# AI models directory

Canonical HTML page: [AI models directory](<https://impossibl.com/models>)
Markdown alternative: [AI models directory as Markdown](<https://impossibl.com/models.md>)

110 models from 16 creators available through the Impossibl API. Compare published prices, context windows, and capabilities.

Select two or three models to [compare specifications and API costs](<https://impossibl.com/compare.md>). Model types and billing units are not interchangeable.

## Models

### [GPT-6 Astra](<https://impossibl.com/openai/gpt-6-astra>)

- API identifier: `openai/gpt-6-astra`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $10.00 per million input tokens; $50.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-6-astra.md>)

### [GPT-5.6 Sol](<https://impossibl.com/openai/gpt-5.6-sol>)

- API identifier: `openai/gpt-5.6-sol`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $4.00 per million input tokens; $20.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.6-sol.md>)

### [GPT-5.6 Luna](<https://impossibl.com/openai/gpt-5.6-luna>)

- API identifier: `openai/gpt-5.6-luna`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.20 per million input tokens; $1.20 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.6-luna.md>)

### [GPT-5.6 Terra](<https://impossibl.com/openai/gpt-5.6-terra>)

- API identifier: `openai/gpt-5.6-terra`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $12.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.6-terra.md>)

### [GPT Image 2.5 Sunburst](<https://impossibl.com/openai/gpt-image-2.5-sunburst>)

- API identifier: `openai/gpt-image-2.5-sunburst`
- Creator: OpenAI; model type: Image generation.
- Context window: 32,000 tokens; tool calling: Not published.
- Inputs: text; outputs: images.
- Base API pricing (USD): $5.00 per million input tokens; $30.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-image-2.5-sunburst.md>)

### [GPT Image 2.5 Flare](<https://impossibl.com/openai/gpt-image-2.5-flare>)

- API identifier: `openai/gpt-image-2.5-flare`
- Creator: OpenAI; model type: Image generation.
- Context window: 32,000 tokens; tool calling: Not published.
- Inputs: text; outputs: images.
- Base API pricing (USD): $5.00 per million input tokens; $30.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-image-2.5-flare.md>)

### [GPT Image 2](<https://impossibl.com/openai/gpt-image-2>)

- API identifier: `openai/gpt-image-2`
- Creator: OpenAI; model type: Image generation.
- Context window: 32,000 tokens; tool calling: Not published.
- Inputs: text; outputs: images.
- Base API pricing (USD): $5.00 per million input tokens; $30.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-image-2.md>)

### [GPT Transcribe](<https://impossibl.com/openai/gpt-transcribe>)

- API identifier: `openai/gpt-transcribe`
- Creator: OpenAI; model type: Speech to text.
- Context window: Not published; tool calling: Not published.
- Inputs: audio, text; outputs: text.
- Base API pricing (USD): $0.0045 per minute of audio.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-transcribe.md>)

### [Text Embedding 3 Small](<https://impossibl.com/openai/text-embedding-3-small>)

- API identifier: `openai/text-embedding-3-small`
- Creator: OpenAI; model type: Embeddings.
- Context window: 8,192 tokens; tool calling: Not published.
- Inputs: text; outputs: embedding vectors.
- Base API pricing (USD): $0.02 per million input tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/text-embedding-3-small.md>)

### [Text Embedding 3 Large](<https://impossibl.com/openai/text-embedding-3-large>)

- API identifier: `openai/text-embedding-3-large`
- Creator: OpenAI; model type: Embeddings.
- Context window: 8,192 tokens; tool calling: Not published.
- Inputs: text; outputs: embedding vectors.
- Base API pricing (USD): $0.13 per million input tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/text-embedding-3-large.md>)

### [GPT-5.5](<https://impossibl.com/openai/gpt-5.5>)

- API identifier: `openai/gpt-5.5`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $30.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.5.md>)

### [GPT-5.5 Pro](<https://impossibl.com/openai/gpt-5.5-pro>)

- API identifier: `openai/gpt-5.5-pro`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $30.00 per million input tokens; $180.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.5-pro.md>)

### [GPT-5.4](<https://impossibl.com/openai/gpt-5.4>)

- API identifier: `openai/gpt-5.4`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.50 per million input tokens; $15.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.4.md>)

