BerriAI/litellm · error · Exception

No pricing information found for model

Error message

No pricing information found for model {model}. Tried checking {models_to_check}

What it means

Raised in the same default_image_cost_calculator after a model entry WAS found in litellm.model_cost, but the entry contains neither input_cost_per_image (priority 1) nor input_cost_per_pixel (priority 2). litellm's image calculator only understands per-image or per-pixel pricing; an entry with only token-based fields (input_cost_per_token) cannot be used, so it raises. The generated image itself was returned successfully; only the cost calculation fails.

Solutions

1. Extend the model's cost entry with input_cost_per_image (preferred): litellm.register_model({"<model>": {"input_cost_per_image": 0.02, "mode": "image_generation"}}).
2. If you must use legacy per-pixel pricing, set input_cost_per_pixel instead — the calculator multiplies it by height*width*n.
3. Verify the matched entry is not a same-named text model; rename the image model or fix the entry so token-only pricing is not silently reused.
4. Upgrade litellm — a newer pricing file may add per-image pricing for the model.

Example fix

# before: entry exists but only has token pricing -> "No pricing information found"
litellm.register_model({"my-image-model": {"input_cost_per_token": 0.00001}})

# after: image-model pricing keys the calculator understands
litellm.register_model({
    "my-image-model": {
        "input_cost_per_image": 0.02,
        "mode": "image_generation",
    }
})

import litellm

def ensure_image_cost_fields(model: str) -> None:
    """Raise before the call unless the model's entry has per-image or per-pixel pricing."""
    entry = litellm.model_cost.get(model) or litellm.model_cost.get(model.split("/")[-1])
    if entry is None or (entry.get("input_cost_per_image") is None and entry.get("input_cost_per_pixel") is None):
        raise ValueError(
            f"{model!r} lacks input_cost_per_image/input_cost_per_pixel; "
            "litellm.register_model with input_cost_per_image before calling."
        )

When it happens

Trigger: A litellm.register_model / proxy model_info entry for an image model that defines only token pricing (input_cost_per_token) or no pricing fields at all; a model name that collides with a text-model entry in the pricing map (found, but the entry has no image keys); hand-edited model_prices_and_context_window.json files missing the image cost fields.

Common situations: Teams copy-pasting a text-model pricing template into register_model for an image model; proxy deployments that set cost per token for image endpoints; partial custom pricing JSON files that list the model but omit the image-specific keys.

Related errors

• Model not found in cost map. Tried checking
• Model not found in cost map for model=
• Could not calculate cost for model
• api_base not set for LiteLLM Proxy route. Set in env via…
• BFL_API_KEY is not set. Please set it via environment…

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/ad13d3f3988f0153. Report an issue: GitHub.

Appendix: source

Thrown at litellm/cost_calculator.py:2023

        model_without_provider,
        model,
        model_name_without_custom_llm_provider,
    ]
    for _model in models_to_check:
        if _model is not None and _model in litellm.model_cost:
            cost_info = litellm.model_cost[_model]
            break
    if cost_info is None:
        raise Exception(f"Model not found in cost map. Tried checking {models_to_check}")

    # Priority 1: Use per-image pricing if available (for gpt-image-1 and similar models)
    if "input_cost_per_image" in cost_info and cost_info["input_cost_per_image"] is not None:
        return cost_info["input_cost_per_image"] * n
    # Priority 2: Fall back to per-pixel pricing for backward compatibility
    elif "input_cost_per_pixel" in cost_info and cost_info["input_cost_per_pixel"] is not None:
        return cost_info["input_cost_per_pixel"] * height * width * n
    else:
        raise Exception(f"No pricing information found for model {model}. Tried checking {models_to_check}")


def default_video_cost_calculator(
    model: str,
    duration_seconds: float,
    custom_llm_provider: str | None = None,
    model_info: ModelInfo | None = None,
    video_resolution: str | None = None,
) -> float:
    """
    Default video cost calculator for video generation

    Args:
        model (str): Model name
        duration_seconds (float): Duration of the generated video in seconds
        custom_llm_provider (Optional[str]): Custom LLM provider
        model_info (Optional[ModelInfo]): Deployment-level model info containing
            custom video pricing. When provided, used before falling back to

View on GitHub (pinned to 77b7c6c40c)