> ## Documentation Index > Fetch the complete documentation index at: https://internal.september.wtf/llms.txt > Use this file to discover all available pages before exploring further. # Models and pricing > Models the Engine supports and what they cost. The Engine is provider-agnostic. You pick which LLM provider runs your agent at deployment time via `LLM_PROVIDER` and `LLM_MODEL`. This page covers what's supported, what we recommend, and where to find current pricing. ## Providers Three providers are supported today: | `LLM_PROVIDER` | Provider | Notes | | -------------- | ------------- | ----------------------------------------------------------------------------------------- | | `anthropic` | Anthropic | Default for production agentic workloads. Strong tool use, long thinking, prompt caching. | | `openai` | OpenAI | Default for OpenAI-shaped APIs. Strong structured outputs, fast streaming. | | `gemini` | Google Gemini | Long context (1M+ tokens), multimodal-first, cost-efficient. | You can also point at OpenAI-compatible endpoints (any provider that implements OpenAI's chat completions API) by setting `LLM_PROVIDER=openai` and adjusting the base URL — see the engine repo for configuration. ## Models we test against The Engine is tested against the following models per Engine version: ### Anthropic * `claude-opus-4-7` — flagship, for the hardest reasoning. * `claude-sonnet-4-7` — recommended default. Strong, fast, cost-aware. * `claude-sonnet-4-6` / `claude-sonnet-4-5` — prior generations, still supported. * `claude-haiku-4-5-20251001` — small, fast, cheap. Good for planners, light tasks, classification. ### OpenAI * `gpt-5.5` — flagship. * `gpt-5.4` — strong default. * `gpt-5.4-mini` — small, cheap, fast. ### Google Gemini * `gemini-2.5-pro` — flagship, 2M context. * `gemini-2.5-flash` — fast, cost-efficient. The Engine doesn't enforce the model identifiers — you can set `LLM_MODEL` to any string the provider accepts. But we test against the above; behavior on other models is best-effort. ## Recommended setups ### Production agentic deployment ``` LLM_PROVIDER=anthropic LLM_MODEL=claude-sonnet-4-7 PLANNER_MODEL=claude-haiku-4-5-20251001 LIGHT_MODEL=claude-haiku-4-5-20251001 FALLBACK_MODEL=claude-sonnet-4-6 ``` The Sonnet 4.7 default handles the main loop. The Haiku planner and light model keep cost down on planning and compaction. Sonnet 4.6 as fallback covers the case where 4.7 has a transient issue. ### Cost-optimized ``` LLM_PROVIDER=anthropic LLM_MODEL=claude-haiku-4-5-20251001 PLANNER_MODEL=claude-haiku-4-5-20251001 LIGHT_MODEL=claude-haiku-4-5-20251001 ``` Haiku 4.5 across the board. Cheaper, faster, lower quality on hard tasks. Good for high-volume, throughput-bound workloads. ### Long-context ``` LLM_PROVIDER=gemini LLM_MODEL=gemini-2.5-pro PLANNER_MODEL=gemini-2.5-flash LIGHT_MODEL=gemini-2.5-flash ``` Gemini 2.5 Pro's 2M-token context shines for tasks that need to load entire codebases, long PDFs, or huge transcripts. Flash for the supporting agents. ## Embeddings Regardless of which chat provider you choose, embeddings always route through OpenAI's embedding model: ``` EMBEDDING_PROVIDER=openai EMBEDDING_MODEL=text-embedding-3-small EMBEDDING_DIM=1536 ``` You need an OpenAI API key (`OPENAI_API_KEY`) even on Anthropic or Gemini deployments. The Engine doesn't yet support embeddings from other providers. ## Pricing Prices change. We don't try to keep numbers up-to-date here — they're authoritatively at: * Anthropic — [docs.claude.com/en/docs/about-claude/pricing](https://docs.claude.com/en/docs/about-claude/pricing) * OpenAI — [openai.com/pricing](https://openai.com/api/pricing) * Google Gemini — [ai.google.dev/pricing](https://ai.google.dev/pricing) Order-of-magnitude as of 2026: | Model class | Input (\$/M tokens) | Output (\$/M tokens) | | --------------------------------------- | ------------------- | -------------------- | | Flagship (Opus, GPT-5.5, Gemini Pro) | \$15 | \$75 | | Mid (Sonnet, GPT-5.4, Gemini 2.5 Flash) | \$3 | \$15 | | Small (Haiku, GPT-5.4-mini) | \$0.80 | \$4 | | Embeddings | \$0.02 | — | Cache hits typically save 70–90% on the cached input portion. ## Choosing per workload The Engine doesn't pick a model per call automatically. Use these heuristics to pick at deployment time: | Workload | Suggested | | ------------------------------------------ | ----------------------------------- | | Coding agent, long sessions, complex tasks | Sonnet 4.7 main + Haiku 4.5 planner | | Customer support, common-questions tier | Haiku 4.5 | | Customer support, escalations | Sonnet 4.7 | | Research / synthesis from long sources | Gemini 2.5 Pro | | High-throughput classification | Haiku 4.5 / GPT-5.4-mini | | Document drafting, long-form writing | Opus 4.7 / Sonnet 4.7 | For workloads that span profiles (e.g., a single product with both classification and drafting), run multiple Engine instances with different model configurations and route at the application layer. ## Switching models Models are chosen at deployment time. To switch: 1. Update `.env` with the new `LLM_MODEL`. 2. Restart the Engine. 3. Run regression evals against the new configuration. 4. Watch cost and latency for a few hundred turns. Behavior shifts subtly across model versions. Same provider, same prompt — different verbosity, different willingness to call tools. Plan to retune system prompts when you change models. ## See also * [Cost and latency](../build-with-engine/cost-and-latency) — managing spend. * [Environment variables](../../operations/config/env-vars#llm-provider-and-models) — the variables that set the model. * [Regression](../test-and-evaluate/regression) — checking behavior across model changes.