### [GPT-5.4 mini](<https://impossibl.com/openai/gpt-5.4-mini>)

- API identifier: `openai/gpt-5.4-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.75 per million input tokens; $4.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.4-mini.md>)

### [GPT-5.4 nano](<https://impossibl.com/openai/gpt-5.4-nano>)

- API identifier: `openai/gpt-5.4-nano`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.20 per million input tokens; $1.25 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.4-nano.md>)

### [GPT-5.4 Pro](<https://impossibl.com/openai/gpt-5.4-pro>)

- API identifier: `openai/gpt-5.4-pro`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,050,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $30.00 per million input tokens; $180.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.4-pro.md>)

### [GPT-5.3 Codex](<https://impossibl.com/openai/gpt-5.3-codex>)

- API identifier: `openai/gpt-5.3-codex`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.75 per million input tokens; $14.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.3-codex.md>)

### [GPT-5.1](<https://impossibl.com/openai/gpt-5.1>)

- API identifier: `openai/gpt-5.1`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.1.md>)

### [GPT-5.2](<https://impossibl.com/openai/gpt-5.2>)

- API identifier: `openai/gpt-5.2`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.75 per million input tokens; $14.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.2.md>)

### [GPT-5.2 Codex](<https://impossibl.com/openai/gpt-5.2-codex>)

- API identifier: `openai/gpt-5.2-codex`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.75 per million input tokens; $14.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.2-codex.md>)

### [GPT-5.1 Codex](<https://impossibl.com/openai/gpt-5.1-codex>)

- API identifier: `openai/gpt-5.1-codex`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.1-codex.md>)

### [GPT-5.1 Codex mini](<https://impossibl.com/openai/gpt-5.1-codex-mini>)

- API identifier: `openai/gpt-5.1-codex-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.25 per million input tokens; $2.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.1-codex-mini.md>)

### [GPT Chat Latest](<https://impossibl.com/openai/chat-latest>)

- API identifier: `openai/chat-latest`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $30.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/chat-latest.md>)

### [GPT-5](<https://impossibl.com/openai/gpt-5>)

- API identifier: `openai/gpt-5`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5.md>)

### [GPT-5 Pro](<https://impossibl.com/openai/gpt-5-pro>)

- API identifier: `openai/gpt-5-pro`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $15.00 per million input tokens; $120.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5-pro.md>)

### [GPT-5 Codex](<https://impossibl.com/openai/gpt-5-codex>)

- API identifier: `openai/gpt-5-codex`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5-codex.md>)

### [GPT-5 mini](<https://impossibl.com/openai/gpt-5-mini>)

- API identifier: `openai/gpt-5-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.25 per million input tokens; $2.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5-mini.md>)

### [GPT-5 nano](<https://impossibl.com/openai/gpt-5-nano>)

- API identifier: `openai/gpt-5-nano`
- Creator: OpenAI; model type: Text generation.
- Context window: 400,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.05 per million input tokens; $0.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-5-nano.md>)

### [GPT-4.1](<https://impossibl.com/openai/gpt-4.1>)

- API identifier: `openai/gpt-4.1`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $8.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4.1.md>)

### [GPT-4.1 mini](<https://impossibl.com/openai/gpt-4.1-mini>)

- API identifier: `openai/gpt-4.1-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.40 per million input tokens; $1.60 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4.1-mini.md>)

### [GPT-4.1 nano](<https://impossibl.com/openai/gpt-4.1-nano>)

- API identifier: `openai/gpt-4.1-nano`
- Creator: OpenAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.10 per million input tokens; $0.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4.1-nano.md>)

### [GPT-4o](<https://impossibl.com/openai/gpt-4o>)

- API identifier: `openai/gpt-4o`
- Creator: OpenAI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.50 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4o.md>)

### [GPT-4o mini](<https://impossibl.com/openai/gpt-4o-mini>)

- API identifier: `openai/gpt-4o-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.15 per million input tokens; $0.60 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4o-mini.md>)

### [GPT-4 Turbo](<https://impossibl.com/openai/gpt-4-turbo>)

- API identifier: `openai/gpt-4-turbo`
- Creator: OpenAI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $10.00 per million input tokens; $30.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-4-turbo.md>)

