A reasoning model works through a problem in intermediate reasoning tokens before it writes its final answer. This improves results on multi-step tasks such as math, code and planning, uses more output tokens and time, and settings such as reasoning effort control it.
A standard language model starts writing its answer immediately. A reasoning model first generates a sequence of intermediate steps, often called thinking, and then writes the answer. During that phase it can break a problem into parts, work through calculations, test an approach and correct itself before it commits to a result.
Reasoning is a capability rather than a separate type of model. A text model can also be a reasoning model, and many let you turn reasoning on or off for each request. Some models always reason, and on those you can usually adjust how much.
Reasoning improves results on tasks with several dependent steps:
It adds little to simple lookups, classification, short rewrites or casual conversation, where it mostly adds latency and output tokens. For those tasks, lower the effort or turn reasoning off.
Prompts for reasoning models work best when they state the goal, the constraints and the expected format of the answer, and leave the planning to the model. Detailed step-by-step instructions are usually unnecessary, because working out the steps is what the reasoning phase does.
EmpirioLabs AI exposes three controls, and each model accepts the ones listed for it on this page:
reasoning_effort sets the depth with named levels such as low, medium and high. On many models, none turns reasoning off. The available levels differ by model.thinking_budget sets the most tokens the model may spend on reasoning when thinking is on. When you leave it out, many models decide for themselves how long to reason.enable_thinking switches reasoning on or off on models that offer the choice.These parameters are accepted on /v1/chat/completions, /v1/responses and /v1/messages for models that support each endpoint. On /v1/messages you can also send a thinking object: enabled with budget_tokens sets a budget, adaptive turns thinking on without one, and disabled turns it off. On some models, a request that uses response_format or forces a tool call answers without reasoning unless it sets enable_thinking. See model parameters across endpoints for details.
Reasoning is generated text, so it is billed even when you never see it. On most models reasoning tokens bill as output tokens, and each model page states how. Some models return the reasoning text, for example in reasoning_content on Chat Completions, while others return only the answer. On /v1/responses, usage.output_tokens_details.reasoning_tokens reports how many were used. On some models, preserve_thinking sends the reasoning of earlier assistant turns back to the model on /v1/chat/completions, and that earlier reasoning bills as input tokens.
Reasoning also counts toward output limits. max_completion_tokens caps reasoning and answer together, and on some models max_tokens does too. When the limit is too low, the model can spend it on reasoning and return a short or empty answer, so leave room for both.
Higher effort also means a longer wait before the answer begins. Stream the response to show progress, and for a response that runs longer than 15 minutes, use the WebSocket mode of /v1/responses. Compare reasoning-capable text models, or try different effort levels in the Playground.
65 models. Each model's page has its rate card, parameters and code.
| Model | Parameter | Range / values |
|---|---|---|
| DeepSeek V4 Flash 0731 DeepSeek | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 393216; default 32768 enable_thinking: default true |
| DeepSeek V4 Pro DeepSeek | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 393216; default 32768 enable_thinking: default true |
| DeepSeek V4 Pro 0813 DeepSeek | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 393216; default 32768 enable_thinking: default true |
| DeepSeek V4.1 Flash 1017 DeepSeek | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 393216; default 32768 enable_thinking: default true |
| GLM 5.1 Z.ai | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 38912; default 32768 enable_thinking: default true |
| Gemma 4 26B-A4B Google | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 128 to 32768; default 4096 enable_thinking: default true |
| Kimi K2.6 Moonshot AI | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 81920; default 32768 enable_thinking: default true |
| Qwen3.5 122B-A10B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 81920 enable_thinking: default true |
| Model | Parameter | Range / values |
|---|---|---|
| Qwen3.5 27B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 81920 enable_thinking: default true |
| Qwen3.5 35B-A3B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 81920 enable_thinking: default true |
| Qwen3.5 397B-A17B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 81920 enable_thinking: default true |
| Qwen3.5 4B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1024 to 32768; default 4096 enable_thinking: default true |
| Qwen3.5 9B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1024 to 32768; default 4096 enable_thinking: default true |
| Qwen3.6 27B Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 131072 enable_thinking: default true |
| Qwen3.6 Flash Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max; default medium thinking_budget: 1 to 64000; default 32768 enable_thinking: default true |
