Model Metadata
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 262,144; output: 32,768
- weights
- label: Hugging Face; url: https://huggingface.co/google/gemma-4-26B-A4B-it
Provider Variants 10
amazon-bedrock google.gemma-4-26b-a4b
Context 262,144 · Output 32,768
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif, video; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, high; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No; service_tier: flex, priority
- limit
- context: 262,144; output: 32,768
- id
- google.gemma-4-26b-a4b
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- api
- responses: base_url: https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1; sdk: aisdk: @ai-sdk/amazon-bedrock/mantle; opencodeai: @opencode/ai/providers/amazon-bedrock/mantle/responses; capabilities: system_updates: Yes; tools: updates: No; chat-completions: base_url: https://bedrock-mantle.${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
cloudflare-ai-gateway workers-ai/@cf/google/gemma-4-26b-a4b-it
Context Not recorded · Output Not recorded
cloudflare-workers-ai @cf/google/gemma-4-26b-a4b-it
Context 256,000 · Output 16,384
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 256,000; output: 16,384
- id
- @cf/google/gemma-4-26b-a4b-it
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- api
- 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-workers-ai; capabilities: tools: choice: auto, none, required, tool; updates: No
deepinfra google/gemma-4-26B-A4B-it
Context 262,144 · Output 32,768
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No; service_tier: flex, priority
- limit
- context: 262,144; output: 32,768
- id
- google/gemma-4-26B-A4B-it
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- api
- chat-completions: base_url: https://api.deepinfra.com/v1/openai; sdk: aisdk: @ai-sdk/deepinfra; opencodeai: @opencode/ai/providers/deepinfra; capabilities: tools: updates: No
Google gemma-4-26b-a4b-it
Context 262,144 · Output 32,768
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 32,768
- id
- gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- api
- generate-content: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google; opencodeai: @opencode/ai/providers/google; capabilities: tools: strict: Yes; choice: auto, none, required, tool; updates: No; chat-completions: base_url: https://generativelanguage.googleapis.com/v1beta/openai; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; capabilities: tools: strict: Yes; choice: auto, none, required, tool; updates: No; interactions: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google; opencodeai: @opencode/ai/providers/google/interactions; capabilities: tools: strict: Yes; choice: auto, none, required, tool; updates: No
Google google/gemma-4-26b-a4b-it-maas
Context 262,144 · Output 128,000
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; cache: implicit: min_tokens: 4,096; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 128,000
- id
- google/gemma-4-26b-a4b-it-maas
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- status
- alpha
- api
- chat-completions: base_url: https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/google-vertex/chat; compatibility: reasoning_field: reasoning_content; capabilities: tools: updates: No
huggingface google/gemma-4-26B-A4B-it
Context 262,144 · Output 32,768
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 32,768
- id
- google/gemma-4-26B-A4B-it
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- api
- chat-completions: base_url: https://router.huggingface.co/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://router.huggingface.co/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No
OpenRouter google/gemma-4-26b-a4b-it
Context 262,144 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: image/png, image/jpeg, image/webp, text, video/mp4, video/mpeg, video/mov, video/webm; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 128,000; input: 134,144
- id
- google/gemma-4-26b-a4b-it
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- 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: No; 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
OpenRouter google/gemma-4-26b-a4b-it:free
Context 262,144 · Output 32,768
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Gemma 4 26B A4B (free)
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: image/png, image/jpeg, image/webp, text, video/mp4, video/mpeg, video/mov, video/webm; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 32,768; input: 229,376
- id
- google/gemma-4-26b-a4b-it:free
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- 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: No; 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 google/gemma-4-26b-a4b-it
Context 265,216 · Output 131,072
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Gemma 4 26B A4B IT
- description
- Open Gemma instruction model for efficient chat and self-hosted deployments
- family
- gemma
- open weights
- Yes
- release date
- 2026-04-02
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 265,216; output: 131,072; input: 134,144
- id
- google/gemma-4-26b-a4b-it
- canonical id
- google/gemma-4-26b-a4b-it
- type
- chat
- last updated
- 2026-04-02
- 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: No; 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: No; 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