaNapi.nan.builders/v18
NanoGPTnano-gpt.com/api/v1617
NEAR AI Cloudcloud-api.near.ai/v156
Nebius Token Factoryapi.tokenfactory.nebius.com/v124
Neuralwattapi.neuralwatt.com/v131
Novaapi.nova.amazon.com/v12
Novita AIapi.novita.ai/openai86
Nvidiaintegrate.api.nvidia.com/v1107
OCI Generative AIinference.generativeai.us-chicago-1.oci.oraclecloud.com/openai/v19
Ofoxapi.ofox.ai/v1154
OpenCodeopencode.ai/inference/openai/v1128
OpenCode Goopencode.ai/inference/go/openai/v133
OpenReasonapi.openreason.app/v13
Opperapi.opper.ai/v3/compat57
OrcaRouterapi.orcarouter.ai/v1117
OVHcloud AI Endpointsoai.endpoints.kepler.ai.cloud.ovh.net/v112
Pareto Inferenceapi.paretoinference.com/v11
Pendraapi.pendra.ai/api/v16
Pioneerapi.fastino.ai/v1117
Poeapi.poe.com/v1142
Poolsideinference.poolside.ai/v13
Prime Inferenceapi.pinference.ai/api/v168
QiHangapi.qhaigc.net/v19
Qiniuapi.qnaigc.com/v191
Reflectionapi.reflection.ai/openai/v11
Regolo AIapi.regolo.ai/v118
Requestyrouter.requesty.ai/v1180
routing.runapi.routing.run/v115
RunInfraapi.runinfra.ai/v18
Sakana AIapi.sakana.ai/v14
SambaNovaapi.sambanova.ai/v16
Sarvam AIapi.sarvam.ai/v12
Scalewayapi.scaleway.ai/v118
SCNet Token Planapi.scnet.cn/api/llm/v119
SCX.aiapi.scx.ai/v14
SenseNova (China)token.sensenova.cn/v16
SiliconFlowapi.siliconflow.com/v157
SiliconFlow (China)api.siliconflow.cn/v144
STACKITapi.openai-compat.model-serving.eu01.onstackit.cloud/v18
Standard Computeapi.stdcmpt.com/v140
StepFun (China)api.stepfun.com/v19
StepFun (Global)api.stepfun.ai/v19
StepFun Step Plan (China)api.stepfun.com/step_plan/v15
StepFun Step Plan (Global)api.stepfun.ai/step_plan/v14
submodelllm.submodel.ai/v19
Syntheticapi.synthetic.new/openai/v111
Tempr Gatewayapi.temprhq.io/v182
Tencent Coding Plan (China)api.lkeap.cloud.tencent.com/coding/v38
Tencent Token Planapi.lkeap.cloud.tencent.com/plan/v32
Tencent TokenHubtokenhub.tencentmaas.com/v13
TensorXapi.tensorx.ai/v125
The Grid AIapi.thegrid.ai/v116
Tinfoilinference.tinfoil.sh/v18
TokenGoapi.tokengo.com/v113
TokenRouterapi.tokenrouter.com/v11
TrustedRouterapi.trustedrouter.com/v17
Umans AIapi.code.umans.ai/v17
Umans AI Coding Planapi.code.umans.ai/v18
UnoRouterapi.unorouter.com/v123
Upstageapi.upstage.ai/v1/solar5
Vancinevancine.com/v18
Visparkapi.lab.vispark.in/v13
Volcengine Arkark.cn-beijing.volces.com/api/v316
Volcengine Ark Coding Planark.cn-beijing.volces.com/api/coding/v310
Vultrapi.vultrinference.com/v115
Waferpass.wafer.ai/v15
Wallabyapi.wallabytoken.com/v11
Xiaomiapi.xiaomimimo.com/v19
Xiaomi Token Plan (China)token-plan-cn.xiaomimimo.com/v19
Xiaomi Token Plan (Europe)token-plan-ams.xiaomimimo.com/v19
Xiaomi Token Plan (Singapore)token-plan-sgp.xiaomimimo.com/v19
Xpersonawww.xpersona.co/v113
Z.AIapi.z.ai/api/paas/v418
Z.AI Coding Planapi.z.ai/api/coding/paas/v47
Zeldocapi.zeldoc.ai/v11
Zenifraai.zenifra.com/v11
ZenMuxzenmux.ai/api/v1130
Zhipu AIopen.bigmodel.cn/api/paas/v417
Zhipu AI Coding Planopen.bigmodel.cn/api/coding/paas/v44

Local runtimes

Each runs models on your own hardware and answers on your own computer. The start command takes a model from its page.

