llms.txt
# RunInfra
> RunInfra serves open models for agents and apps through OpenAI-compatible and Anthropic-compatible Model APIs at https://api.runinfra.ai/v1, billed per token. Setup guides connect coding agents such as Claude Code and Codex. Backed by Y Combinator.
## Model APIs
Model APIs is RunInfra's hosted model API product at https://api.runinfra.ai/v1. Each model publishes its operation and compatibility. Chat models expose OpenAI-compatible chat completions at POST /v1/chat/completions and Anthropic-compatible Messages at POST /v1/messages. Chat model requests use workspace API keys and support streaming. JSON mode is supported per chat model, and a model that requires a specific reasoning_effort to deliver it publishes that value with its capabilities. Pricing is published per model in USD with only the billed dimensions shown.
The entries below come from the hosted model registry. A registered model appears here only when its own public row passes the same publication gate used by the sitemap. Entries that do not pass that public gate are omitted.
- [Model API library](https://runinfra.ai/inference-api): available hosted models with their operation and compatibility contracts.
- [Nemotron 3.5 Lightning 30B Model API](https://runinfra.ai/inference-api/nemotron-3-5-lightning-30b): Served model ID: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.05 per 1M input tokens; $0.01 per 1M cached input tokens; $0.15 per 1M output tokens. Context window: 262,144 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text only.
- [Qwen3.8 27B Model API](https://runinfra.ai/inference-api/qwen3-8-27b): Served model ID: Qwen/Qwen3.8-27B. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.10 per 1M input tokens; $0.01 per 1M cached input tokens; $0.40 per 1M output tokens. Context window: 262,144 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text and images.
- [Ornith 1.5 35B Model API](https://runinfra.ai/inference-api/ornith-1-5-35b): Served model ID: ornith-ai/Ornith-1.5-35B-A3B. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.10 per 1M input tokens; $0.01 per 1M cached input tokens; $0.40 per 1M output tokens. Context window: 262,144 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text and images.
- [GLM 5.3 Flash Model API](https://runinfra.ai/inference-api/glm-5-3-flash): Served model ID: zai-org/GLM-5.3-Flash. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.11 per 1M input tokens; $0.03 per 1M cached input tokens; $0.45 per 1M output tokens. Context window: 1,048,576 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text and images.
- [DeepSeek V4.1 Flash Model API](https://runinfra.ai/inference-api/deepseek-v4-1-flash): Served model ID: deepseek-ai/DeepSeek-V4.1-Flash. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.14 per 1M input tokens; $0.03 per 1M cached input tokens; $0.58 per 1M output tokens. Context window: 1,048,576 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text only.
- [DeepSeek V4.1 Flash 1017 Model API](https://runinfra.ai/inference-api/deepseek-v4-1-flash-1017): Served model ID: deepseek-ai/DeepSeek-V4.1-Flash-1017. OpenAI-compatible chat completions: POST /v1/chat/completions. Anthropic-compatible Messages: POST /v1/messages. Published token pricing: $0.15 per 1M input tokens; $0.01 per 1M cached input tokens; $0.60 per 1M output tokens. Context window: 1,048,576 tokens. Published capabilities: Tool calling, JSON mode, Streaming. API access is available.
Accepted input: Text and images.
## Coding agents
- [Set up with your coding agent](https://runinfra.ai/docs/tools-sdks/agent-setup): Your coding agent sets up RunInfra's open models after you approve the sign-in and the changes it proposes.
Coding agents: Your coding agent sets up RunInfra's open models by following the agent setup guide. It shows the proposed changes, applies them only after approval, and verifies them with a real API request that counts toward workspace usage. The per-agent guides are references for configuration, compatibility limits and recovery.
### Set up RunInfra with your coding agent
Set up RunInfra's open models in this coding agent for me. Read https://runinfra.ai/docs/tools-sdks/agent-setup.md and follow it step by step. If you cannot open links, run `npx -y @runinfra/cli@latest --help` and follow its FOR CODING AGENTS section. I approve sign-in in my browser. Before you install anything, change this agent's settings or spend money, show me the plan and wait for my yes.
