Baltor Get started

Endpoints

AI/ML API

A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.

Addresses and facts

  • OpenAI Chat Completions: https://api.aimlapi.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in AIMLAPI_API_KEY models.dev, read
Structured output
Unknown
Tool calling
148 of 177 listed models The share of this provider's models that models.dev records with tool calling. models.dev, read
Rate limits
Unknown
Prices
Unknown
Data retention
Unknown
Documentation
Read the page models.dev, read
Output limits Baltor recorded
Unknown

Harness setup

Replace aion-labs/aion-rp-llama-3.1-8b with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "aimlapi": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AI/ML API",
      "options": {
        "baseURL": "https://api.aimlapi.com/v1",
        "apiKey": "{env:AIMLAPI_API_KEY}"
      },
      "models": {
        "aion-labs/aion-rp-llama-3.1-8b": {
          "name": "aion-labs/aion-rp-llama-3.1-8b"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "aimlapi": {
      "baseUrl": "https://api.aimlapi.com/v1",
      "api": "openai-completions",
      "apiKey": "$AIMLAPI_API_KEY",
      "models": [
        {
          "id": "aion-labs/aion-rp-llama-3.1-8b"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and AI/ML API documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and AI/ML API documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Models it lists

Prices in US dollars per million tokens, input and output, as models.dev, read records them.

