Available Models
This page lists all models available through the PwC AI-CoE Coding Agents Gateway: the models of the PwC GenAI Shared Service plus a set of self-hosted and partner models served via the PwC Agent orchestrator.
These models are safe to use as they run on dedicated instances provisioned for PwC by PwC Global. They are the same models powering the IDI (Instant Document Interaction) platform. For more information, visit the official PwC GenAI Shared Service SharePoint.
Model Compatibility
Different coding agents work best with different model families:
| Coding Agent | Compatible Models | Recommendation |
|---|---|---|
| Claude Code | Anthropic models (Claude Opus, Sonnet, Haiku), self-hosted models, and auto | Anthropic models recommended |
| Cline | All supported models | Optimized for Anthropic models |
| Codex | OpenAI models with Responses API support only | See Responses API column below |
Use models from the same vendor as your coding agent for the best experience. For example, use Claude models with Claude Code, and OpenAI models with Codex.
Supported Models
When configuring your coding agent, you can use any of the three model ID formats accepted by the gateway:
- Vendor naming convention (e.g.,
claude-sonnet-4-6,gpt-5.2-codex) — shortest, routes to the default provider for that model - PwC GenAI Shared Service naming convention (e.g.,
bedrock.anthropic.claude-opus-4-6) — provider-explicit shorthand - Coding Agents Gateway naming convention (e.g.,
GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_46_OPUS) — recommended when you want to pin a specific cloud provider
The Vendor Name column below shows the bare name for each model. Where two rows share the same model (different providers), only the default-provider row shows a bare name — use the GENAI internal name to target the other provider explicitly.
Models marked with ⭐ are our recommended choices for the best balance of performance and cost.
Model IDs
The gateway accepts three formats for the model field (or model-name custom header):
| Format | Example | Notes |
|---|---|---|
| Vendor naming convention | claude-sonnet-4-6 | Shortest. Routes to the default provider. Date suffixes are stripped automatically (e.g., claude-sonnet-4-5-20241022 → claude-sonnet-4-5). |
| PwC GenAI Shared Service naming convention | bedrock.anthropic.claude-opus-4-6 | Provider-explicit shorthand. |
| Coding Agents Gateway naming convention | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_46_OPUS | Unambiguous. Recommended when pinning a specific cloud provider. |
Anthropic Models
| Official Name | Vendor Name | Gateway Model ID 🔑 | PwC Cloud Provider | Input ($/1M) | Output ($/1M) | Context | Max Output | Responses API |
|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 ⭐ | claude-opus-4-8 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_48_OPUS | Vertex AI | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.8 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_48_OPUS | Bedrock | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.7 | claude-opus-4-7 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_47_OPUS | Vertex AI | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.7 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_47_OPUS | Bedrock | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.6 | claude-opus-4-6 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_46_OPUS | Vertex AI | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.6 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_46_OPUS | Bedrock | $5.50 | $27.50 | 1M | 128k | - |
| Claude Opus 4.5 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_45_OPUS | Bedrock | $5.00 | $25.00 | 200k | 64k | - |
| Claude Opus 4.5 | claude-opus-4-5 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_45_OPUS | Vertex AI | $5.00 | $25.00 | 200k | 64k | - |
| Claude Sonnet 5 ⭐ | claude-sonnet-5 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_5_SONNET | Vertex AI | $2.20 | $11.00 | 1M | 128k | - |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_46_SONNET | Vertex AI | $3.30 | $16.50 | 1M | 64k | - |
| Claude Sonnet 4.6 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_46_SONNET | Bedrock | $3.30 | $16.50 | 1M | 64k | - |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_45_SONNET | Vertex AI | $3.00 | $15.00 | 200k | 64k | - |
| Claude Sonnet 4.5 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_45_SONNET | Bedrock | $3.00 | $15.00 | 200k | 64k | - |
| Claude Sonnet 4 | claude-sonnet-4 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_4_SONNET | Vertex AI | $3.00 | $15.00 | 1M | 64k | - |
| Claude Sonnet 4 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_4_SONNET | Bedrock | $3.00 | $15.00 | 1M | 64k | - |
| Claude Haiku 4.5 | claude-haiku-4-5 | GENAI_SHARED_VERTEXAI_ANTHROPIC_CLAUDE_45_HAIKU | Vertex AI | $1.00 | $5.00 | 200k | 8k | - |
| Claude Haiku 4.5 | - | GENAI_SHARED_BEDROCK_ANTHROPIC_CLAUDE_45_HAIKU | Bedrock | $1.00 | $5.00 | 200k | 8k | - |
Models marked with 1M context (Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, Sonnet 4.6, Sonnet 4) support extended context via the anthropic-beta: context-1m-2025-08-07 header. The gateway automatically injects this header — no client configuration needed. The full 1M context window is included at standard pricing with no extra cost.