- [Claude Code](https://runinfra.ai/docs/tools-sdks/claude-code): Anthropic-compatible Messages setup and agent-specific guidance.
- [Codex](https://runinfra.ai/docs/tools-sdks/codex): Separate Codex command setup and Responses provider reference.
- [RightNow Agent](https://runinfra.ai/docs/tools-sdks/rightnow): Native RunInfra provider setup.
- [OpenCode](https://runinfra.ai/docs/tools-sdks/opencode): Provider and model setup guide.
- [Pi](https://runinfra.ai/docs/tools-sdks/pi): Provider and model setup guide.
- [Aider](https://runinfra.ai/docs/tools-sdks/aider): OpenAI-compatible configuration guide.
- [Qwen Code](https://runinfra.ai/docs/tools-sdks/qwen-code): Provider and model selection guide.
- [Kilo Code](https://runinfra.ai/docs/tools-sdks/kilo-code): Compatible provider configuration guide.
- [Goose](https://runinfra.ai/docs/tools-sdks/goose): Provider setup and credential handoff guide.
- [Continue](https://runinfra.ai/docs/tools-sdks/continue): Configuration and restart guidance.
- [Cline](https://runinfra.ai/docs/tools-sdks/cline): Provider setup and manual IDE verification.
- [Droid](https://runinfra.ai/docs/tools-sdks/droid): Personal model configuration and selection guide.
- [Zed](https://runinfra.ai/docs/tools-sdks/zed): Preview setup and manual credential handoff limitations.
- [Grok Build](https://runinfra.ai/docs/tools-sdks/grok-build): Provider and model picker guide.
- [Hermes](https://runinfra.ai/docs/tools-sdks/hermes): Custom provider setup guide.
- [OpenClaw](https://runinfra.ai/docs/tools-sdks/openclaw): Provider setup and model selection guide.
- [Crush](https://runinfra.ai/docs/tools-sdks/crush): Add RunInfra alongside your provider, with configuration and recovery references.
- [Docs MCP server](https://runinfra.ai/docs/mcp): Retrieve RunInfra documentation from an MCP client.
- [Docs MCP server card](https://runinfra.ai/docs/.well-known/mcp/server-card.json): Published documentation-server discovery metadata.
## Pricing
Pay as you go: Model API usage is billed per token at each model's published input, cached-input where configured, and output prices. Only the billed dimensions are shown. Check the model page for current availability and prices.
- [Pricing](https://runinfra.ai/pricing): current payment options.
- [Pricing docs](https://runinfra.ai/docs/introduction/plans): credits, top-ups, and usage billing.
### Coding plans
- [Coding plans](https://runinfra.ai/pricing#coding-plans): Starter: $10 a month. About $12 of usage a month, paced as $2.77 a week and $1.11 per 5 hours. Pro: $29 a month. About $35 of usage a month, paced as $8.08 a week and $3.23 per 5 hours. Team: $99 a month. About $119 of usage a month, paced as $27.46 a week and $10.98 per 5 hours. At a limit, keep full speed on credits (your choice: a cap, or no limit), then Standby, free and slower. Images and audio always stay pay as you go.
## Documentation
- [Docs](https://runinfra.ai/docs): Product documentation and integration guides.
- [Model APIs quickstart](https://runinfra.ai/docs/api-reference/model-apis-quickstart): Make a first call with a workspace API key.
- [Authentication](https://runinfra.ai/docs/api-reference/authentication): Workspace API keys and request authentication.
- [Chat Completions API reference](https://runinfra.ai/docs/api-reference/chat-completions): OpenAI-compatible chat request and response contract.
- [Anthropic Messages API reference](https://runinfra.ai/docs/api-reference/anthropic-messages): Anthropic-compatible request and response contract.
- [Model discovery](https://runinfra.ai/docs/api-reference/models): Discover model IDs and their published capabilities.
- [OpenAI compatibility](https://runinfra.ai/docs/tools-sdks/openai-compatibility): Chat Completions, Responses, client setup, and compatibility limits.
- [OpenAPI specification](https://runinfra.ai/docs/api-reference/openapi.json): Machine-readable API reference. Current product availability is listed on each model page.
- [Errors](https://runinfra.ai/docs/api-reference/errors): Error codes, causes, and recovery guidance.