ModelInputOutputContextAs of
Aion-RP 1.0 (8B) aion-labs/aion-rp-llama-3.1-8b1.10 USD2.20 USD32,768 older than 30 days
Qwen Max alibaba/qwen-max2.08 USD8.32 USD32,000 older than 30 days
Qwen Plus alibaba/qwen-plus0.520 USD1.56 USD131,000 older than 30 days
Qwen3 Coder alibaba/qwen3-coder-480b-a35b-instruct1.38 USD6.71 USD262,000
Qwen3 Next 80B A3B Instruct alibaba/qwen3-next-80b-a3b-instruct0.206 USD1.65 USD129,024
Qwen3.8 2.4T A95B alibaba/qwen3.8-2.4t-a95b3.44 USD8.60 USD262,144 older than 30 days
Qwen3.8 27B alibaba/qwen3.8-27b0.619 USD4.40 USD262,144 older than 30 days
Qwen3.8 Flash alibaba/qwen3.8-flash0.208 USD0.611 USD1,000,000 older than 30 days
Qwen3.8 Max alibaba/qwen3.8-max2.60 USD7.80 USD1,000,000 older than 30 days
Qwen3.8 Max Prime alibaba/qwen3.8-max-prime5.50 USD16.50 USD1,000,000
Nova Lite 1.0 amazon/nova-lite-v10.083 USD0.330 USD300,000 older than 30 days
Nova Micro 1.0 amazon/nova-micro-v10.048 USD0.193 USD128,000 older than 30 days
Nova Pro 1.0 amazon/nova-pro-v11.10 USD4.40 USD300,000 older than 30 days
Magnum v4 72B anthracite-org/magnum-v4-72b4.13 USD6.88 USD32,000 older than 30 days
Claude Fable 5 anthropic/claude-fable-513.00 USD65.00 USD1,000,000 older than 30 days
Claude Fable 5.1 anthropic/claude-fable-5.113.00 USD65.00 USD1,000,000 older than 30 days
Claude 4.5 Haiku anthropic/claude-haiku-4.51.38 USD6.88 USD200,000 older than 30 days
Claude Haiku 5.5 anthropic/claude-haiku-5.50.130 USD0.650 USD1,000,000
Claude 4.5 Opus anthropic/claude-opus-4.56.88 USD34.38 USD200,000 older than 30 days
Claude 4.7 Opus anthropic/claude-opus-4.76.88 USD34.38 USD1,000,000 older than 30 days
Claude 4.8 Opus anthropic/claude-opus-4.86.88 USD34.38 USD1,000,000 older than 30 days
Claude Opus 5 anthropic/claude-opus-56.50 USD32.50 USD1,000,000 older than 30 days
Claude Opus 5.5 anthropic/claude-opus-5.55.20 USD26.00 USD1,000,000
Claude 4.5 Sonnet anthropic/claude-sonnet-4.54.13 USD20.63 USD200,000 older than 30 days
Claude 4.6 Sonnet anthropic/claude-sonnet-4.64.13 USD20.63 USD200,000 older than 30 days
Claude Sonnet 5 anthropic/claude-sonnet-52.60 USD13.00 USD1,000,000 older than 30 days
Claude Sonnet 5.5 anthropic/claude-sonnet-5.52.60 USD13.00 USD1,000,000
Seed 1.6 Flash bytedance-seed/seed-1.6-flash0.103 USD0.413 USD262,144 older than 30 days
Seed-2.0-Code bytedance-seed/seed-2.0-code0.688 USD4.13 USD262,144 older than 30 days
Seed-2.0-Lite bytedance-seed/seed-2.0-lite0.344 USD2.75 USD262,144 older than 30 days
Seed-2.0-Mini bytedance-seed/seed-2.0-mini0.138 USD0.550 USD262,144 older than 30 days
Venice Uncensored cognitivecomputations/dolphin-mistral-24b-venice-edition0.275 USD1.24 USD128,000 older than 30 days
Command A cohere/command-a3.44 USD13.75 USD256,000 older than 30 days
Command R (08-2024) cohere/command-r-08-20240.206 USD0.825 USD128,000 older than 30 days
Command R+ (08-2024) cohere/command-r-plus-08-20243.44 USD13.75 USD128,000 older than 30 days
Command R7B (12-2024) cohere/command-r7b-12-20240.052 USD0.206 USD128,000 older than 30 days
DeepSeek V4 Flash deepseek/deepseek-chat0.390 USD1.56 USD1,000,000 older than 30 days
DeepSeek V3 deepseek/deepseek-chat-v3-03240.399 USD1.57 USD128,000 older than 30 days
DeepSeek V4 Flash deepseek/deepseek-v4-flash0.390 USD1.56 USD1,000,000 older than 30 days
DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp0.572 USD1.72 USD1,048,576 older than 30 days
DeepSeek V4 Pro deepseek/deepseek-v4-pro1.17 USD3.51 USD1,000,000 older than 30 days
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-08132.39 USD4.79 USD1,048,576 older than 30 days
