ScrapeGraphAI/Scrapegraph-ai · error · ValueError

Unsupported service tier {service_tier!r} for {model_name}

Error message

Unsupported service tier {service_tier!r} for {model_name}

What it means

ValueError from get_model_cost_per_1k_tokens: the model has tiered pricing but the supplied service_tier key (default 'standard') has no entry in MODEL_COST_TIERS_PER_1K_TOKENS for that model (e.g. only 'priority'/'other' tiers defined).

Source

Thrown at scrapegraphai/utils/model_costs.py:167

    }
}


def get_model_cost_per_1k_tokens(
    model_name: str,
    input_tokens: int,
    is_completion: bool = False,
    service_tier: str = "standard",
) -> float:
    """Return the applicable input or output rate for a model."""
    if input_tokens < 0:
        raise ValueError("input_tokens must not be negative")

    if model_name in MODEL_COST_TIERS_PER_1K_TOKENS:
        try:
            pricing_tiers = MODEL_COST_TIERS_PER_1K_TOKENS[model_name][service_tier]
        except KeyError as exc:
            raise ValueError(
                f"Unsupported service tier {service_tier!r} for {model_name}"
            ) from exc

        rate_key = "output" if is_completion else "input"
        for pricing in pricing_tiers:
            upper_bound = pricing.get("input_tokens_lte")
            lower_bound = pricing.get("input_tokens_gt")
            if upper_bound is not None and input_tokens <= upper_bound:
                return float(pricing[rate_key])
            if lower_bound is not None and input_tokens > lower_bound:
                return float(pricing[rate_key])
        raise ValueError(f"No pricing tier matches {input_tokens} input tokens")

    costs = (
        MODEL_COST_PER_1K_TOKENS_OUTPUT
        if is_completion
        else MODEL_COST_PER_1K_TOKENS_INPUT
    )

View on GitHub (pinned to 532dfffbf6)

Solutions

1. Check MODEL_COST_TIERS_PER_1K_TOKENS[model] keys and pass a service_tier that exists (e.g. 'priority')
2. Ensure tiered model entries always include a 'standard' tier in the cost table
3. Normalize provider tier strings before passing them to the helper

Example fix

# before
rate = get_model_cost_per_1k_tokens(model, n, service_tier="batch")
# after
tiers = MODEL_COST_TIERS_PER_1K_TOKENS.get(model, {})
rate = get_model_cost_per_1k_tokens(model, n, service_tier="batch" if "batch" in tiers else "standard")

from scrapegraphai.utils.model_costs import MODEL_COST_TIERS_PER_1K_TOKENS
tiers = MODEL_COST_TIERS_PER_1K_TOKENS.get(model, {})
service_tier = service_tier if service_tier in tiers else "standard"

def is_supported_tier(model, tier) -> bool:
    return tier in MODEL_COST_TIERS_PER_1K_TOKENS.get(model, {})

try:
    rate = get_model_cost_per_1k_tokens(model, n, service_tier=tier)
except ValueError:
    rate = get_model_cost_per_1k_tokens(model, n)  # default standard

When it happens

Trigger: Calling get_model_cost_per_1k_tokens for a tiered model with service_tier set to a tier not defined for it, or a model whose dict lacks the default 'standard' key.

Common situations: Adding a new tiered-pricing model to the cost table without a 'standard' entry, or forwarding a provider-specific service tier string verbatim.

Related errors

• No pricing tier matches {input_tokens} input tokens
• The 'graphviz' library is required for this functionality. P
• The browserbase module is not installed. Please install it u
• Cannot deep copy object of type {type(obj)}
• input_tokens is required for completion costs with tiered pr

AI-assisted analysis of ScrapeGraphAI/Scrapegraph-ai@532dfffbf6 (2026-08-28). Data as JSON: /api/errors/5424cffaa7397a06. Report an issue: GitHub.