Pioneer model catalog: encoders, decoders, and inference

Pioneer supports two model families: encoder models (GLiNER) for structured extraction tasks like named entity recognition, and decoder models (LLMs) for text generation, classification, and open-ended prompting. The tables below are a snapshot of the current catalog — use GET /base-models to query the live list, which always reflects current availability and capabilities.

Encoder models (GLiNER)

GLiNER models perform named entity recognition and structured extraction. Most encoder models support both LoRA and full fine-tuning, and are served on-demand after training.

Model ID	Label	Input	Output	Training	Inference
`fastino/gliner2-base-v1`	GLiNER2 Base	$0.15	$0.15	LoRA, Full	On-demand
`fastino/gliner2-large-v1`	GLiNER2 Large	$0.15	$0.15	LoRA, Full	On-demand
`fastino/gliner2-multi-v1`	GLiNER2 Multi	$0.15	$0.15	LoRA, Full	On-demand
`fastino/gliner2-multi-large-v1`	GLiNER2 Multi Large	$0.15	$0.15	LoRA, Full	On-demand

fastino/gliner2-multi-v1 and fastino/gliner2-multi-large-v1 are multilingual variants suitable for non-English text.

Decoder models — training

These LLMs are available for LoRA fine-tuning via POST /felix/training-jobs. When you submit a job, Pioneer automatically routes it to the best available provider.

Model ID	Label	Input	Output	Context
`Qwen/Qwen3-32B`	Qwen3 32B	$0.90	$0.90	131K
`Qwen/Qwen3-8B`	Qwen3 8B	$0.20	$0.20	131K
`Qwen/Qwen3-4B-Instruct-2507`	Qwen3 4B Instruct	$0.20	$0.20	262K
`Qwen/Qwen3-4B`	Qwen3 4B Base	$0.15	$0.15	131K
`Qwen/Qwen3-1.7B`	Qwen3 1.7B Base	$0.10	$0.10	131K
`Qwen/Qwen3.5-9B`	Qwen3.5 9B	$0.30	$0.30	32K
`Qwen/Qwen3.6-27B`	Qwen3.6 27B	$0.60	$0.60	32K
`google/gemma-4-31b-it`	Gemma 4 31B IT	$0.50	$0.50	128K
`google/gemma-4-12b-it`	Gemma 4 12B IT	$0.25	$0.25	128K
`google/gemma-4-e2b-it`	Gemma 4 E2B IT	$0.10	$0.10	128K
`google/gemma-4-e4b-it`	Gemma 4 E4B IT	$0.20	$0.20	128K
`google/gemma-3-4b`	Gemma 3 4B	$0.15	$0.15	128K
`meta-llama/Llama-3.3-70B-Instruct`	Llama 3.3 70B Instruct	$0.90	$0.90	131K
`meta-llama/Llama-3.1-8B-Instruct`	Llama 3.1 8B Instruct	$0.02	$0.05	131K
`meta-llama/Llama-3.2-3B-Instruct`	Llama 3.2 3B Instruct	$0.051	$0.335	131K
`meta-llama/Llama-3.2-1B-Instruct`	Llama 3.2 1B Instruct	$0.027	$0.201	131K
`HuggingFaceTB/SmolLM3-3B`	SmolLM3 3B Base	$0.15	$0.15	131K

Decoder models — serverless inference

These models are pre-deployed and available for inference immediately — no fine-tuning required and no startup latency. Prices are per 1M tokens.

Anthropic

Model ID	Label	Input	Output	Context
`claude-haiku-4-5`	Claude Haiku 4.5	$1.00	$5.00	200K
`claude-sonnet-4-6`	Claude Sonnet 4.6	$3.00	$15.00	1M
`claude-opus-4-1`	Claude Opus 4.1	$15.00	$75.00	200K
`claude-opus-4-5`	Claude Opus 4.5	$5.00	$25.00	200K
`claude-opus-4-6`	Claude Opus 4.6	$5.00	$25.00	1M
`claude-opus-4-7`	Claude Opus 4.7	$5.00	$25.00	1M
`claude-opus-4-8`	Claude Opus 4.8	$5.00	$25.00	1M
`claude-fable-5`	Claude Fable 5	$10.00	$50.00	1M

OpenAI

Model ID	Label	Input	Output	Context
`gpt-4o`	GPT-4o	$2.50	$10.00	128K
`gpt-4o-mini`	GPT-4o mini	$0.15	$0.60	128K
`gpt-4.1`	GPT-4.1	$2.00	$8.00	1M
`gpt-4.1-mini`	GPT-4.1 mini	$0.40	$1.60	1M
`gpt-4.1-nano`	GPT-4.1 nano	$0.10	$0.40	1M
`gpt-5-mini`	GPT-5 mini	$0.25	$2.00	400K
`gpt-5-nano`	GPT-5 nano	$0.05	$0.40	400K
`gpt-5.1`	GPT-5.1	$1.25	$10.00	400K
`gpt-5.4`	GPT-5.4	$2.50	$15.00	400K
`gpt-5.4-mini`	GPT-5.4 mini	$0.75	$4.50	400K
`gpt-5.4-nano`	GPT-5.4 nano	$0.20	$1.25	400K
`gpt-5.5`	GPT-5.5	$5.00	$30.00	400K
`openai/gpt-oss-20b`	GPT-OSS 20B	$0.07	$0.30	131K
`openai/gpt-oss-120b`	GPT-OSS 120B	$0.15	$0.60	131K