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash0.390 USD1.56 USD1,048,576 older than 30 days
Gemini 3.8 Flash google/gemini-3-8-flash0.975 USD4.88 USD1,048,576 older than 30 days
Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview0.344 USD2.06 USD1,000,000 older than 30 days
Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview2.60 USD15.60 USD1,000,000 older than 30 days
Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-customtools2.75 USD16.50 USD1,048,756 older than 30 days
Gemini 3.6 Flash google/gemini-3.6-flash1.95 USD9.75 USD1,048,576 older than 30 days
Gemini 3.7 Flash google/gemini-3.7-flash0.975 USD4.88 USD1,048,576 older than 30 days
Gemini 3.8 Flash google/gemini-3.8-flash0.975 USD4.88 USD1,048,576 older than 30 days
Gemini Flash Latest google/gemini-flash-latest2.06 USD12.38 USD1,048,576 older than 30 days
Gemma 2 27B google/gemma-2-27b-it0.894 USD0.894 USD8,192 older than 30 days
Gemma 3 12B google/gemma-3-12b-it0.069 USD0.206 USD131,000 older than 30 days
Gemma 3 27B google/gemma-3-27b-it0.206 USD0.633 USD128,000 older than 30 days
Gemma 3 4B google/gemma-3-4b-it0.069 USD0.138 USD131,000 older than 30 days
Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it0.206 USD0.825 USD262,144 older than 30 days
Gemma 4 31B Instruct google/gemma-4-31b-it1.36 USD2.05 USD256,000 older than 30 days
MythoMax 13B gryphe/mythomax-l2-13b2.58 USD2.58 USD4,096 older than 30 days
Granite 4.0 Micro ibm-granite/granite-4.0-h-micro0.023 USD0.154 USD131,000 older than 30 days
Mercury 2 inception/mercury-20.344 USD1.03 USD128,000 older than 30 days
Mercury 2.5 inception/mercury-2.50.275 USD1.03 USD260,000 older than 30 days
Schematron V2 Small inference-net/schematron-v2-small0.069 USD0.316 USD128,000 older than 30 days
Schematron V2 Turbo inference-net/schematron-v2-turbo0.041 USD0.206 USD128,000 older than 30 days
Weaver (alpha) mancer/weaver1.03 USD1.38 USD8,000 older than 30 days
Llama 3.3 70B Instruct Turbo meta-llama/Llama-3.3-70B-Instruct-Turbo1.35 USD1.35 USD128,000 older than 30 days
Muse Glimmer 30B meta/muse-glimmer-30b0.481 USD2.06 USD131,072 older than 30 days
Muse Spark 1.1 meta/muse-spark-1.11.72 USD5.85 USD1,048,576 older than 30 days
Muse Spark 1.2 meta/muse-spark-1.21.72 USD5.85 USD1,048,576 older than 30 days
Muse Spark 1.3 meta/muse-spark-1.31.72 USD5.85 USD1,048,576 older than 30 days
Codestral 2508 mistralai/codestral-25080.413 USD1.24 USD256,000 older than 30 days
Devstral 2 2512 mistralai/devstral-25120.605 USD3.03 USD262,144 older than 30 days
Ministral 3 14B 2512 mistralai/ministral-14b-25120.481 USD0.481 USD262,144 older than 30 days
Ministral 3 3B 2512 mistralai/ministral-3b-25120.206 USD0.206 USD131,072 older than 30 days
Ministral 3 8B 2512 mistralai/ministral-8b-25120.413 USD0.413 USD262,144 older than 30 days
Large mistralai/mistral-large2.75 USD8.25 USD128,000 older than 30 days
Large 2407 mistralai/mistral-large-24072.75 USD8.25 USD131,072 older than 30 days
Medium 3 mistralai/mistral-medium-30.550 USD2.75 USD131,072 older than 30 days
Medium 3.5 mistralai/mistral-medium-3-52.06 USD10.32 USD262,144 older than 30 days
Medium 3.1 mistralai/mistral-medium-3.10.550 USD2.75 USD131,072 older than 30 days
Mistral NeMo mistralai/mistral-nemo0.206 USD0.234 USD128,000 older than 30 days
Saba mistralai/mistral-saba0.275 USD0.825 USD32,768 older than 30 days
Small 3 mistralai/mistral-small-24b-instruct-25010.069 USD0.110 USD32,768 older than 30 days
Small 4 mistralai/mistral-small-26030.258 USD1.03 USD262,144 older than 30 days
Small 3.1 24B mistralai/mistral-small-3.1-24b-instruct0.483 USD0.763 USD128,000 older than 30 days