### [GPT-3.5 Turbo](<https://impossibl.com/openai/gpt-3.5-turbo>)

- API identifier: `openai/gpt-3.5-turbo`
- Creator: OpenAI; model type: Text generation.
- Context window: 16,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.50 per million input tokens; $1.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-3.5-turbo.md>)

### [OpenAI o3](<https://impossibl.com/openai/o3>)

- API identifier: `openai/o3`
- Creator: OpenAI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $8.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/o3.md>)

### [OpenAI o3-mini](<https://impossibl.com/openai/o3-mini>)

- API identifier: `openai/o3-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.10 per million input tokens; $4.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/o3-mini.md>)

### [OpenAI o4-mini](<https://impossibl.com/openai/o4-mini>)

- API identifier: `openai/o4-mini`
- Creator: OpenAI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.10 per million input tokens; $4.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/o4-mini.md>)

### [OpenAI o1](<https://impossibl.com/openai/o1>)

- API identifier: `openai/o1`
- Creator: OpenAI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $15.00 per million input tokens; $60.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/o1.md>)

### [GPT OSS 120B](<https://impossibl.com/openai/gpt-oss-120b>)

- API identifier: `openai/gpt-oss-120b`
- Creator: OpenAI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.35 per million input tokens; $0.75 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-oss-120b.md>)

### [GPT OSS 20B](<https://impossibl.com/openai/gpt-oss-20b>)

- API identifier: `openai/gpt-oss-20b`
- Creator: OpenAI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.075 per million input tokens; $0.30 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/openai/gpt-oss-20b.md>)

### [Claude Opus 5](<https://impossibl.com/anthropic/claude-opus-5>)

- API identifier: `anthropic/claude-opus-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-opus-5.md>)

### [Claude Fable 5.1](<https://impossibl.com/anthropic/claude-fable-5-1>)

- API identifier: `anthropic/claude-fable-5-1`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $10.00 per million input tokens; $50.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-fable-5-1.md>)

### [Claude Fable 5](<https://impossibl.com/anthropic/claude-fable-5>)

- API identifier: `anthropic/claude-fable-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $10.00 per million input tokens; $50.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-fable-5.md>)

### [Claude Opus 4.8](<https://impossibl.com/anthropic/claude-opus-4-8>)

- API identifier: `anthropic/claude-opus-4-8`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-opus-4-8.md>)

### [Claude Opus 4.7](<https://impossibl.com/anthropic/claude-opus-4-7>)

- API identifier: `anthropic/claude-opus-4-7`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-opus-4-7.md>)

### [Claude Opus 4.6](<https://impossibl.com/anthropic/claude-opus-4-6>)

- API identifier: `anthropic/claude-opus-4-6`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-opus-4-6.md>)

### [Claude Sonnet 5](<https://impossibl.com/anthropic/claude-sonnet-5>)

- API identifier: `anthropic/claude-sonnet-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-sonnet-5.md>)

### [Claude Sonnet 4.6](<https://impossibl.com/anthropic/claude-sonnet-4-6>)

- API identifier: `anthropic/claude-sonnet-4-6`
- Creator: Anthropic; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $3.00 per million input tokens; $15.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-sonnet-4-6.md>)

### [Claude Haiku 4.5](<https://impossibl.com/anthropic/claude-haiku-4-5>)

- API identifier: `anthropic/claude-haiku-4-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.00 per million input tokens; $5.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-haiku-4-5.md>)

### [Claude Opus 4.5](<https://impossibl.com/anthropic/claude-opus-4-5>)

- API identifier: `anthropic/claude-opus-4-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-opus-4-5.md>)

### [Claude Sonnet 4.5](<https://impossibl.com/anthropic/claude-sonnet-4-5>)

- API identifier: `anthropic/claude-sonnet-4-5`
- Creator: Anthropic; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $3.00 per million input tokens; $15.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/anthropic/claude-sonnet-4-5.md>)

### [Gemini 3.8 Flash](<https://impossibl.com/google/gemini-3.8-flash>)

- API identifier: `google/gemini-3.8-flash`
- Creator: Google; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.75 per million input tokens; $3.75 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.8-flash.md>)

