> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pioneer.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pioneer model catalog: encoders, decoders, and inference

> Browse Pioneer's encoder (GLiNER) and decoder (LLM) models for fine-tuning and inference. Covers on-demand vs. serverless and how to query the live catalog.

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.

Some rollout-stage models are feature-gated. They appear in the live catalog only for workspaces that have the corresponding rollout enabled.

## Encoder models (GLiNER)

GLiNER models perform named entity recognition and structured extraction. Most GLiNER base models support both training and on-demand inference after training. Prices are per 1M tokens.

| Model ID                                   | Label                              | Input  | Output | Training   | Inference             |
| :----------------------------------------- | :--------------------------------- | :----- | :----- | :--------- | :-------------------- |
| `fastino/gliner2-base-v1`                  | GLiNER2 Base                       | \$0.15 | \$0.15 | LoRA, Full | Serverless, On-demand |
| `fastino/gliner2-large-v1`                 | GLiNER2 Large                      | \$0.15 | \$0.15 | LoRA, Full | Serverless, On-demand |
| `fastino/gliner2-multi-v1`                 | GLiNER2 Multi                      | \$0.15 | \$0.15 | LoRA, Full | Serverless, On-demand |
| `fastino/gliner2-multi-large-v1`           | GLiNER2 Multi Large                | \$0.15 | \$0.15 | LoRA, Full | Serverless, On-demand |
| `fastino/gliguard-LLMGuardrails-300M`      | GLiGuard LLM Guardrails 300M       | \$0.15 | \$0.15 | —          | Serverless            |
| `fastino/gliner2-privacy-filter-PII-multi` | GLiNER2 Privacy Filter PII (Multi) | \$0.15 | \$0.15 | —          | Serverless            |
| `fastino/gliguard-PII-multi`               | GLiNER2-Guardrails-PII-Multi       | \$0.15 | \$0.15 | —          | Serverless            |

`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/Qwen2.5-Coder-0.5B`            | Qwen2.5 Coder 0.5B       | \$0.10 | \$0.10  | 32,768  |
| `Qwen/Qwen3-1.7B-Base`               | Qwen3 1.7B Base          | \$0.10 | \$0.10  | 32,768  |
| `Qwen/Qwen3-32B`                     | Qwen3 32B                | \$0.90 | \$0.90  | 32,768  |
| `Qwen/Qwen3-4B-Base`                 | Qwen3 4B Base            | \$0.15 | \$0.15  | 32,768  |
| `Qwen/Qwen3-4B-Instruct-2507`        | Qwen3 4B Instruct        | \$0.20 | \$0.20  | 32,768  |
| `Qwen/Qwen3-8B`                      | Qwen3 8B                 | \$0.20 | \$0.20  | 40,960  |
| `Qwen/Qwen3.5-9B`                    | Qwen3.5 9B               | \$0.30 | \$0.30  | 32,768  |
| `Qwen/Qwen3.6-27B`                   | Qwen3.6 27B              | \$0.60 | \$0.60  | 32,768  |
| `google/gemma-3-4b-pt`               | Gemma 3 4B (Pretrained)  | \$0.15 | \$0.15  | 32,768  |
| `google/gemma-4-12B-it`              | Gemma 4 12B IT           | \$0.25 | \$0.25  | 32,768  |
| `google/gemma-4-31B-it`              | Gemma 4 31B IT           | \$0.50 | \$0.50  | 32,768  |
| `google/gemma-4-E2B-it`              | Gemma 4 E2B IT           | \$0.10 | \$0.10  | 32,768  |
| `google/gemma-4-E4B-it`              | Gemma 4 E4B IT           | \$0.20 | \$0.20  | 32,768  |
| `meta-llama/Llama-3.1-8B-Instruct`   | Llama 3.1 8B Instruct    | \$0.20 | \$0.20  | 16,384  |
| `meta-llama/Llama-3.2-1B-Instruct`   | Llama 3.2 1B Instruct    | \$0.10 | \$0.201 | 60,000  |
| `mistralai/Mistral-7B-Instruct-v0.3` | Mistral 7B Instruct v0.3 | \$0.20 | \$0.20  | 32,768  |
| `HuggingFaceTB/SmolLM3-3B-Base`      | SmolLM3 3B Base          | \$0.15 | \$0.15  | 32,768  |

## Decoder models — serverless inference

These decoder models are pre-deployed and available for inference immediately. Trainable decoder rows that also support serverless inference are listed in the training table above and are not repeated here.