Small 3.2 24B mistralai/mistral-small-3.2-24b-instruct0.103 USD0.275 USD128,000 older than 30 days
Mixtral 8x22B Instruct mistralai/mixtral-8x22b-instruct2.75 USD8.25 USD65,536 older than 30 days
Voxtral Small 24B 2507 mistralai/voxtral-small-24b-25070.138 USD0.413 USD32,000 older than 30 days
Kimi K3 moonshot/kimi-k33.90 USD19.50 USD1,048,576 older than 30 days
Kimi K2 0711 moonshotai/kimi-k20.784 USD3.16 USD131,072 older than 30 days
Kimi K2 0905 moonshotai/kimi-k2-09051.38 USD4.13 USD262,144 older than 30 days
Kimi K2 Thinking moonshotai/kimi-k2-thinking0.825 USD3.44 USD262,144 older than 30 days
V3 Fast morph/morph-v3-fast1.10 USD1.65 USD81,920 older than 30 days
V3 Large morph/morph-v3-large1.24 USD2.61 USD262,144 older than 30 days
Hermes 3 405B Instruct nousresearch/hermes-3-llama-3.1-405b1.38 USD1.38 USD131,072 older than 30 days
Hermes 3 70B Instruct nousresearch/hermes-3-llama-3.1-70b0.963 USD0.963 USD131,072 older than 30 days
GPT-3.5 Turbo openai/gpt-3.5-turbo0.650 USD1.95 USD16,000 older than 30 days
GPT-4 openai/gpt-439.00 USD78.00 USD8,000 older than 30 days
GPT-4 Turbo openai/gpt-4-turbo13.00 USD39.00 USD128,000 older than 30 days
GPT-4.1 openai/gpt-4.12.60 USD10.40 USD1,047,576 older than 30 days
GPT-4.1 Mini openai/gpt-4.1-mini0.520 USD2.08 USD1,000,000 older than 30 days
GPT-4.1 Nano openai/gpt-4.1-nano0.130 USD0.520 USD1,000,000 older than 30 days
GPT-4o openai/gpt-4o3.25 USD13.00 USD128,000 older than 30 days
GPT-4o openai/gpt-4o-2024-05-136.50 USD19.50 USD128,000 older than 30 days
GPT-4o openai/gpt-4o-2024-08-063.25 USD13.00 USD128,000 older than 30 days
GPT-4o openai/gpt-4o-2024-11-203.25 USD13.00 USD128,000 older than 30 days
GPT-4o Mini openai/gpt-4o-mini0.195 USD0.780 USD128,000 older than 30 days
GPT-5 openai/gpt-51.62 USD13.00 USD400,000 older than 30 days
GPT-5.1 openai/gpt-5-11.62 USD13.00 USD400,000 older than 30 days
GPT-5.2 openai/gpt-5-22.27 USD18.20 USD400,000 older than 30 days
GPT-5.4 openai/gpt-5-43.25 USD19.50 USD1,050,000 older than 30 days
GPT-5.5 openai/gpt-5-56.50 USD39.00 USD1,050,000 older than 30 days
GPT-5 Mini openai/gpt-5-mini0.325 USD2.60 USD400,000 older than 30 days
GPT-5 Nano openai/gpt-5-nano0.065 USD0.520 USD400,000 older than 30 days
GPT-5 Pro openai/gpt-5-pro20.63 USD165.05 USD400,000 older than 30 days
GPT-5.1-Codex-Max openai/gpt-5.1-codex-max3.44 USD27.51 USD400,000 older than 30 days
GPT-5.2 Pro openai/gpt-5.2-pro28.88 USD231.07 USD400,000 older than 30 days
GPT-5.3 Codex openai/gpt-5.3-codex4.81 USD38.51 USD400,000 older than 30 days
GPT-5.4 Image 2 openai/gpt-5.4-image-211.00 USD20.63 USD272,000 older than 30 days
GPT-5.4 Mini openai/gpt-5.4-mini2.06 USD12.38 USD400,000 older than 30 days
GPT-5.4 Nano openai/gpt-5.4-nano0.275 USD1.72 USD400,000 older than 30 days
GPT-5.4 Pro openai/gpt-5.4-pro41.26 USD247.57 USD1,050,000 older than 30 days
GPT-5.5 Pro openai/gpt-5.5-pro41.26 USD247.57 USD1,050,000 older than 30 days
GPT-5.6 Luna openai/gpt-5.6-luna0.260 USD1.56 USD1,050,000 older than 30 days
GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro0.275 USD1.65 USD1,050,000 older than 30 days
GPT-5.6 Sol openai/gpt-5.6-sol5.20 USD26.00 USD1,050,000 older than 30 days
GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro5.50 USD27.51 USD1,050,000 older than 30 days
GPT-5.6 Terra openai/gpt-5.6-terra2.60 USD15.60 USD1,050,000 older than 30 days
GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro2.75 USD16.50 USD1,050,000 older than 30 days
GPT-6 Astra openai/gpt-6-astra13.00 USD65.00 USD1,050,000 older than 30 days
