Model Metadata
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
Provider Variants 11
amazon-bedrock openai.gpt-5.4
Context 1,000,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; cache: implicit: min_tokens: 1,024; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 1,000,000; output: 128,000
- id
- openai.gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-06-01
- api
- responses: base_url: https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1; sdk: aisdk: @ai-sdk/amazon-bedrock/mantle; opencodeai: @opencode/ai/providers/amazon-bedrock/mantle/responses; capabilities: system_updates: Yes; tools: updates: Yes; chat-completions: base_url: https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1; sdk: aisdk: @ai-sdk/amazon-bedrock/mantle; opencodeai: @opencode/ai/providers/amazon-bedrock/mantle/chat; capabilities: tools: updates: No
azure gpt-5.4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; cache: implicit: ttl: 24h; min_tokens: 1,024; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No; store: Yes; service_tier: priority
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- responses: base_url: https://${AZURE_RESOURCE_NAME}.openai.azure.com/openai/v1; sdk: aisdk: @ai-sdk/azure; opencodeai: @opencode/ai/providers/azure/responses; capabilities: tools: strict: Yes; choice: auto, none, required, tool; search: Yes; freeform: text, lark; updates: Yes; chat-completions: base_url: https://${AZURE_RESOURCE_NAME}.openai.azure.com/openai/v1; sdk: aisdk: @ai-sdk/azure; opencodeai: @opencode/ai/providers/azure/chat; capabilities: tools: strict: Yes; choice: auto, none, required, tool; freeform: text, lark; updates: No
- experimental
- modes: fast: service_tier: priority; body: service_tier: priority
cloudflare-ai-gateway openai/gpt-5.4
Context 1,000,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; cache: implicit: ttl: 24h; min_tokens: 1,024; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No
- limit
- context: 1,000,000; input: 922,000; output: 128,000
- id
- openai/gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- responses: base_url: https://gateway.ai.cloudflare.com/v1/${CLOUDFLARE_ACCOUNT_ID}/${CLOUDFLARE_GATEWAY_ID}/openai; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/cloudflare-ai-gateway; capabilities: tools: strict: Yes; choice: auto, none, required, tool; search: Yes; freeform: text, lark, regex; updates: Yes; chat-completions: base_url: https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/cloudflare-ai-gateway; capabilities: tools: strict: Yes; choice: auto, none, required, tool; freeform: text, lark, regex; updates: No
databricks databricks-gpt-5-4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: low, medium, high; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No; store: No; service_tier: priority
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- databricks-gpt-5-4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- chat-completions: base_url: https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; compatibility: max_tokens_field: max_tokens; capabilities: tools: updates: No; responses: base_url: https://${DATABRICKS_HOST}/serving-endpoints; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No
- experimental
- modes: fast: service_tier: priority; body: service_tier: priority
github-copilot gpt-5.4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- status
- deprecated
- api
- responses: base_url: https://api.githubcopilot.com; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai/responses; capabilities: tools: updates: No
model-oracle-ai gpt-5.4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: minimal, low, medium, high; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- chat-completions: base_url: https://api.modeloracle.com/api/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; capabilities: tools: updates: No
OpenAI gpt-5.4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; cache: implicit: ttl: 24h; min_tokens: 1,024; structured_output: Yes; temperature: Yes; system_updates: Yes; effort_updates: No; store: Yes; prompt_cache_key: Yes; service_tier: flex, priority
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- responses: base_url: https://api.openai.com/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai/responses; capabilities: tools: strict: Yes; choice: auto, none, required, tool; search: Yes; freeform: text, lark, regex; updates: Yes; chat-completions: base_url: https://api.openai.com/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai/chat; capabilities: tools: strict: Yes; choice: auto, none, required, tool; freeform: text, lark, regex; updates: No
- experimental
- modes: fast: service_tier: priority; body: service_tier: priority
opencode gpt-5.4
Context 1,050,000 · Output 128,000
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- responses: base_url: https://opencode.ai/inference/openai/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai/responses; capabilities: tools: strict: Yes; choice: auto, none, required, tool; search: Yes; freeform: text, lark, regex; updates: Yes
OpenRouter openai/gpt-5.4
Context 1,050,000 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- GPT-5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high, xhigh; cache: implicit: min_tokens: 1,024; structured_output: Yes; temperature: No; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- openai/gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- chat-completions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @openrouter/ai-sdk-provider; opencodeai: @opencode/ai/providers/openrouter; capabilities: tools: choice: auto, none, required, tool; updates: No; responses: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: choice: auto, none, required, tool; updates: Yes; messages: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, none, required, tool; updates: No
vercel openai/gpt-5.4
Context 1,050,000 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- GPT 5.4
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, xhigh; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- openai/gpt-5.4
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- chat-completions: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/gateway; opencodeai: @opencode/ai/providers/vercel-ai-gateway; capabilities: tools: choice: auto, none, required, tool; updates: Yes; responses: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/open-responses; opencodeai: @opencode/ai/providers/vercel-ai-gateway/responses; capabilities: tools: choice: auto, none, required, tool; updates: Yes; messages: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/vercel-ai-gateway/messages; capabilities: tools: choice: auto, none, required, tool; updates: No
vercel openai/gpt-5.4-fast
Context 1,050,000 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- GPT 5.4 (Fast)
- description
- Agent-ready GPT for coding and computer-use workflows at a lower cost
- family
- gpt
- open weights
- No
- knowledge
- 2025-08-31
- release date
- 2026-03-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, xhigh; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: Yes; effort_updates: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- openai/gpt-5.4-fast
- canonical id
- openai/gpt-5.4
- type
- chat
- last updated
- 2026-03-05
- api
- chat-completions: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/gateway; opencodeai: @opencode/ai/providers/vercel-ai-gateway; capabilities: tools: choice: auto, none, required, tool; updates: Yes; responses: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/open-responses; opencodeai: @opencode/ai/providers/vercel-ai-gateway/responses; capabilities: tools: choice: auto, none, required, tool; updates: Yes; messages: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/vercel-ai-gateway/messages; capabilities: tools: choice: auto, none, required, tool; updates: No