### Anthropic

| Model ID            | Label             | Input   | Output  | Context   |
| ------------------- | ----------------- | ------- | ------- | --------- |
| `claude-fable-5`    | Claude Fable 5    | \$10.00 | \$50.00 | 1,000,000 |
| `claude-haiku-4-5`  | Claude Haiku 4.5  | \$1.00  | \$5.00  | 200,000   |
| `claude-opus-4-1`   | Claude Opus 4.1   | \$15.00 | \$75.00 | 200,000   |
| `claude-opus-4-5`   | Claude Opus 4.5   | \$5.00  | \$25.00 | 200,000   |
| `claude-opus-4-6`   | Claude Opus 4.6   | \$5.00  | \$25.00 | 1,000,000 |
| `claude-opus-4-7`   | Claude Opus 4.7   | \$5.00  | \$25.00 | 1,000,000 |
| `claude-opus-4-8`   | Claude Opus 4.8   | \$5.00  | \$25.00 | 1,000,000 |
| `claude-sonnet-4-5` | Claude Sonnet 4.5 | \$3.00  | \$15.00 | 200,000   |
| `claude-sonnet-4-6` | Claude Sonnet 4.6 | \$3.00  | \$15.00 | 1,000,000 |
| `claude-sonnet-5`   | Claude Sonnet 5   | \$2.00  | \$10.00 | 1,000,000 |

### OpenAI

| Model ID              | Label         | Input  | Output  | Context   |
| --------------------- | ------------- | ------ | ------- | --------- |
| `gpt-4o`              | GPT-4o        | \$2.50 | \$10.00 | 128,000   |
| `gpt-4o-mini`         | GPT-4o mini   | \$0.15 | \$0.60  | 128,000   |
| `gpt-4.1`             | GPT-4.1       | \$2.00 | \$8.00  | 1,047,576 |
| `gpt-4.1-mini`        | GPT-4.1 mini  | \$0.40 | \$1.60  | 1,047,576 |
| `gpt-4.1-nano`        | GPT-4.1 nano  | \$0.10 | \$0.40  | 1,047,576 |
| `gpt-5-mini`          | GPT-5 mini    | \$0.25 | \$2.00  | 400,000   |
| `gpt-5-nano`          | GPT-5 nano    | \$0.05 | \$0.40  | 400,000   |
| `gpt-5.1`             | GPT-5.1       | \$1.25 | \$10.00 | 400,000   |
| `gpt-5.3-codex`       | GPT-5.3 Codex | \$1.75 | \$14.00 | 400,000   |
| `gpt-5.4`             | GPT-5.4       | \$2.50 | \$15.00 | 1,047,576 |
| `gpt-5.4-mini`        | GPT-5.4 mini  | \$0.75 | \$4.50  | 400,000   |
| `gpt-5.4-nano`        | GPT-5.4 nano  | \$0.20 | \$1.25  | 1,047,576 |
| `gpt-5.5`             | GPT-5.5       | \$5.00 | \$30.00 | 1,000,000 |
| `gpt-5.6-luna`        | GPT-5.6 Luna  | \$1.00 | \$6.00  | 1,050,000 |
| `gpt-5.6-terra`       | GPT-5.6 Terra | \$2.50 | \$15.00 | 1,050,000 |
| `gpt-5.6-sol`         | GPT-5.6 Sol   | \$5.00 | \$30.00 | 1,050,000 |
| `openai/gpt-oss-20b`  | GPT-OSS 20B   | \$0.07 | \$0.30  | 131,072   |
| `openai/gpt-oss-120b` | GPT-OSS 120B  | \$0.15 | \$0.60  | 131,072   |

### Google

| Model ID                           | Label                     | Input  | Output  | Context   |
| ---------------------------------- | ------------------------- | ------ | ------- | --------- |
| `google/diffusiongemma-26B-A4B-it` | DiffusionGemma 26B-A4B IT | \$0.50 | \$0.50  | 262,144   |
| `gemini-3.1-pro`                   | Gemini 3.1 Pro            | \$2.00 | \$12.00 | 1,048,576 |
| `gemini-3.1-flash-lite`            | Gemini 3.1 Flash Lite     | \$0.25 | \$1.50  | 1,000,000 |
| `gemini-3.5-flash`                 | Gemini 3.5 Flash          | \$1.50 | \$9.00  | 1,048,576 |
| `gemini-3.5-flash-lite`            | Gemini 3.5 Flash Lite     | \$0.30 | \$2.50  | 1,000,000 |
| `gemini-3.6-flash`                 | Gemini 3.6 Flash          | \$1.50 | \$7.50  | 1,000,000 |
| `gemini-3-flash`                   | Gemini 3 Flash            | \$0.50 | \$3.00  | 1,048,576 |