| Qwen3.6 Plus Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 131072 enable_thinking: default true |
| Qwen3.7 Flash Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 131072 enable_thinking: default true |
| Qwen3.7 Max Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen3.7 Plus Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen3.8 Flash Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen3.8 Max Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen3.8 Max 0902 Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen3.8 Omni Flash Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: none, low, medium, high, max thinking_budget: 1 to 262144 enable_thinking: default true |
| Qwen4 Max Alibaba Cloud | reasoning_effort thinking_budget enable_thinking | reasoning_effort: low, high, xhigh; default high thinking_budget: 1 to 262144 enable_thinking: default true |
| GLM 5.2 Z.ai | reasoning_effort enable_thinking | reasoning_effort: none, minimal, low, medium, high, xhigh, max; default max enable_thinking: default true |
| Kimi K3.1 Pro Moonshot AI | reasoning_effort enable_thinking | reasoning_effort: low, medium, high, max; default max enable_thinking: default true |
| Nova Lite 2 Amazon | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default medium enable_thinking: default true |
| Qwen3.5 Flash Alibaba Cloud | thinking_budget enable_thinking | thinking_budget: 1 to 81920 enable_thinking: default true |
| Qwen3.5 Plus Alibaba Cloud | thinking_budget enable_thinking | thinking_budget: 1 to 81920 enable_thinking: default true |
| Qwen3.6 35B A3B Alibaba Cloud | reasoning_effort enable_thinking | reasoning_effort: none, low, medium, high, max; default medium enable_thinking: default true |
| Qwen3.8 27B Alibaba Cloud | reasoning_effort enable_thinking | reasoning_effort: none, low, medium, xhigh; default xhigh enable_thinking: default true |
| Seed 2.0 Code ByteDance | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default medium enable_thinking: default true |
| Seed 2.0 Lite ByteDance | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default medium enable_thinking: default true |
| Seed 2.0 Mini ByteDance | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default medium enable_thinking: default true |
| Seed 2.0 Pro ByteDance | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default medium enable_thinking: default true |
| Seed 2.1 Turbo ByteDance | reasoning_effort enable_thinking | reasoning_effort: low, medium, high; default high enable_thinking: default true |
| Fugu Max Sakana AI | reasoning_effort | high, xhigh, max; default high |
| Fugu Ultra v1.0 Sakana AI | reasoning_effort | high, xhigh, max; default high |
| Fugu Ultra v1.1 Sakana AI | reasoning_effort | high, xhigh, max; default high |
| Fugu Ultra v2.0 Sakana AI | reasoning_effort | high, xhigh, max; default high |
| GLM 4.5 Flash Z.ai | enable_thinking | default true |
| GLM 4.6V Flash Z.ai | enable_thinking | default true |
| GLM 4.6V FlashX Z.ai | enable_thinking | default true |
| GLM 4.7 Flash Z.ai | enable_thinking | default true |
| GLM 4.7 FlashX Z.ai | enable_thinking | default true |
| GLM 5.3 Z.ai | reasoning_effort | low, high, max; default max |
| GLM 5.3 Flash Z.ai | reasoning_effort | low, high, max; default max |
| Gemini 3.8 Live Extended Thinking Google | reasoning_effort | low, medium, high; default medium |
| Kimi K3 Moonshot AI | reasoning_effort | low, high, max; default max |
| MiMo V2.6 Flash Xiaomi | enable_thinking | default true |
| MiMo V2.6 Pro Xiaomi | enable_thinking | default true |
| MiMo V2.6 Pro UltraSpeed Xiaomi | enable_thinking | default true |
| MiniMax M3 MiniMax | enable_thinking | default true |
| MiniMax M3.1 Flash MiniMax | reasoning_effort | low, medium, high, xhigh, max; default max |
| Muse Glimmer 30B Meta AI | reasoning_effort | none, low, medium, high, max; default high |
| Muse Spark 1.1 Meta AI | reasoning_effort | minimal, low, medium, high, xhigh; default medium |
| Muse Spark 1.2 Meta AI | reasoning_effort | minimal, low, medium, high, xhigh; default medium |
| Muse Spark 1.3 Meta AI | reasoning_effort | minimal, low, medium, high, xhigh; default medium |
| Perplexity Advanced Deep Research Perplexity | reasoning_effort | low, medium, high; default medium |
| Perplexity Deep Research Perplexity | reasoning_effort | low, medium, high; default medium |
| Perplexity Pro Search Perplexity | reasoning_effort | minimal, low, medium, high; default minimal |
| Perplexity Sonar Reasoning Pro Perplexity | reasoning_effort | low, medium, high; default medium |
| Step 3.5 Flash 2603 StepFun | reasoning_effort | low, high; default low |
| Step 3.7 Flash StepFun | reasoning_effort | low, medium, high; default low |
| Step 5 Preview StepFun | reasoning_effort | low, medium, high; default low |
Yes. Reasoning is generated text, so it is billed even when the model does not return it. On most models it bills as output tokens, and each model page states how.
On many models, yes: set enable_thinking to false or reasoning_effort to none, depending on which control the model offers. Some models always reason and only let you change the effort level.
reasoning_effort picks a named level of depth, such as low or high. thinking_budget sets a maximum number of tokens for reasoning when thinking is on.
When the output limit is too low, the model can spend all of it on reasoning. Raise max_completion_tokens or max_tokens, or lower the reasoning effort, so room remains for the answer.
Check out our pricing or reach out if you want your own model deployed on our stack.