OpenAI Models
| Official Name | Vendor Name | Gateway Model ID 🔑 | PwC Cloud Provider | Input ($/1M) | Output ($/1M) | Context | Max Output | Responses API |
|---|---|---|---|---|---|---|---|---|
| GPT-5.2 Codex ⭐ | gpt-5.2-codex | GENAI_SHARED_OPENAI_GPT_52_CODEX | OpenAI | $1.75 | $14.00 | 400k | 128k | ✅ |
| GPT-5.2 | gpt-5.2 | GENAI_SHARED_OPENAI_GPT_52 | OpenAI | $1.75 | $14.00 | 400k | 128k | - |
| GPT-5.1 Codex | gpt-5.1-codex | GENAI_SHARED_OPENAI_GPT_51_CODEX | OpenAI | $1.25 | $10.00 | 272k | 128k | ✅ |
| GPT-5.1 | gpt-5.1 | GENAI_SHARED_OPENAI_GPT_51 | OpenAI | $1.25 | $10.00 | 272k | 128k | - |
| GPT-5 Codex | gpt-5-codex | GENAI_SHARED_OPENAI_GPT_5_CODEX | OpenAI | $1.25 | $10.00 | 272k | 128k | ✅ |
| GPT-5.4 | gpt-5.4 | GENAI_SHARED_OPENAI_OPENAI_GPT_54 | OpenAI | $2.50 | $15.00 | 1M | 128k | ✅ |
| GPT-5.4 Mini | gpt-5.4-mini | GENAI_SHARED_OPENAI_OPENAI_GPT_54_MINI | OpenAI | $0.75 | $4.50 | 400k | 128k | ✅ |
| GPT-5.4 Nano | gpt-5.4-nano | GENAI_SHARED_OPENAI_OPENAI_GPT_54_NANO | OpenAI | $0.20 | $1.25 | 400k | 128k | ✅ |
| GPT-5.4 Pro | gpt-5.4-pro | GENAI_SHARED_OPENAI_OPENAI_GPT_54_PRO | OpenAI | - | - | 400k | 128k | ✅ |
| GPT-5.5 | - | GENAI_SHARED_OPENAI_OPENAI_GPT_55 | OpenAI | $5.00 | $30.00 | 1M | 128k | ✅ |
| GPT-5.5 | gpt-5.5 | GENAI_SHARED_AZURE_OPENAI_GPT_55 | Azure | $5.00 | $30.00 | 1M | 128k | ✅ |
| GPT-5.6 Luna (EU) | gpt-5.6-luna | GENAI_SHARED_OPENAI_OPENAI_GPT_56_LUNA | OpenAI | $1.00 | $6.00 | 1M | 128k | - |
| GPT-5.6 Sol (EU) | gpt-5.6-sol | GENAI_SHARED_OPENAI_OPENAI_GPT_56_SOL | OpenAI | $5.00 | $30.00 | 1M | 128k | - |
| GPT-5.6 Terra (EU) | gpt-5.6-terra | GENAI_SHARED_OPENAI_OPENAI_GPT_56_TERRA | OpenAI | $2.50 | $15.00 | 1M | 128k | - |
| GPT-5 | gpt-5 | GENAI_SHARED_AZURE_OPENAI_GPT_5 | Azure | $1.25 | $10.00 | 272k | 128k | - |
| GPT-5 Mini | gpt-5-mini | GENAI_SHARED_AZURE_OPENAI_GPT_5_MINI | Azure | $0.25 | $2.00 | 272k | 128k | - |
| GPT-5 Nano | gpt-5-nano | GENAI_SHARED_AZURE_OPENAI_GPT_5_NANO | Azure | $0.05 | $0.40 | 272k | 128k | - |
The Responses API column indicates which models support OpenAI's Responses API format. This is required for Codex coding agent compatibility. Models marked with ✅ can be used with Codex; models marked with - cannot.