### Mistral

| Model ID                               | Label              | Input  | Output | Context |
| -------------------------------------- | ------------------ | ------ | ------ | ------- |
| `mistral-medium-3.5`                   | Mistral Medium 3.5 | \$1.50 | \$7.50 | 262,144 |
| `mistralai/Mistral-Small-4-119B-2603`  | Mistral Small 4    | \$0.15 | \$0.60 | 262,144 |
| `mistralai/Mistral-Nemo-Instruct-2407` | Mistral Nemo       | \$0.02 | \$0.03 | 131,072 |

### DeepSeek

| Model ID                        | Label             | Input   | Output | Context   |
| ------------------------------- | ----------------- | ------- | ------ | --------- |
| `deepseek-ai/DeepSeek-V4-Pro`   | DeepSeek V4 Pro   | \$0.435 | \$0.87 | 1,000,000 |
| `deepseek-ai/DeepSeek-V4-Flash` | DeepSeek V4 Flash | \$0.10  | \$0.20 | 1,000,000 |
| `deepseek-ai/DeepSeek-V3`       | DeepSeek V3 0324  | \$0.27  | \$1.12 | 163,840   |

### Qwen

| Model ID               | Label               | Input    | Output  | Context   |
| ---------------------- | ------------------- | -------- | ------- | --------- |
| `Qwen/Qwen3.6-35B-A3B` | Qwen3.6 35B A3B     | \$0.14   | \$1.00  | 262,144   |
| `qwen3.6-flash`        | Qwen3.6 Flash       | \$0.1875 | \$1.125 | 1,000,000 |
| `qwen3.6-max-preview`  | Qwen3.6 Max Preview | \$1.04   | \$6.24  | 262,144   |
| `qwen3.6-plus`         | Qwen3.6 Plus        | \$0.325  | \$1.95  | 1,000,000 |
| `qwen3.7-max`          | Qwen3.7 Max         | \$1.25   | \$3.75  | 1,000,000 |
| `qwen3.7-plus`         | Qwen3.7 Plus        | \$0.32   | \$1.28  | 1,000,000 |

### Meta

| Model ID                            | Label                  | Input  | Output  | Context   |
| :---------------------------------- | :--------------------- | :----- | :------ | :-------- |
| `meta-llama/Llama-3.2-3B-Instruct`  | Llama 3.2 3B Instruct  | \$0.10 | \$0.335 | 80,000    |
| `meta-llama/Llama-3.3-70B-Instruct` | Llama 3.3 70B Instruct | \$0.90 | \$0.90  | 16,384    |
| `meta/muse-spark-1.1`               | Muse Spark 1.1         | \$1.25 | \$4.25  | 1,048,576 |

### Z.ai

| Model ID          | Label   | Input  | Output | Context   |
| ----------------- | ------- | ------ | ------ | --------- |
| `zai-org/GLM-5.1` | GLM 5.1 | \$0.98 | \$3.08 | 202,752   |
| `zai-org/GLM-5.2` | GLM 5.2 | \$1.40 | \$4.40 | 1,048,576 |

### Liquid AI

| Model ID                | Label        | Input  | Output | Context |
| ----------------------- | ------------ | ------ | ------ | ------- |
| `LiquidAI/LFM2-24B-A2B` | LFM2 24B A2B | \$0.03 | \$0.12 | 128,000 |

### Xiaomi MiMo

| Model ID                   | Label         | Input   | Output | Context   |
| -------------------------- | ------------- | ------- | ------ | --------- |
| `XiaomiMiMo/MiMo-V2.5`     | MiMo V2.5     | \$0.14  | \$0.28 | 1,048,576 |
| `XiaomiMiMo/MiMo-V2.5-Pro` | MiMo V2.5 Pro | \$0.435 | \$0.87 | 1,048,576 |

### MiniMax

| Model ID                 | Label        | Input   | Output | Context |
| ------------------------ | ------------ | ------- | ------ | ------- |
| `MiniMaxAI/MiniMax-M2.7` | MiniMax M2.7 | \$0.279 | \$1.20 | 196,608 |
| `MiniMaxAI/MiniMax-M3`   | MiniMax M3   | \$0.30  | \$1.20 | 524,288 |

### Moonshot AI

| Model ID                    | Label          | Input  | Output | Context |
| --------------------------- | -------------- | ------ | ------ | ------- |
| `moonshotai/Kimi-K2.6`      | Kimi K2.6      | \$0.95 | \$4.00 | 256,000 |
| `moonshotai/Kimi-K2.7-Code` | Kimi K2.7 Code | \$0.95 | \$4.00 | 262,144 |