### [Gemini 3.7 Flash](<https://impossibl.com/google/gemini-3.7-flash>)

- API identifier: `google/gemini-3.7-flash`
- Creator: Google; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.75 per million input tokens; $3.75 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.7-flash.md>)

### [Gemini Robotics-ER 2 Preview](<https://impossibl.com/google/gemini-robotics-er-2-preview>)

- API identifier: `google/gemini-robotics-er-2-preview`
- Creator: Google; model type: Text generation.
- Context window: 131,072 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $10.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-robotics-er-2-preview.md>)

### [Gemini 3.6 Flash](<https://impossibl.com/google/gemini-3.6-flash>)

- API identifier: `google/gemini-3.6-flash`
- Creator: Google; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.75 per million input tokens; $3.75 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.6-flash.md>)

### [Gemini 3.5 Flash](<https://impossibl.com/google/gemini-3.5-flash>)

- API identifier: `google/gemini-3.5-flash`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $1.50 per million input tokens; $9.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.5-flash.md>)

### [Gemini 3.5 Flash-Lite](<https://impossibl.com/google/gemini-3.5-flash-lite>)

- API identifier: `google/gemini-3.5-flash-lite`
- Creator: Google; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.30 per million input tokens; $2.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.5-flash-lite.md>)

### [Gemini 3.1 Pro (preview)](<https://impossibl.com/google/gemini-3.1-pro-preview>)

- API identifier: `google/gemini-3.1-pro-preview`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $12.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.1-pro-preview.md>)

### [Gemini 3.1 Flash-Lite](<https://impossibl.com/google/gemini-3.1-flash-lite>)

- API identifier: `google/gemini-3.1-flash-lite`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.25 per million input tokens; $1.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.1-flash-lite.md>)

### [Gemini 2.5 Pro](<https://impossibl.com/google/gemini-2.5-pro>)

- API identifier: `google/gemini-2.5-pro`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $10.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-2.5-pro.md>)

### [Gemini 2.5 Flash](<https://impossibl.com/google/gemini-2.5-flash>)

- API identifier: `google/gemini-2.5-flash`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.30 per million input tokens; $2.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-2.5-flash.md>)

### [Gemini 2.5 Flash-Lite](<https://impossibl.com/google/gemini-2.5-flash-lite>)

- API identifier: `google/gemini-2.5-flash-lite`
- Creator: Google; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image, audio, video; outputs: text.
- Base API pricing (USD): $0.10 per million input tokens; $0.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-2.5-flash-lite.md>)

### [Gemma 4 31B](<https://impossibl.com/google/gemma-4-31b>)

- API identifier: `google/gemma-4-31b`
- Creator: Google; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.99 per million input tokens; $1.49 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemma-4-31b.md>)

### [Gemini 3.1 Flash TTS (preview)](<https://impossibl.com/google/gemini-3.1-flash-tts-preview>)

- API identifier: `google/gemini-3.1-flash-tts-preview`
- Creator: Google; model type: Text to speech.
- Context window: Not published; tool calling: Not published.
- Inputs: text; outputs: audio.
- Base API pricing (USD): $1.00 per million input tokens; $20.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/google/gemini-3.1-flash-tts-preview.md>)

### [Grok 4.6](<https://impossibl.com/xai/grok-4.6>)

- API identifier: `xai/grok-4.6`
- Creator: xAI; model type: Text generation.
- Context window: 500,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $6.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.6.md>)

### [Grok 4.5](<https://impossibl.com/xai/grok-4.5>)

- API identifier: `xai/grok-4.5`
- Creator: xAI; model type: Text generation.
- Context window: 500,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $6.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.5.md>)

### [Grok 4.3](<https://impossibl.com/xai/grok-4.3>)

- API identifier: `xai/grok-4.3`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.3.md>)

### [Grok 4.20 (reasoning)](<https://impossibl.com/xai/grok-4.20-0309-reasoning>)

- API identifier: `xai/grok-4.20-0309-reasoning`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-0309-reasoning.md>)

### [Grok 4.20 (non-reasoning)](<https://impossibl.com/xai/grok-4.20-0309-non-reasoning>)

- API identifier: `xai/grok-4.20-0309-non-reasoning`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-0309-non-reasoning.md>)

### [Grok 4.20 (multi-agent)](<https://impossibl.com/xai/grok-4.20-multi-agent-0309>)

- API identifier: `xai/grok-4.20-multi-agent-0309`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-multi-agent-0309.md>)

