o3 on AvalAI

Available on AvalAI

Publisher

OpenAI

Available AvalAI IDs

1

Provider and configuration variants

3

Available AvalAI IDsUse through AvalAIAvalAI pricesProvider namespaces and configurationsProvider reference pricesCapabilities and limitsTechnical reference observations

Model Explorer

Available AvalAI IDs

Exact callable model IDs

Model ID	Operation	Supported endpoints	Minimum tier
o3	"chat"	["/v1/responses","/v1/chat/completions","/v1/completions"]	2

Unknown means unrecorded. null is an explicit unknown value; false means lack of support. A reference namespace does not establish which provider AvalAI uses.

Use through AvalAI

• /v1/chat/completions
• /v1/responses

Use the guide for this exact ID’s supported endpoint. An unrecorded endpoint cannot supply a verified request example.

AvalAI prices

These are recorded AvalAI charges. Each row retains its exact model ID, billing unit, and qualifiers.

AvalAI prices by exact charge field

Covered exact IDs	Charge field	Amount	Unit	Currency / role / modality	Configuration and qualifiers	Source
o3	Cached text input pricing.cached_input	0.5	USD/1M tokens	USD / cached-input / text	—	AvalAI catalog
o3	Text input pricing.input	2.0	USD/1M tokens	USD / input / text	—	AvalAI catalog
o3	Text output pricing.output	8.0	USD/1M tokens	USD / output / text	—	AvalAI catalog
o3	Source charge search_context_cost_per_query	{"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}	Unit not verified	Unknown / Unknown / Unknown	—	AvalAI catalog

Provider namespaces and configurations

Namespaces and regions describe the reference IDs and do not confirm AvalAI routing. Different qualified billing units are not directly comparable.

Exact namespaces and configuration axes

Variant	Exact ID	Identity and configuration	AvalAI availability
V1	azure/o3	{"axes":{},"hostingProvider":"azure","region":null}	Reference only
V2	o3	{"axes":{},"hostingProvider":null,"region":null}	Available on AvalAI
V3	vercel_ai_gateway/openai/o3	{"axes":{},"hostingProvider":"vercel_ai_gateway","region":null}	Reference only

Provider reference prices

{"currency":"USD","modality":"text","normalizationStatus":"normalized","source":"primary-reference","sourcePath":"data/rate-limits/model_prices_and_context_window.json","unit":"USD/token"}

F1 — Cached text input{"billingRole":"cached-input","field":"cache_read_input_token_cost","qualifiers":{}}

F2 — Text input{"billingRole":"input","field":"input_cost_per_token","qualifiers":{}}

F3 — Text output{"billingRole":"output","field":"output_cost_per_token","qualifiers":{}}

F4 — Cached text input{"billingRole":"cached-input","field":"cache_read_input_token_cost_flex","qualifiers":{"executionMode":"flex"}}

F5 — Cached text input{"billingRole":"cached-input","field":"cache_read_input_token_cost_priority","qualifiers":{"executionMode":"priority"}}

F6 — Text input{"billingRole":"input","field":"input_cost_per_token_batches","qualifiers":{"executionMode":"batches"}}

F7 — Text input{"billingRole":"input","field":"input_cost_per_token_flex","qualifiers":{"executionMode":"flex"}}

F8 — Text input{"billingRole":"input","field":"input_cost_per_token_priority","qualifiers":{"executionMode":"priority"}}

F9 — Text output{"billingRole":"output","field":"output_cost_per_token_batches","qualifiers":{"executionMode":"batches"}}

F10 — Text output{"billingRole":"output","field":"output_cost_per_token_flex","qualifiers":{"executionMode":"flex"}}

F11 — Text output{"billingRole":"output","field":"output_cost_per_token_priority","qualifiers":{"executionMode":"priority"}}

F12 — Source charge{"billingRole":"cache-creation-input","field":"cache_creation_input_token_cost","qualifiers":{}}

Source-qualified charges

Source-qualified charges

Charge field	Amount	Variants
F1	5e-07	V1
F2	2e-06	V1
F3	8e-06	V1
F1	5e-07	V2
F4	2.5e-07	V2
F5	8.75e-07	V2
F2	2e-06	V2
F6	1e-06	V2
F7	1e-06	V2
F8	3.5e-06	V2
F3	8e-06	V2
F9	4e-06	V2
F10	4e-06	V2
F11	1.4e-05	V2
F12	0.0	V3
F1	5e-07	V3
F2	2e-06	V3
F3	8e-06	V3

{"billingRole":null,"currency":null,"modality":null,"normalizationStatus":"opaque","qualifiers":{},"source":"primary-reference","sourcePath":"data/rate-limits/model_prices_and_context_window.json","unit":null}

F1 — Source charge{"field":"search_context_cost_per_query"}

Source-qualified charges — Unit not verified

Source-qualified charges — Unit not verified

Charge field	Amount	Variants
F1	{"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}	V2

Unit not verified means the source value is retained without interpretation and cannot be compared as a price. null does not mean free.

