Models reference

Model Provider Tokenizes Structured Output Reasoning Verbosity Built-in Web Tools
qwen-long aliyun Text json (schema) — — —
qwen-max aliyun Text, Vision json (object) — — —
qwen-plus aliyun Text, Vision json (object) — — —
qwen-turbo aliyun Text, Vision json (object) — — —
qwen3-max aliyun Text json (schema) — — —
anthropic.claude-3-5-haiku anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-5-sonnet anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-7-sonnet anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: anthropic.claude-3-7-sonnet?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-haiku anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-opus anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-sonnet-20240229 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-3-sonnet anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
anthropic.claude-haiku-4-5-20251001 anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: anthropic.claude-haiku-4-5-20251001?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-3-5-haiku-20241022 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-3-5-sonnet-20240620 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-3-5-sonnet-20241022 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-3-7-sonnet-20250219 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: claude-3-7-sonnet-20250219?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-3-opus-20240229 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-opus-4-0 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: claude-opus-4-0?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-opus-4-20250514 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: claude-opus-4-20250514?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-sonnet-4-20250514 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: claude-sonnet-4-20250514?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude-sonnet-4-5-20250929 anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: claude-sonnet-4-5-20250929?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
claude anthropic Text, Vision, Document json (schema) effort: auto, low, medium, high, max, off
Example: claude.auto		 — web_search (web_search_20260209)
web_fetch (web_fetch_20260209)
beta: code-execution-web-tools-2026-02-09
haiku35 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
haiku3 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
haiku anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: haiku?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
opus3 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
opus45 anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: opus45?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
opus4 anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: opus4?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
opus anthropic Text, Vision, Document json (schema) effort: auto, low, medium, high, max, off
Example: opus.auto		 — web_search (web_search_20260209)
web_fetch (web_fetch_20260209)
beta: code-execution-web-tools-2026-02-09
sonnet35 anthropic Text, Vision, Document tool_use — — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
sonnet37 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: sonnet37?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
sonnet45 anthropic Text, Vision, Document json (schema) budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: sonnet45?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
sonnet4 anthropic Text, Vision, Document tool_use budget: low, medium, high, max, 0, 1024, 16000, 32000, off
Example: sonnet4?reasoning=1024		 — web_search (web_search_20250305)
web_fetch (web_fetch_20250910)
codexspark codexresponses Text json (schema) — — —
deepseek deepseek Text json (schema) — — —
passthrough fast-agent Text json (schema) — — —
playback fast-agent Text json (schema) — — —
silent fast-agent Text json (schema) — — —
slow fast-agent Text json (schema) — — —
gemini-2.5-flash-preview-05-20 google Text, Vision, Document, Audio, Video json (schema) — — —
gemini-2.5-pro-preview-05-06 google Text, Vision, Document, Audio, Video json (schema) — — —
gemini25 google Text, Vision, Document, Audio, Video json (schema) — — —
gemini25pro google Text, Vision, Document, Audio, Video json (schema) — — —
gemini2 google Text, Vision, Document, Audio, Video json (schema) — — —
gemini3 google Text, Vision, Document, Audio, Video json (schema) — — —
gemini3flash google Text, Vision, Document, Audio, Video json (schema) — — —