### [Grok Build 0.1](<https://impossibl.com/xai/grok-build-0.1>)

- API identifier: `xai/grok-build-0.1`
- Creator: xAI; model type: Text generation.
- Context window: 256,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.00 per million input tokens; $2.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-build-0.1.md>)

### [Grok Voice TTS 1.0](<https://impossibl.com/xai/grok-voice-tts-1.0>)

- API identifier: `xai/grok-voice-tts-1.0`
- Creator: xAI; model type: Text to speech.
- Context window: Not published; tool calling: Not published.
- Inputs: text; outputs: audio.
- Base API pricing (USD): $15.00 per million input characters.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-voice-tts-1.0.md>)

### [Llama 3.3 70B Instruct](<https://impossibl.com/meta/llama-3.3-70b>)

- API identifier: `meta/llama-3.3-70b`
- Creator: Meta; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.71 per million input tokens; $0.71 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/llama-3.3-70b.md>)

### [Muse Glimmer 30B](<https://impossibl.com/meta/muse-glimmer-30b>)

- API identifier: `meta/muse-glimmer-30b`
- Creator: Meta; model type: Text generation.
- Context window: 131,072 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.35 per million input tokens; $1.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-glimmer-30b.md>)

### [Mistral Large 3](<https://impossibl.com/mistral/mistral-large-3>)

- API identifier: `mistral/mistral-large-3`
- Creator: Mistral; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.50 per million input tokens; $1.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/mistral/mistral-large-3.md>)

### [Phi-4](<https://impossibl.com/microsoft/phi-4>)

- API identifier: `microsoft/phi-4`
- Creator: Microsoft; model type: Text generation.
- Context window: 16,000 tokens; tool calling: Not supported.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.125 per million input tokens; $0.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/microsoft/phi-4.md>)

### [DeepSeek V4 Flash 0731](<https://impossibl.com/deepseek/deepseek-v4-flash-0731>)

- API identifier: `deepseek/deepseek-v4-flash-0731`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.14 per million input tokens; $0.28 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-flash-0731.md>)

### [DeepSeek V4 Pro 0813](<https://impossibl.com/deepseek/deepseek-v4-pro-0813>)

- API identifier: `deepseek/deepseek-v4-pro-0813`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.74 per million input tokens; $3.48 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-pro-0813.md>)

### [DeepSeek V4.1 Flash](<https://impossibl.com/deepseek/deepseek-v4.1-flash>)

- API identifier: `deepseek/deepseek-v4.1-flash`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.30 per million input tokens; $1.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4.1-flash.md>)

### [Nemotron 3.5 Lightning](<https://impossibl.com/nvidia/nemotron-3.5-lightning>)

- API identifier: `nvidia/nemotron-3.5-lightning`
- Creator: NVIDIA; model type: Text generation.
- Context window: 262,144 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.05 per million input tokens; $0.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/nvidia/nemotron-3.5-lightning.md>)

### [DeepSeek V4 Flash](<https://impossibl.com/deepseek/deepseek-v4-flash>)

- API identifier: `deepseek/deepseek-v4-flash`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.19 per million input tokens; $0.51 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-flash.md>)

### [DeepSeek V4 Pro](<https://impossibl.com/deepseek/deepseek-v4-pro>)

- API identifier: `deepseek/deepseek-v4-pro`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.74 per million input tokens; $3.48 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-pro.md>)

### [DeepSeek V3.2](<https://impossibl.com/deepseek/deepseek-v3-2>)

- API identifier: `deepseek/deepseek-v3-2`
- Creator: DeepSeek; model type: Text generation.
- Context window: 163,840 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v3-2.md>)

### [DeepSeek V3.2 Speciale](<https://impossibl.com/deepseek/deepseek-v3-2-speciale>)

- API identifier: `deepseek/deepseek-v3-2-speciale`
- Creator: DeepSeek; model type: Text generation.
- Context window: 163,840 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v3-2-speciale.md>)

### [GLM-5.3](<https://impossibl.com/zai/glm-5.3>)

- API identifier: `zai/glm-5.3`
- Creator: Z.AI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.40 per million input tokens; $4.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.3.md>)

