Built-in LLM Models¶
Trailblaze ships with the following built-in models. When you reference a model by id in your trails/config/trailblaze.yaml, all specs below are inherited automatically.
These models can change between Trailblaze releases (models added/removed, pricing updated). For stable, predictable configuration, set explicit values in your workspace trails/config/trailblaze.yaml.
Anthropic¶
| Model ID | Context | Max Output | Input $/1M | Output $/1M | Cached Input $/1M | Capabilities |
|---|---|---|---|---|---|---|
claude-fable-5 |
1M | 128K | $10.00 | $50.00 | $1.00 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
claude-haiku-4-5 |
200K | 64K | $1.00 | $5.00 | $0.10 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
claude-opus-5 |
1M | 128K | $5.00 | $25.00 | $0.50 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
claude-sonnet-5 |
1M | 128K | $3.00 | $15.00 | $0.30 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
Google¶
| Model ID | Context | Max Output | Input $/1M | Output $/1M | Cached Input $/1M | Capabilities |
|---|---|---|---|---|---|---|
gemini-3.1-flash-lite |
1M | 65K | $0.25 | $1.50 | $0.03 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemini-3.1-pro-preview |
1M | 65K | $2.00 | $12.00 | $0.20 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemini-3.5-flash |
1M | 65K | $1.50 | $9.00 | $0.15 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemini-3.5-flash-lite |
1M | 65K | $0.30 | $2.50 | $0.03 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemini-3.6-flash |
1M | 65K | $1.50 | $7.50 | $0.15 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemma-4-26b-a4b-it |
262K | 32K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemma-4-31b-it |
262K | 32K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
Ollama¶
| Model ID | Context | Max Output | Input $/1M | Output $/1M | Cached Input $/1M | Capabilities |
|---|---|---|---|---|---|---|
gemma4:12b |
262K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemma4:26b |
262K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gemma4:31b |
262K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gpt-oss:120b |
131K | 65K | free | free | free | basic-json-schema, completion, document, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gpt-oss:20b |
131K | 65K | free | free | free | basic-json-schema, completion, document, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3-vl:2b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3-vl:30b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3-vl:4b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3-vl:8b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:0.8b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:122b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:27b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:2b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:35b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:4b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:9b |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen3.5:latest |
131K | 8K | free | free | free | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
OpenAI¶
| Model ID | Context | Max Output | Input $/1M | Output $/1M | Cached Input $/1M | Capabilities |
|---|---|---|---|---|---|---|
gpt-5.6-luna |
1M | 128K | $0.20 | $1.20 | $0.02 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gpt-5.6-sol |
1M | 128K | $5.00 | $30.00 | $0.50 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
gpt-5.6-terra |
1M | 128K | $2.00 | $12.00 | $0.20 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
OpenRouter¶
| Model ID | Context | Max Output | Input $/1M | Output $/1M | Cached Input $/1M | Capabilities |
|---|---|---|---|---|---|---|
openai/gpt-oss-120b:free |
131K | 131K | free | free | free | basic-json-schema, completion, document, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
qwen/qwen3-vl-8b-instruct |
131K | 32K | $0.08 | $0.50 | $0.08 | basic-json-schema, completion, document, image, multipleChoices, openai-endpoint-chat-completions, openai-endpoint-responses, speculation, standard-json-schema, temperature, toolChoice, tools |
Using Built-in Models in YAML Config¶
Reference any model above by its ID:
providers:
"openai":
models:
- id: "gpt-5.6-sol"
- id: "gpt-5.6-terra"
- id: "gpt-5.6-luna"
cost:
input_per_million: 0.3
When using a custom endpoint, specify the model specs explicitly. See the tables above for reference values:
providers:
"my_gateway":
type: "openai_compatible"
base_url: "https://gateway.example.com/v1"
models:
- id: "my-gpt4-deployment"
vision: true
context_length: 1048576
max_output_tokens: 32768
NOTE: THIS IS GENERATED DOCUMENTATION