google.gemini-2.5-flash-preview google Text, Vision, Document, Audio, Video json (schema) — — —
google.gemini-2.5-flash google Text, Vision, Document, Audio, Video json (schema) — — —
google.gemini-2.5-pro-preview google Text, Vision, Document, Audio, Video json (schema) — — —
groq.deepseek-r1-distill-llama-70b groq Text json (object) — — —
groq.moonshotai/kimi-k2-thinking-0905 groq Text json (object) — — —
groq.moonshotai/kimi-k2 groq Text json (object) — — —
groq.qwen/qwen3-32b groq Text json (object) — — —
kimi groq Text json (object) — — —
kimithink groq Text json (object) — — —
deepseek31 hf Text json (schema) — — —
deepseek32 hf Text json (schema) — — —
glm47 hf Text json (object) toggle: on, off
Example: glm47?reasoning=off		 — —
glm hf Text json (object) toggle: on, off
Example: glm?reasoning=off		 — —
gpt-oss-20b hf Text json (object) — — —
gpt-oss hf Text json (object) — — —
hf.minimaxai/minimax-m2 hf Text json (object) — — —
hf.zai-org/glm-4.6 hf Text json (object) — — —
kimi25 hf Text, Vision json (schema) toggle: on, off
Example: kimi25?reasoning=off		 — —
minimax hf Text json (object) — — —
qwen3 hf Text json (schema) — — —
gpt-4.1-mini openai Text, Vision, Document json (schema) — — —
gpt-4.1-nano openai Text, Vision, Document json (schema) — — —
gpt-4.1 openai Text, Vision, Document json (schema) — — —
gpt-4o openai Text, Vision, Document json (schema) — — —
openai.gpt-4.1-2025-04-14 openai Text, Vision, Document json (schema) — — —
openai.gpt-4.1-mini-2025-04-14 openai Text, Vision, Document json (schema) — — —
openai.gpt-4.1-nano-2025-04-14 openai Text, Vision, Document json (schema) — — —
openai.gpt-4o-2024-11-20 openai Text, Vision, Document json (schema) — — —
openai.gpt-4o-mini-2024-07-18 openai Text, Vision, Document json (schema) — — —
codex responses Text, Vision, Document json (schema) effort: low, medium, high, xhigh
Example: codex.medium		 low, medium, high
Example: codex?verbosity=low		 —
codexplan responses Text, Vision, Document json (schema) effort: low, medium, high, xhigh
Example: codexplan.medium		 low, medium, high
Example: codexplan?verbosity=low		 —
gpt-5-mini responses Text, Vision, Document json (schema) effort: minimal, low, medium, high
Example: gpt-5-mini.medium		 low, medium, high
Example: gpt-5-mini?verbosity=low		 —
gpt-5-nano responses Text, Vision, Document json (schema) effort: minimal, low, medium, high
Example: gpt-5-nano.medium		 low, medium, high
Example: gpt-5-nano?verbosity=low		 —
gpt-5.1-codex responses Text, Vision, Document json (schema) effort: low, medium, high, xhigh
Example: gpt-5.1-codex.medium		 low, medium, high
Example: gpt-5.1-codex?verbosity=low		 —
gpt-5 responses Text, Vision, Document json (schema) effort: minimal, low, medium, high
Example: gpt-5.medium		 low, medium, high
Example: gpt-5?verbosity=low		 —
gpt51 responses Text, Vision, Document json (schema) effort: none, low, medium, high, xhigh, off
Example: gpt51.medium		 low, medium, high
Example: gpt51?verbosity=low		 —
gpt52 responses Text, Vision, Document json (schema) effort: minimal, low, medium, high
Example: gpt52.medium		 low, medium, high
Example: gpt52?verbosity=low		 —
o1 responses Text, Vision json (schema) effort: minimal, low, medium, high, xhigh
Example: o1.medium		 — —
o3-mini responses Text json (schema) effort: low, medium, high
Example: o3-mini.medium		 — —
o3 responses Text, Vision, Document json (schema) effort: low, medium, high
Example: o3.medium		 — —
o4-mini responses Text, Vision, Document json (schema) effort: low, medium, high
Example: o4-mini.medium		 — —
responses.o1-2024-12-17 responses Text, Vision json (schema) effort: minimal, low, medium, high, xhigh
Example: responses.o1-2024-12-17.medium		 — —
responses.o3-2025-04-16 responses Text, Vision, Document json (schema) effort: low, medium, high
Example: responses.o3-2025-04-16.medium		 — —
responses.o3-mini-2025-01-31 responses Text json (schema) effort: low, medium, high
Example: responses.o3-mini-2025-01-31.medium		 — —
responses.o3-pro responses Text json (schema) — — —
responses.o4-mini-2025-04-16 responses Text, Vision, Document json (schema) effort: low, medium, high
Example: responses.o4-mini-2025-04-16.medium		 — —
grok-3-fast xai Text json (schema) — — —
grok-3-mini-fast xai Text json (schema) — — —
grok-3-mini xai Text json (schema) — — —
grok-3 xai Text json (schema) — — —
grok-4-0709 xai Text json (schema) — — —
grok-4-fast-reasoning xai Text, Vision json (schema) — — —
grok-4-fast xai Text, Vision json (schema) — — —
grok-4 xai Text json (schema) — — —