### [GLM-5.3-Flash](<https://impossibl.com/zai/glm-5.3-flash>)

- API identifier: `zai/glm-5.3-flash`
- Creator: Z.AI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.15 per million input tokens; $0.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.3-flash.md>)

### [GLM-5.2](<https://impossibl.com/zai/glm-5.2>)

- API identifier: `zai/glm-5.2`
- Creator: Z.AI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.40 per million input tokens; $4.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.2.md>)

### [GLM-5.2 Fast](<https://impossibl.com/zai/glm-5.2-fast>)

- API identifier: `zai/glm-5.2-fast`
- Creator: Z.AI; model type: Text generation.
- Context window: 1,040,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $2.10 per million input tokens; $6.60 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.2-fast.md>)

### [GLM-5.1](<https://impossibl.com/zai/glm-5.1>)

- API identifier: `zai/glm-5.1`
- Creator: Z.AI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.40 per million input tokens; $4.40 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.1.md>)

### [GLM-5](<https://impossibl.com/zai/glm-5>)

- API identifier: `zai/glm-5`
- Creator: Z.AI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.00 per million input tokens; $3.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5.md>)

### [GLM-5 Turbo](<https://impossibl.com/zai/glm-5-turbo>)

- API identifier: `zai/glm-5-turbo`
- Creator: Z.AI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.20 per million input tokens; $4.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-5-turbo.md>)

### [GLM-4.7](<https://impossibl.com/zai/glm-4.7>)

- API identifier: `zai/glm-4.7`
- Creator: Z.AI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.60 per million input tokens; $2.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-4.7.md>)

### [GLM-4.6](<https://impossibl.com/zai/glm-4.6>)

- API identifier: `zai/glm-4.6`
- Creator: Z.AI; model type: Text generation.
- Context window: 200,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.60 per million input tokens; $2.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-4.6.md>)

### [GLM-4.5](<https://impossibl.com/zai/glm-4.5>)

- API identifier: `zai/glm-4.5`
- Creator: Z.AI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.60 per million input tokens; $2.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-4.5.md>)

### [GLM-4.5 Air](<https://impossibl.com/zai/glm-4.5-air>)

- API identifier: `zai/glm-4.5-air`
- Creator: Z.AI; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.20 per million input tokens; $1.10 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/zai/glm-4.5-air.md>)

### [Kimi K3](<https://impossibl.com/moonshotai/kimi-k3>)

- API identifier: `moonshotai/kimi-k3`
- Creator: Moonshot AI; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $3.00 per million input tokens; $15.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/moonshotai/kimi-k3.md>)

### [Qwen3.7 Max](<https://impossibl.com/qwen/qwen3.7-max>)

- API identifier: `qwen/qwen3.7-max`
- Creator: Qwen; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $2.50 per million input tokens; $7.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.7-max.md>)

### [Qwen3.7 Plus](<https://impossibl.com/qwen/qwen3.7-plus>)

- API identifier: `qwen/qwen3.7-plus`
- Creator: Qwen; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.40 per million input tokens; $1.60 per million output tokens. Above 262,144 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.7-plus.md>)

### [Qwen3.6 Flash](<https://impossibl.com/qwen/qwen3.6-flash>)

- API identifier: `qwen/qwen3.6-flash`
- Creator: Qwen; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.25 per million input tokens; $1.50 per million output tokens. Above 262,144 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.6-flash.md>)

### [Qwen3.8 Max](<https://impossibl.com/qwen/qwen3.8-max>)

- API identifier: `qwen/qwen3.8-max`
- Creator: Qwen; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $6.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.8-max.md>)

### [Qwen3.8 27B](<https://impossibl.com/qwen/qwen3.8-27b>)

- API identifier: `qwen/qwen3.8-27b`
- Creator: Qwen; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.50 per million input tokens; $3.00 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.8-27b.md>)

### [Qwen3.8 2.4T A95B](<https://impossibl.com/qwen/qwen3.8-2.4t-a95b>)

- API identifier: `qwen/qwen3.8-2.4t-a95b`
- Creator: Qwen; model type: Text generation.
- Context window: 262,144 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.20 per million input tokens; $1.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/qwen/qwen3.8-2.4t-a95b.md>)