Google Models
| Official Name | Vendor Name | Gateway Model ID 🔑 | PwC Cloud Provider | Input ($/1M) | Output ($/1M) | Context | Max Output | Responses API |
|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | GENAI_SHARED_VERTEXAI_GOOGLE_GEMINI_25_PRO | Vertex AI | $1.25 | $10.00 | 1M | 65k | - |
| Gemini 2.5 Flash ⭐ | gemini-2.5-flash | GENAI_SHARED_VERTEXAI_GOOGLE_GEMINI_25_FLASH | Vertex AI | $0.30 | $2.50 | 1M | 65k | - |
| Gemini 2.5 Flash Lite | gemini-2.5-flash-lite | GENAI_SHARED_VERTEXAI_GOOGLE_GEMINI_25_FLASH_LITE | Vertex AI | $0.10 | $0.40 | 1M | 65k | - |
Self-Hosted and Partner Models (PwC Agent)
These models are served through the PwC Agent orchestrator (self-hosted on PwC infrastructure or via Azure AI Foundry). Use the Model ID shown as the model value.
| Official Name | Model ID | Hosting | Notes |
|---|---|---|---|
| GLM-5.2 | glm | Self-hosted | General coding model |
| Qwen3-27B (thinking) | qwen-thinking | Self-hosted | Thinking mode enabled |
| Qwen3-27B (fast) | qwen-fast | Self-hosted | Thinking mode disabled |
| DeepSeek V4 Flash (thinking) | ds4 | Self-hosted | Thinking mode enabled |
| DeepSeek V4 Flash (fast) | ds4-fast | Self-hosted | Thinking mode disabled |
| Ternary-Bonsai-27B | bonsai | Self-hosted | Fallback model |
| Claude Fable 5 | claude-fable-5 | Vertex AI (PwC Agent) | |
| DeepSeek V4 Pro | DeepSeek-V4-Pro | Azure AI Foundry | |
| Kimi K2.6 | Kimi-K2.6 | Azure AI Foundry |
Discovering your models (/models command)
GET /models (OpenAI shape) and GET /v1/models (Anthropic shape) return the models available to your API key — restricted models (e.g. Claude Fable 5, GPT-5.6 Sol) are listed only if your key is entitled.
Claude Code users can install a /models slash command that shows this list directly in the CLI:
mkdir -p ~/.claude/commands
curl -fsSL https://idi-coding-agents.pwc.it/downloads/models-command.md -o ~/.claude/commands/models.md
Then type /models inside Claude Code to get a table of the model IDs you can use with /model <id>.
Automatic Model Selection (auto)
Set model to auto to let the gateway pick the best model for each request. A task classifier analyses your message (task type and difficulty) and routes it to an appropriate backend — lightweight self-hosted models for simple tasks, Claude Sonnet/Opus for hard coding or planning tasks.
Embedding Models
Available via the /embeddings endpoint:
| Official Name | Vendor Name | Gateway Model ID 🔑 | PwC Cloud Provider |
|---|---|---|---|
| Text Embedding 3 Large | text-embedding-3-large | GENAI_SHARED_AZURE_OPENAI_TEXT_EMBEDDING_003_LARGE | Azure |
| Text Embedding Ada 002 | text-embedding-ada-002 | GENAI_SHARED_AZURE_OPENAI_TEXT_ADA_002 | Azure |
| Titan Embed Image v1 | titan-embed-image-v1 | GENAI_SHARED_BEDROCK_AMAZON_TITAN_EMBED_IMAGE_V1 | Bedrock |
| Gemini Embedding | gemini-embedding | GENAI_SHARED_VERTEXAI_GEMINI_EMBEDDING | Vertex AI |