{"asOf":"2026-10-27","providerId":"deepinfra","rowCount":8,"providerCount":1,"providersWithSourcedTokenPrice":1,"providersWithPriceSortKey":1,"normalizedUsdPerMillionTokensNullRows":5,"countsByUnit":{"usd_per_million_input_tokens":2,"usd_per_million_output_tokens":1,"usd_per_gpu_hour":5},"countsByNormalizationStatus":{"sourced_token_price":3,"unit_mismatch":5},"refusedCoercions":["gpu_hour_not_coerced_to_per_million_tokens","per_minute_and_per_hour_voice_not_coerced","per_1k_posts_profiles_calls_searches_characters_not_coerced","input_and_output_not_blended","cached_vs_uncached_not_blended","short_vs_long_context_not_blended","scheduled_future_rate_not_treated_as_today","peak_vs_offpeak_not_collapsed","promo_and_list_shown_together_not_picked","unlabeled_api_unit_not_multiplied","openrouter_rows_not_copied_onto_vendor_providers","pricing_notes_prose_not_promoted","fireworks_serverless_chat_matrix_not_on_fetched_page"],"priceSort":{"param":"sort=price","key":"Without jtbd: lowest priceSortEligible chat/completion input (or undifferentiated) USD per 1M tokens. With jtbd: cheapest SKU whose unit matches that job (see GET /api/quote).","excludes":"output, cached input, long-context tiers, scheduled future rates, peak/off-peak pairs, training tokens on chat sorts, and any unit that does not match the job. GPU hours, per-minute speech, and search units are not coerced into $/1M."},"rows":[{"id":"deepinfra-llama-33-70b-turbo-input","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"128k context row"},{"id":"deepinfra-llama-33-70b-turbo-output","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_output_tokens","amountUsd":0.32,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.32,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"deepinfra-bge-base-en","providerId":"deepinfra","sku":"bge-base-en-v1.5","unit":"usd_per_million_input_tokens","amountUsd":0.005,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.005,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"embeddings; input only"},{"id":"deepinfra-gpu-a100","providerId":"deepinfra","sku":"A100","unit":"usd_per_gpu_hour","amountUsd":1.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-h100","providerId":"deepinfra","sku":"H100","unit":"usd_per_gpu_hour","amountUsd":2.9,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-h200","providerId":"deepinfra","sku":"H200","unit":"usd_per_gpu_hour","amountUsd":3.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-b200","providerId":"deepinfra","sku":"B200","unit":"usd_per_gpu_hour","amountUsd":4.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-b300","providerId":"deepinfra","sku":"B300","unit":"usd_per_gpu_hour","amountUsd":5.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"}],"provider":{"id":"deepinfra","slug":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.1,"rows":[{"id":"deepinfra-llama-33-70b-turbo-input","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"128k context row"},{"id":"deepinfra-llama-33-70b-turbo-output","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_output_tokens","amountUsd":0.32,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.32,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"deepinfra-bge-base-en","providerId":"deepinfra","sku":"bge-base-en-v1.5","unit":"usd_per_million_input_tokens","amountUsd":0.005,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.005,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"embeddings; input only"},{"id":"deepinfra-gpu-a100","providerId":"deepinfra","sku":"A100","unit":"usd_per_gpu_hour","amountUsd":1.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-h100","providerId":"deepinfra","sku":"H100","unit":"usd_per_gpu_hour","amountUsd":2.9,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-h200","providerId":"deepinfra","sku":"H200","unit":"usd_per_gpu_hour","amountUsd":3.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-b200","providerId":"deepinfra","sku":"B200","unit":"usd_per_gpu_hour","amountUsd":4.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"},{"id":"deepinfra-gpu-b300","providerId":"deepinfra","sku":"B300","unit":"usd_per_gpu_hour","amountUsd":5.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour"}],"notesExcerpt":"As of 2026-09-14: Broad OpenAI-compatible catalog with model-specific token rates (e.g. Llama-3.3-70B Turbo $0.10/$0.32 per 1M in/out; DeepSeek-V4-Flash input $0.09, cached input $0.018 and output $0.18 per 1M (deepinfra.com/pricing as of 2026-10-21; not stored as rows); embeddin…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://deepinfra.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."}}