### [MiMo V2.5](<https://impossibl.com/xiaomi/mimo-v2.5>)

- API identifier: `xiaomi/mimo-v2.5`
- Creator: Xiaomi; model type: Text generation.
- Context window: 1,024,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.14 per million input tokens; $0.28 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xiaomi/mimo-v2.5.md>)

### [MiniMax M3](<https://impossibl.com/minimaxai/minimax-m3>)

- API identifier: `minimaxai/minimax-m3`
- Creator: MiniMax; model type: Text generation.
- Context window: 524,300 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.30 per million input tokens; $1.20 per million output tokens. Above 512,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/minimaxai/minimax-m3.md>)

### [Hunyuan 3](<https://impossibl.com/tencent/hy3>)

- API identifier: `tencent/hy3`
- Creator: Tencent; model type: Text generation.
- Context window: 262,144 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.20 per million input tokens; $0.80 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/tencent/hy3.md>)

### [Inkling](<https://impossibl.com/thinkingmachines/inkling>)

- API identifier: `thinkingmachines/inkling`
- Creator: Thinking Machines; model type: Text generation.
- Context window: 65,536 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.87 per million input tokens; $4.68 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/thinkingmachines/inkling.md>)

### [Inkling 256K](<https://impossibl.com/thinkingmachines/inkling-256k>)

- API identifier: `thinkingmachines/inkling-256k`
- Creator: Thinking Machines; model type: Text generation.
- Context window: 262,144 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $3.74 per million input tokens; $9.36 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/thinkingmachines/inkling-256k.md>)

### [Muse Spark 1.3](<https://impossibl.com/meta/muse-spark-1.3>)

- API identifier: `meta/muse-spark-1.3`
- Creator: Meta; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $4.25 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-spark-1.3.md>)

### [Muse Spark 1.3 (Contributor)](<https://impossibl.com/meta/muse-spark-1.3-contributor>)

- API identifier: `meta/muse-spark-1.3-contributor`
- Creator: Meta; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.10 per million input tokens; $0.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-spark-1.3-contributor.md>)

## Browse by creator

- [Anthropic](<https://impossibl.com/anthropic.md>)
- [DeepSeek](<https://impossibl.com/deepseek.md>)
- [Google](<https://impossibl.com/google.md>)
- [Meta](<https://impossibl.com/meta.md>)
- [Microsoft](<https://impossibl.com/microsoft.md>)
- [MiniMax](<https://impossibl.com/minimaxai.md>)
- [Mistral](<https://impossibl.com/mistral.md>)
- [Moonshot AI](<https://impossibl.com/moonshotai.md>)
- [NVIDIA](<https://impossibl.com/nvidia.md>)
- [OpenAI](<https://impossibl.com/openai.md>)
- [Qwen](<https://impossibl.com/qwen.md>)
- [Tencent](<https://impossibl.com/tencent.md>)
- [Thinking Machines](<https://impossibl.com/thinkingmachines.md>)
- [xAI](<https://impossibl.com/xai.md>)
- [Xiaomi](<https://impossibl.com/xiaomi.md>)
- [Z.AI](<https://impossibl.com/zai.md>)

## Frequently asked questions

### which ai models can i access through one api?

impossibl gives you access to 110 ai models from 16 creators through one api. creators include [Anthropic](<https://impossibl.com/anthropic>), [DeepSeek](<https://impossibl.com/deepseek>), [Google](<https://impossibl.com/google>), [Meta](<https://impossibl.com/meta>), [Microsoft](<https://impossibl.com/microsoft>), [MiniMax](<https://impossibl.com/minimaxai>), [Mistral](<https://impossibl.com/mistral>), [Moonshot AI](<https://impossibl.com/moonshotai>). the catalog covers text generation, image generation, embeddings, text to speech, and speech to text. each model page lists its exact api model id, supported endpoints, and published prices.

### which ai models have the lowest api prices?

low-cost ai models include [Nemotron 3.5 Lightning](<https://impossibl.com/nvidia/nemotron-3.5-lightning>) at $0.05 per million input tokens and $0.20 per million output tokens; [GPT OSS 20B](<https://impossibl.com/openai/gpt-oss-20b>) at $0.075 per million input tokens and $0.30 per million output tokens; [Muse Spark 1.3 (Contributor)](<https://impossibl.com/meta/muse-spark-1.3-contributor>) at $0.10 per million input tokens and $0.20 per million output tokens. these text models rank lowest for a 4:1 input-to-output token mix at base rates. your cheapest option depends on output volume, caching, and context pricing. [compare api costs for the same workload](<https://impossibl.com/compare>).