Google

Model ID	Label	Input	Output	Context
`gemini-3.1-pro`	Gemini 3.1 Pro	$2.00	$12.00	1M
`gemini-3.5-flash`	Gemini 3.5 Flash	$1.50	$9.00	1M
`gemini-3-flash`	Gemini 3 Flash	$0.50	$3.00	1M

Mistral

Model ID	Label	Input	Output	Context
`mistralai/Mistral-Medium-3.5`	Mistral Medium 3.5	$1.50	$7.50	131K
`mistralai/Mistral-Small-4`	Mistral Small 4	$0.15	$0.60	131K
`mistralai/Mistral-Nemo`	Mistral Nemo	$0.02	$0.03	131K

DeepSeek

Model ID	Label	Input	Output	Context
`deepseek-ai/DeepSeek-V4-Pro`	DeepSeek V4 Pro	$0.435	$0.87	163K
`deepseek-ai/DeepSeek-V4-Flash`	DeepSeek V4 Flash	$0.10	$0.20	163K

Qwen

Model ID	Label	Input	Output	Context
`Qwen/Qwen3-32B`	Qwen3 32B	$0.08	$0.28	131K
`Qwen/Qwen3.6-Flash`	Qwen3.6 Flash	$0.1875	$1.125	131K
`Qwen/Qwen3.6-35B-A3B`	Qwen3.6 35B A3B	$0.14	$1.00	131K
`Qwen/Qwen3.6-Plus`	Qwen3.6 Plus	$0.33	$1.95	131K
`Qwen/Qwen3.6-Max-Preview`	Qwen3.6 Max Preview	$1.04	$6.24	131K
`Qwen/Qwen3.7-Max`	Qwen3.7 Max	$1.25	$3.75	131K

Meta (Llama)

Model ID	Label	Input	Output	Context
`meta-llama/Llama-3.2-1B-Instruct`	Llama 3.2 1B Instruct	$0.027	$0.201	131K
`meta-llama/Llama-3.2-3B-Instruct`	Llama 3.2 3B Instruct	$0.051	$0.335	131K
`meta-llama/Llama-3.1-8B-Instruct`	Llama 3.1 8B Instruct	$0.02	$0.05	131K
`meta-llama/Llama-3.3-70B-Instruct`	Llama 3.3 70B Instruct	$0.90	$0.90	131K

Others

Model ID	Label	Input	Output	Context
`nvidia/nemotron-3-ultra`	NVIDIA Nemotron 3 Ultra	$0.50	$2.50	131K
`zai-org/GLM-5.1`	GLM 5.1	$0.98	$3.08	202.8K
`moonshotai/Kimi-K2.6`	Kimi K2.6	$0.684	$3.42	262K
`MiMo-V2.5-Pro`	MiMo V2.5 Pro	$0.435	$0.87	131K
`MiniMax/M2.7`	MiniMax M2.7	$0.279	$1.20	131K
`MiniMax/M3`	MiniMax M3	$0.30	$1.20	131K
`liquidai/LFM2-24B-A2B`	LFM2 24B A2B	$0.03	$0.12	131K
`fastino/gliguard-llm-guardrails-300m`	GLiGuard LLM Guardrails 300M	$0.15	$0.15	—
`fastino/gliner2-privacy-filter-pii`	GLiNER2 Privacy Filter PII	$0.15	$0.15	—

On-demand vs. serverless inference

Pioneer offers two ways to serve predictions, and the right choice depends on your workflow. Serverless inference uses pre-deployed base model endpoints. There is no startup delay and you are billed per token. This is the default for models in the serverless table above and is ideal when you want to call a frontier model without fine-tuning. On-demand inference provisions a dedicated GPU after fine-tuning completes. Your LoRA adapter is loaded onto the GPU and served exclusively for your requests. Pioneer routes inference calls to an on-demand deployment automatically when you pass a training job ID as model_id.

Querying the live catalog

The tables above may lag behind newly added models. Use GET /base-models to get the current catalog at runtime.

# All models
curl https://api.pioneer.ai/base-models \
  -H "X-API-Key: YOUR_API_KEY"

# Only models that support inference
curl "https://api.pioneer.ai/base-models?supports_inference=true" \
  -H "X-API-Key: YOUR_API_KEY"

# Only models that support training
curl "https://api.pioneer.ai/base-models?supports_training=true" \
  -H "X-API-Key: YOUR_API_KEY"

# Filter by model family
curl "https://api.pioneer.ai/base-models?task_type=encoder" \
  -H "X-API-Key: YOUR_API_KEY"

curl "https://api.pioneer.ai/base-models?task_type=decoder" \
  -H "X-API-Key: YOUR_API_KEY"

Each entry in the response includes the model ID, its display label, context length, and boolean flags for supports_training and supports_inference. Use the model ID value directly in training job requests and inference calls.

​Encoder models (GLiNER)

​Decoder models — training

​Decoder models — serverless inference

​Anthropic

​OpenAI

​Google

​Mistral

​DeepSeek

​Qwen

​Meta (Llama)

​Others

​On-demand vs. serverless inference

​Querying the live catalog