### NVIDIA

| Model ID                                        | Label            | Input  | Output | Context   |
| ----------------------------------------------- | ---------------- | ------ | ------ | --------- |
| `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`    | Nemotron 3 Nano  | \$0.05 | \$0.20 | 262,144   |
| `nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8`  | Nemotron 3 Super | \$0.09 | \$0.45 | 1,000,000 |
| `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16` | Nemotron 3 Ultra | \$0.50 | \$2.50 | 1,000,000 |

### xAI

| Model ID   | Label    | Input  | Output | Context |
| ---------- | -------- | ------ | ------ | ------- |
| `grok-4.5` | Grok 4.5 | \$2.00 | \$6.00 | 500,000 |

### Sakana AI

| Model ID            | Label             | Input  | Output  | Context   |
| ------------------- | ----------------- | ------ | ------- | --------- |
| `sakana/fugu-ultra` | Sakana Fugu Ultra | \$5.00 | \$30.00 | 1,000,000 |

### Poolside

| Model ID                | Label        | Input  | Output | Context   |
| ----------------------- | ------------ | ------ | ------ | --------- |
| `poolside/laguna-s-2.1` | Laguna S 2.1 | \$0.10 | \$0.20 | 1,000,000 |

`poolside/laguna-s-2.1` is an open-weight model (OpenMDW-1.1 license) for agentic coding and long-horizon work.

### Embeddings

Embedding-only models. They don't support chat or text-generation inference, but they are live and fully servable through `POST /v1/embeddings` (the deprecated `POST /felix/embeddings` wraps the same path). Use them as the `model` value in an embeddings request — not as a `model_id` for chat/completions or training.

| Model ID                  | Label                  | Input  | Output | Context |
| ------------------------- | ---------------------- | ------ | ------ | ------- |
| `text-embedding-3-large`  | text-embedding-3-large | \$0.13 | —      | 8,191   |
| `text-embedding-3-small`  | text-embedding-3-small | \$0.02 | —      | 8,191   |
| `text-embedding-ada-002`  | text-embedding-ada-002 | \$0.10 | —      | 8,191   |
| `BAAI/bge-m3`             | BGE-M3                 | \$0.01 | —      | 8,192   |
| `Qwen/Qwen3-Embedding-4B` | Qwen3 Embedding 4B     | \$0.02 | —      | 32,768  |
| `Qwen/Qwen3-Embedding-8B` | Qwen3 Embedding 8B     | \$0.01 | —      | 32,768  |

## Prompt caching

Many serverless models bill cached input tokens at a discount, and some providers bill a one-time surcharge to write tokens into the cache. Pioneer passes each provider's published cache rates straight through — these are the same rates `GET /base-models` returns as `cache_read_price_per_million` and `cache_write_price_per_million`, and the same rates Pioneer bills you.

Cache rates are derived from each model's input rate using the multipliers below. Where a provider has no separate cache-write line item, cache writes bill at the standard input rate.

| Provider              | Cache read  | Cache write |
| --------------------- | ----------- | ----------- |
| Anthropic (Claude)    | 0.1× input  | 1.25× input |
| OpenAI (GPT-4 family) | 0.5× input  | input rate  |
| OpenAI (GPT-5 family) | 0.1× input  | input rate  |
| Google (Gemini)       | 0.1× input  | input rate  |
| Qwen                  | 0.2× input  | 1.25× input |
| Mistral               | 0.1× input  | input rate  |
| MiniMax               | 0.2× input  | input rate  |
| NVIDIA (Nemotron)     | 0.3× input  | input rate  |
| xAI (Grok)            | 0.25× input | input rate  |
| Sakana AI             | 0.1× input  | input rate  |

Self-hosted models served on Modal — and any provider without an explicit cache discount — bill cached input at the standard input rate. Fireworks-served models carry per-model cache rates rather than a single ratio, so query the live catalog for exact values.

For example, `claude-opus-4-8` lists \$5.00 input, so cache reads bill at \$0.50 and cache writes at \$6.25 per 1M tokens. `gpt-5.1` lists \$1.25 input, so cache reads bill at \$0.125 per 1M tokens.

## 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 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.

```bash theme={null}
# 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, per-1M-token rates (`input_price_per_million`, `output_price_per_million`, `cache_read_price_per_million`, `cache_write_price_per_million`), and boolean flags for `supports_training` and `supports_inference`. Use the model ID value directly in training job requests and inference calls.

To list every model alongside its input, output, and cache rates:

```bash theme={null}
curl -s "https://api.pioneer.ai/base-models?supports_inference=true" \
  -H "X-API-Key: YOUR_API_KEY" \
| jq -r '["model","input/M","output/M","cache_read/M","cache_write/M"],
    (.models[] | [.id, .input_price_per_million, .output_price_per_million,
      .cache_read_price_per_million, .cache_write_price_per_million]) | @tsv' \
| column -t -s $'\t'
```