### how much does one million ai tokens cost?

the cost depends on the model and how many tokens you send and receive. for example, a model charging $1 per million input tokens and $5 per million output tokens would cost $1.80 for 800,000 input tokens and 200,000 output tokens across requests at base rates. this hypothetical token-only estimate excludes additional fees; caching and long-context rates can change the total. [estimate your model workload cost](<https://impossibl.com/compare>).

### which ai models have the largest context windows?

the ai models with the largest published text context windows include [GPT-5.4](<https://impossibl.com/openai/gpt-5.4>) with 1,050,000 tokens; [GPT-5.4 Pro](<https://impossibl.com/openai/gpt-5.4-pro>) with 1,050,000 tokens; [GPT-5.5](<https://impossibl.com/openai/gpt-5.5>) with 1,050,000 tokens. long context windows let you work with larger documents, codebases, and conversations. check output limits and long-context prices on each model page.

### which ai models support image inputs?

ai models with image input support include [GPT-6 Astra](<https://impossibl.com/openai/gpt-6-astra>), [GPT-5.6 Sol](<https://impossibl.com/openai/gpt-5.6-sol>), [GPT-5.6 Luna](<https://impossibl.com/openai/gpt-5.6-luna>). these accept images as input and generate text responses. use them to ask questions about images. image generation is a separate capability. [browse models with image input support](<https://impossibl.com/models#input=image>) and check each model's supported endpoint before integrating it.

### which embedding models can i use for semantic search and rag?

embedding models available through impossibl include [Text Embedding 3 Small](<https://impossibl.com/openai/text-embedding-3-small>), [Text Embedding 3 Large](<https://impossibl.com/openai/text-embedding-3-large>). embeddings turn inputs into vectors for semantic search and retrieval-augmented generation (rag). compare input prices and context limits, then test retrieval quality on your documents. open a model page for its api endpoint and pricing.

### how do cached input tokens affect ai api pricing?

prompt caching can lower api costs when you reuse the same input and the model offers a discounted cache-read rate. cache writes may have a separate charge. each model page lists published cache prices and long-context rates so you can compare the cost of repeated prompts.

### which ai models are best for coding?

coding models to compare include [GPT-6 Astra](<https://impossibl.com/openai/gpt-6-astra>), [Claude Opus 5](<https://impossibl.com/anthropic/claude-opus-5>), [Claude Sonnet 4.6](<https://impossibl.com/anthropic/claude-sonnet-4-6>). evaluate them on debugging, code generation, and changes across multiple files. model pages show available benchmark results with source links; compare those alongside api prices, context windows, and tool support. [compare coding models](<https://impossibl.com/compare>) and test your shortlist on real tasks from your project.

### how do claude, gpt, and gemini compare?

claude, gpt, and gemini are model families from Anthropic, OpenAI, and Google. api prices, context windows, image inputs, and tool support vary by the exact model. available models include [Claude Opus 5](<https://impossibl.com/anthropic/claude-opus-5>), [GPT-6 Astra](<https://impossibl.com/openai/gpt-6-astra>), [Gemini 3.8 Flash](<https://impossibl.com/google/gemini-3.8-flash>). [compare claude, gpt, and gemini models side by side](<https://impossibl.com/compare>) to see their specifications and estimate the same workload cost.

### how do i start using an ai model through the impossibl api?

create an api key, choose a model from the directory, and use its exact model id with a supported endpoint. model pages include request examples and published input and output capabilities. when switching models, check endpoint and input compatibility as well as the model id. follow the [api quickstart](<https://impossibl.com/docs/agent-quickstart>) for your first request or read the [model documentation](<https://impossibl.com/docs/models>).

## Sources and related links

Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Model directory as Markdown](<https://impossibl.com/models.md>)
- [API quickstart](<https://impossibl.com/docs/agent-quickstart>)
- [Model documentation](<https://impossibl.com/docs/models>)