GPT-6 Luna openai/gpt-6-luna0.130 USD0.650 USD1,050,000
GPT-6 Sol openai/gpt-6-sol2.60 USD13.00 USD1,050,000
GPT-6.1 Sol openai/gpt-6.1-sol2.60 USD13.00 USD1,050,000
GPT OSS 120B openai/gpt-oss-120b0.481 USD1.31 USD131,000 older than 30 days
GPT OSS 20B openai/gpt-oss-20b0.103 USD0.413 USD131,000 older than 30 days
gpt-oss-safeguard-20b openai/gpt-oss-safeguard-20b0.103 USD0.413 USD131,072 older than 30 days
o1 openai/o119.50 USD78.00 USD128,000 older than 30 days
o1-pro openai/o1-pro206.31 USD825.24 USD200,000 older than 30 days
o3 Mini openai/o3-mini1.43 USD5.72 USD200,000 older than 30 days
o3 Pro openai/o3-pro27.51 USD110.03 USD200,000 older than 30 days
Sonar perplexity/sonar1.30 USD1.30 USD128,000 older than 30 days
Sonar Pro perplexity/sonar-pro3.90 USD19.50 USD200,000 older than 30 days
Reka Edge rekaai/reka-edge0.138 USD0.138 USD16,384 older than 30 days
Apply 3 relace/relace-apply-31.17 USD1.72 USD256,000 older than 30 days
Search relace/relace-search1.38 USD4.13 USD256,000 older than 30 days
Fugu Max sakana/fugu-max2.75 USD8.25 USD1,000,000 older than 30 days
Fugu Ultra sakana/fugu-ultra6.88 USD41.26 USD1,000,000 older than 30 days
Fugu Ultra v2 sakana/fugu-ultra-v26.88 USD41.26 USD1,000,000 older than 30 days
Llama 3 8B Lunaris sao10k/l3-lunaris-8b0.069 USD0.069 USD8,192 older than 30 days
Llama 3.1 Euryale 70B v2.2 sao10k/l3.1-euryale-70b1.99 USD1.99 USD131,072 older than 30 days
Llama 3.3 Euryale 70B sao10k/l3.3-euryale-70b0.894 USD1.03 USD131,072 older than 30 days
Step 5 Preview stepfun/step-5-preview1.38 USD3.71 USD1,000,000
Hy-MT2-1.8B tencent/hy-mt2-1.8b0.061 USD0.243 USD8,192 older than 30 days
Hy-MT2-30B-A3B tencent/hy-mt2-30b-a3b0.102 USD0.406 USD8,192 older than 30 days
Hy-MT2-7B tencent/hy-mt2-7b0.102 USD0.406 USD8,192 older than 30 days
Hy3 tencent/hy30.275 USD1.10 USD262,144 older than 30 days
Hy4 preview tencent/hy4-preview1.15 USD3.44 USD1,048,576 older than 30 days
Cydonia 24B V4.1 thedrummer/cydonia-24b-v4.10.413 USD0.688 USD131,072 older than 30 days
Skyfall 36B V2 thedrummer/skyfall-36b-v20.756 USD1.10 USD32,768 older than 30 days
UnslopNemo 12B thedrummer/unslopnemo-12b0.550 USD0.550 USD32,768 older than 30 days
Inkling thinkingmachines/inkling1.38 USD5.57 USD1,048,576 older than 30 days
Inkling Small thinkingmachines/inkling-small0.798 USD1.98 USD524,288 older than 30 days
Pareto unbiased/pareto3.44 USD10.32 USD262,144 older than 30 days
ReMM SLERP 13B undi95/remm-slerp-l2-13b0.688 USD1.03 USD6,144 older than 30 days
Solar Pro 3 upstage/solar-pro-30.206 USD0.825 USD128,000
Solar Pro 4 upstage/solar-pro40.041 USD0.165 USD524,288 older than 30 days
Grok 4.20 Non-Reasoning x-ai/grok-4-20-0309-non-reasoning1.62 USD3.25 USD2,000,000 older than 30 days
Grok 4 Fast Non-Reasoning x-ai/grok-4-fast-non-reasoning1.62 USD3.25 USD2,000,000 older than 30 days
MiMo V2.5 xiaomi/mimo-v2.50.193 USD0.385 USD1,000,000 older than 30 days
MiMo V2.5 Pro xiaomi/mimo-v2.5-pro0.598 USD1.20 USD1,000,000 older than 30 days
GLM 4.5V z-ai/glm-4.5v0.825 USD2.48 USD65,536 older than 30 days
GLM 4.6V z-ai/glm-4.6v0.413 USD1.24 USD131,072 older than 30 days
GLM 4.7 Flash z-ai/glm-4.7-flash0.172 USD0.688 USD202,752 older than 30 days
GLM 5 Turbo z-ai/glm-5-turbo1.56 USD5.20 USD262,144 older than 30 days
GLM 5.3 Flash z-ai/glm-5.3-flash0.195 USD0.650 USD1,048,576 older than 30 days
GLM 5V Turbo z-ai/glm-5v-turbo1.56 USD5.20 USD202,752 older than 30 days
GLM 5.2 zhipu/glm-5.21.82 USD5.72 USD1,000,000 older than 30 days
GLM 5.3 zhipu/glm-5.31.82 USD5.72 USD1,024,000 older than 30 days

Sources of this page