- [Rate limits](https://runinfra.ai/docs/api-reference/rate-limits): Request limits and retry guidance.
- [Prompt caching](https://runinfra.ai/docs/cookbook/prompt-caching): Prompt reuse for agents, cache usage, and cached-input pricing.
- [Session affinity](https://runinfra.ai/docs/api-reference/session-affinity): Session routing and its limits for repeated agent requests.
- [Idempotent retries](https://runinfra.ai/docs/api-reference/idempotent-retries): Retry behavior and request identity.
- [Docs llms.txt](https://runinfra.ai/docs/llms.txt): Documentation index for agents, with Markdown page links.
- [Docs sitemap](https://runinfra.ai/docs/sitemap.xml): Canonical documentation pages.
## Evidence and methodology
- [Methodology](https://runinfra.ai/methodology): definitions, measurement conditions, sources, and limitations for published metrics.
- [Benchmarks](https://runinfra.ai/benchmarks): historical self-reported serving results with incomplete runtime and workload provenance, source and date beneath every chart. The source record belongs to the reported workload; historical results do not establish current Model API performance.
Published model pages own current prices, availability, context limits, and capabilities. Cache measurements describe their stated observation window, not a guaranteed result for a new workload.
### Capability boundaries
Model API availability and supported operations are listed on each model page. Technical references and benchmark results do not imply that other models or workflows are available as products.
## Optional
Reference material below retains its own scope, evidence, and dates; it does not expand the current product offering.
### Resources
- [Brand assets](https://runinfra.ai/brand-assets): official RunInfra logo downloads, brand colors and usage guidance.
- [Home](https://runinfra.ai): RunInfra's Model APIs overview and public technical reference surface.
- [Inference cost calculator](https://runinfra.ai/calc): server-rendered model fit plus GPU rent, paid idle capacity, API crossover, dated provider rates, and measured RunInfra evidence only when the required source rows exist. Missing economics stay absent, and a result can recommend staying on the API when that is the lower-cost choice.
- [Benchmarks](https://runinfra.ai/benchmarks): measured optimization receipts from real GPU runs, with the statistic, source record, and date beneath every chart.
- [RunInfra for Startups](https://runinfra.ai/startups): an application-based program offering Model API credits subject to approval, a working session with the founding team, and support for shipping open models.
- [Changelog](https://runinfra.ai/docs/changelog): product release notes.
### Measured GPU, technique, engine, and model pages
Historical serving references with their own evidence, conditions, and dates. Family indexes: [GPU](https://runinfra.ai/gpu), [Techniques](https://runinfra.ai/optimization), [Engines](https://runinfra.ai/engines), and [Models](https://runinfra.ai/model).
- [NVIDIA B300 measured results](https://runinfra.ai/gpu/b300): Kimi K3, with baseline and optimized latency, throughput, accuracy evidence, and proof dates.
- [NVIDIA H100 measured results](https://runinfra.ai/gpu/h100): AREX-Turbo, Qwen3.6 27B, Qwythos-9B-Claude-Mythos-5-1M, with baseline and optimized latency, throughput, accuracy evidence, and proof dates.
- [Channelwise FP8 weights, dynamic per-token activations measured results](https://runinfra.ai/optimization/fp8-channel-dynamic): AREX-Turbo, Qwythos-9B-Claude-Mythos-5-1M, with measured speed and accuracy recovery on the same protocol as each baseline.
- [Channelwise FP8, measured selective-layer recipe measured results](https://runinfra.ai/optimization/fp8-channel-dynamic-s2): Qwen3.6 27B, with measured speed and accuracy recovery on the same protocol as each baseline.
- [SGLang measured results](https://runinfra.ai/engines/sglang): measured comparison rows with conditions and limitations; no published package yet, stated honestly.
- [TensorRT-LLM measured results](https://runinfra.ai/engines/tensorrt-llm): measured comparison rows with conditions and limitations; no published package yet, stated honestly.
- [vLLM measured results](https://runinfra.ai/engines/vllm): measured comparison rows with conditions and limitations; 4 published packages with measured baseline and optimized numbers.