Capabilities and limits

Exact AvalAI capabilities and context

Field	Value	Covered IDs	Source
max_input_tokens	200000	V2	AvalAI catalog
max_output_tokens	100000	V2	AvalAI catalog
max_requests_per_1_minute	5000.0	V2	AvalAI catalog
max_tokens	100000	V2	AvalAI catalog
max_tokens_per_1_minute	4000000.0	V2	AvalAI catalog
min_tier	2	V2	AvalAI catalog
mode	"chat"	V2	AvalAI catalog
object	"model"	V2	AvalAI catalog
owned_by	"openai"	V2	AvalAI catalog
supported_endpoints	["/v1/responses","/v1/chat/completions","/v1/completions"]	V2	AvalAI catalog
supports_function_calling	true — Supported	V2	AvalAI catalog
supports_parallel_function_calling	false — Unsupported	V2	AvalAI catalog
supports_pdf_input	true — Supported	V2	AvalAI catalog
supports_prompt_caching	true — Supported	V2	AvalAI catalog
supports_reasoning	true — Supported	V2	AvalAI catalog
supports_response_schema	true — Supported	V2	AvalAI catalog
supports_tool_choice	true — Supported	V2	AvalAI catalog
supports_vision	true — Supported	V2	AvalAI catalog
supports_web_search	true — Supported	V2	AvalAI catalog

Rate limits and account access by exact ID

Model ID	Tier	Access	RPM	TPM	Other limits	Source
V2	0	No access	Unknown	Unknown	—	Unrecorded
V2	1	No access	Unknown	Unknown	—	Unrecorded
V2	2	Available	500.0	200000.0	{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_tokens_per_1_day":2147483647.0,"owner":"openai","provider":"openai"}	Exact tier source
V2	3	Available	2500.0	800000.0	{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_tokens_per_1_day":2147483647.0,"owner":"openai","provider":"openai"}	Exact tier source
V2	4	Available	3500.0	2000000.0	{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_tokens_per_1_day":2147483647.0,"owner":"openai","provider":"openai"}	Exact tier source
V2	5	Available	5000.0	4000000.0	{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_tokens_per_1_day":2147483647.0,"owner":"openai","provider":"openai"}	Exact tier source

Technical reference observations

The sources below are independent and may disagree. Their observations do not override AvalAI prices, capabilities, or supported endpoints.

{"source":"primary-reference","sourcePath":"data/rate-limits/model_prices_and_context_window.json"}

V1

{"deprecation_date":"2026-11-19","litellm_provider":"azure","max_input_tokens":200000,"max_output_tokens":100000,"max_tokens":100000,"mode":"chat","supported_endpoints":["/v1/chat/completions","/v1/batch","/v1/responses"],"supported_modalities":["text","image"],"supported_output_modalities":["text"],"supports_function_calling":true,"supports_parallel_function_calling":false,"supports_prompt_caching":true,"supports_reasoning":true,"supports_response_schema":true,"supports_tool_choice":true,"supports_vision":true}

{"source":"primary-reference","sourcePath":"data/rate-limits/model_prices_and_context_window.json"}

V2

{"litellm_provider":"openai","max_input_tokens":200000,"max_output_tokens":100000,"max_tokens":100000,"mode":"chat","source":"https://developers.openai.com/api/docs/pricing","supported_endpoints":["/v1/responses","/v1/chat/completions","/v1/completions","/v1/batch"],"supported_modalities":["text","image"],"supported_output_modalities":["text"],"supports_function_calling":true,"supports_parallel_function_calling":false,"supports_pdf_input":true,"supports_prompt_caching":true,"supports_reasoning":true,"supports_response_schema":true,"supports_tool_choice":true,"supports_vision":true,"supports_web_search":true}

{"source":"primary-reference","sourcePath":"data/rate-limits/model_prices_and_context_window.json"}

V3

{"litellm_provider":"vercel_ai_gateway","max_input_tokens":200000,"max_output_tokens":100000,"max_tokens":100000,"mode":"chat","supports_function_calling":true,"supports_response_schema":true,"supports_tool_choice":true,"supports_vision":true}

{"sourcePath":"data/rate-limits/tier2.json","tier":2,"values":{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_requests_per_1_minute":500.0,"max_tokens_per_1_day":2147483647.0,"max_tokens_per_1_minute":200000.0,"owner":"openai","provider":"openai"}}V2

{"sourcePath":"data/rate-limits/tier3.json","tier":3,"values":{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_requests_per_1_minute":2500.0,"max_tokens_per_1_day":2147483647.0,"max_tokens_per_1_minute":800000.0,"owner":"openai","provider":"openai"}}V2

{"sourcePath":"data/rate-limits/tier4.json","tier":4,"values":{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_requests_per_1_minute":3500.0,"max_tokens_per_1_day":2147483647.0,"max_tokens_per_1_minute":2000000.0,"owner":"openai","provider":"openai"}}V2

{"sourcePath":"data/rate-limits/tier5.json","tier":5,"values":{"max_audio_megabytes_per_1_minute":null,"max_images_per_1_minute":null,"max_requests_per_1_day":null,"max_requests_per_1_minute":5000.0,"max_tokens_per_1_day":2147483647.0,"max_tokens_per_1_minute":4000000.0,"owner":"openai","provider":"openai"}}V2