  • Ollamagguf files

    OpenAI Chat Completions, OpenAI Responses, Anthropic Messages

    ollama run hf.co/{repository}:{quantization}
  • LM Studiogguf, mlx files

    OpenAI Chat Completions, OpenAI Responses, Anthropic Messages

    lms get {repository}
    lms server start
  • llama.cpp servergguf files

    OpenAI Chat Completions, OpenAI Responses, Anthropic Messages

    llama-server -hf {repository}:{quantization} --jinja
  • vLLMsafetensors files

    OpenAI Chat Completions, OpenAI Responses, Anthropic Messages

    vllm serve {huggingface_id}
  • SGLangsafetensors files

    OpenAI Chat Completions, Anthropic Messages

    sglang serve --model-path {huggingface_id} --port 30000
  • MLX LMmlx files

    OpenAI Chat Completions

    mlx_lm.server --model {mlx_repository}

What each harness reads

HarnessOpenAI Chat CompletionsOpenAI ResponsesAnthropic MessagesSource
OpenCodeReads itReads itNoDocumentation, read 2026-09-24
PiReads itReads itReads itDocumentation, read 2026-09-24
CodexNoReads itNoDocumentation, read 2026-09-24
Claude CodeNoNoReads itDocumentation, read 2026-09-24

Sources and dates

Every row keeps the address of each source it uses and the day it was read. A fact no source states is shown as Unknown. The directory republishes only sources whose licence or terms allow it. It was built on .

SourceWhat it givesLicence or termsRowsLast read
Hugging Face Hub APILicence, parameter count, publication date, downloads and task of open models, read within the API's published request limit.Terms of service; each model card declares its own licence, checked 2,0182026-10-20
Hugging Face model configurationsLayers, key and value heads, head size and context length, the numbers the memory formula needs.Terms of service, checked 8252026-10-20
Hugging Face GGUF file listsThe quantized files of a model and their sizes, from the GGUF copy its maker or the most downloaded copier publishes.Terms of service, checked 6072026-10-20
models.devProvider prices with each record's own date, the limits and capabilities of the makers' own APIs, release dates, and each provider's documented address and key variable.MIT, checked 8042026-10-20
LiteLLM model price and context fileProvider prices as listed on the day the file was read, and the input and output limits and tool calling, structured output and reasoning flags of the makers' own APIs.MIT, checked 3532026-10-20
LMArena leaderboard datasetThe overall text arena score with style control from the latest leaderboard, rounded to a whole number, for a hosted model the arena names with its maker's own identifier.CC BY 4.0, checked 692026-10-19
Baltor provider client recordsOutput limits that Baltor's own provider clients declare or observed, each with its day.Baltor's own record, checked 72026-09-04
Provider and runtime documentationAPI styles, authentication, structured output, tool calling, rate-limit, pricing and data-policy pages, read by a person on the day each fact names.Baltor's own record of each provider's public pages, checked 172026-09-27
Harness documentationHow OpenCode, Pi, Codex and Claude Code read a model provider, from each harness's own documentation.Baltor's own record of each harness's documentation, checked 0Unknown

Linked, never copied:

  • Ollama library: Linked only. Ollama's terms refuse automated access without permission, so no data is copied from it. Terms
  • OpenRouter: Linked only. OpenRouter's terms of August 31, 2026 forbid copying information on its site or services by script and using it for a competing service, so none of its prices, limits or rankings are copied here. It documents a Models API that your own tool can read with your own account. Terms
  • Artificial Analysis: Linked only. Its website terms allow only personal, noncommercial use, so none of its indexes, prices or speed measurements are copied here. Terms