- [AREX-Turbo measured packages](https://runinfra.ai/model/baai-arex-turbo): 1 published package on H100, with publication and proof dates.
- [Qwythos-9B-Claude-Mythos-5-1M measured packages](https://runinfra.ai/model/empero-ai-qwythos-9b-claude-mythos-5-1m): 1 published package on H100, with publication and proof dates.
- [Kimi K3 measured packages](https://runinfra.ai/model/moonshotai-kimi-k3): 1 published package on B300, with publication and proof dates.
- [Qwen3.6 27B measured packages](https://runinfra.ai/model/qwen-qwen3-6-27b): 1 published package on H100, with publication and proof dates.
- [NVIDIA A100 40GB rate and capacity](https://runinfra.ai/gpu/a100-40gb): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA A100 80GB rate and capacity](https://runinfra.ai/gpu/a100-80gb): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA A10G rate and capacity](https://runinfra.ai/gpu/a10g): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA B200 rate and capacity](https://runinfra.ai/gpu/b200): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA H200 rate and capacity](https://runinfra.ai/gpu/h200): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA L4 rate and capacity](https://runinfra.ai/gpu/l4): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA L40S rate and capacity](https://runinfra.ai/gpu/l40s): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [NVIDIA T4 rate and capacity](https://runinfra.ai/gpu/t4): RunInfra hourly rate and capacity facts; no measured optimization package is published for this GPU yet.
- [vllm vs sglang](https://runinfra.ai/compare/vllm-vs-sglang): measured engine comparison on one GPU, one model, with the as-of date and every limitation stated.
- [vllm vs tensorrt llm](https://runinfra.ai/compare/vllm-vs-tensorrt-llm): measured engine comparison on one GPU, one model, with the as-of date and every limitation stated.
- [sglang vs tensorrt llm](https://runinfra.ai/compare/sglang-vs-tensorrt-llm): measured engine comparison on one GPU, one model, with the as-of date and every limitation stated.
### Model reference pages
Vendor-cited specifications and source dates. A reference does not establish current Model API availability.
- [DeepSeek-V4-Pro-0813 reference](https://runinfra.ai/model/deepseek-v4-pro-0813): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Qwen3.8-2.4T-A95B reference](https://runinfra.ai/model/qwen-qwen3-8-2-4t-a95b): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [NVIDIA Nemotron 3.5 Lightning 30B-A3B reference](https://runinfra.ai/model/nvidia-nvidia-nemotron-3-5-lightning-30b-a3b-bf16): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; published Model API details and current availability at https://runinfra.ai/inference-api/nemotron-3-5-lightning-30b; no measured optimization package is published.
- [DeepSeek-V4-Flash-0731 reference](https://runinfra.ai/model/deepseek-ai-deepseek-v4-flash-0731): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Gemma 4 31B reference](https://runinfra.ai/model/google-gemma-4-31b-it): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [gpt-oss-120b reference](https://runinfra.ai/model/openai-gpt-oss-120b): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Llama 4 Maverick reference](https://runinfra.ai/model/meta-llama-llama-4-maverick-17b-128e-instruct): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [GLM-5.2 reference](https://runinfra.ai/model/zai-org-glm-5-2): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Mistral Medium 3.5 reference](https://runinfra.ai/model/mistralai-mistral-medium-3-5-128b): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Muse Glimmer 30B reference](https://runinfra.ai/model/meta-models-muse-glimmer-30b): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [Hy3 reference](https://runinfra.ai/model/tencent-hy3): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [MiniMax H3 reference](https://runinfra.ai/model/minimaxai-minimax-h3): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [GPT-5.6 Sol reference](https://runinfra.ai/model/gpt-5-6-sol): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
- [MiMo-V2.5 reference](https://runinfra.ai/model/xiaomimimo-mimo-v2-5): vendor-cited specifications, license, availability, and serving status with source links and as-of dates; not yet measured by RunInfra.
### Inference serving glossary
Definitions of serving mechanisms and metrics, with links to the pages that own any measurements.
- [Glossary index](https://runinfra.ai/glossary): all entries grouped by category.
### Research
- [Research index](https://runinfra.ai/research): papers by the RunInfra team on inference efficiency and model architectures, wit
