List prices, applied per call
Rates are each provider’s public list prices for its own API, in US dollars per million tokens. Cached input, batch, priority and long-context rates are applied when the call reports them.
Supported models · Updated with each provider price change
Every model Ganivra prices for you
Send usage for any of these models and Ganivra prices each call at the provider’s published rate, then rolls it up by customer, feature and workflow. Calls to models not listed here are still recorded and shown as unpriced, never as free.
165models priced automatically
9providers
82open models on Together AI, Fireworks, DeepInfra and Baseten
Pricing guides: Claude API pricing · Claude Opus · Claude Sonnet · OpenAI API pricing · GPT-6 · GPT-5.6 · Gemini API pricing · Gemini Flash · Gemini 4 Argon and Pro · Model vs model price comparisons · Price changes and shutdowns
Download every price as JSON or CSV: open LLM price data on GitHub (CC BY 4.0).
Priced models
165 of 165 models · USD per 1M tokens
OpenAI Frontier
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
gpt-4.1Snapshot: gpt-4.1-2025-04-14Deprecated, shuts down January 14, 2027 | $2.00 | $0.50 | $8.00 | Batch at 50% off · Fast mode at 1.75× |
gpt-4.1-miniSnapshot: gpt-4.1-mini-2025-04-14Deprecated, shuts down January 14, 2027 | $0.40 | $0.10 | $1.60 | Batch at 50% off · Fast mode at 1.75× |
gpt-4.1-nanoShut down October 23, 2026 | $0.10 | $0.025 | $0.40 | Batch at 50% off · Fast mode at 2× |
gpt-4oDeprecated, shuts down January 14, 2027 | $2.50 | $1.25 | $10.00 | Batch at 50% off · Fast mode at 1.7× |
gpt-4o-miniDeprecated, shuts down January 14, 2027 | $0.15 | $0.075 | $0.60 | Batch at 50% off |
gpt-5Snapshot: gpt-5-2025-08-07Deprecated, shuts down December 11, 2026 | $1.25 | $0.125 | $10.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× |
gpt-5-miniSnapshot: gpt-5-mini-2025-08-07Deprecated, shuts down December 11, 2026 | $0.25 | $0.025 | $2.00 | Batch at 50% off · Flex at 50% off · Fast mode at 1.8× |
gpt-5-nanoDeprecated, shuts down December 11, 2026 | $0.05 | $0.005 | $0.40 | Batch at 50% off · Flex at 50% off |
gpt-5-proDeprecated, shuts down December 11, 2026 | $15.00 | — | $120.00 | Batch at 50% off |
gpt-5.1Deprecated, shuts down April 1, 2027 | $1.25 | $0.125 | $10.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× |
gpt-5.2 | $1.75 | $0.175 | $14.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× |
gpt-5.2-pro | $21.00 | — | $168.00 | Batch at 50% off |
gpt-5.3-codexDeprecated, shuts down April 1, 2027 | $1.75 | $0.175 | $14.00 | Fast mode at 2× |
gpt-5.4 | $2.50 | $0.25 | $15.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $5.00 in / $22.50 out |
gpt-5.4-mini | $0.75 | $0.075 | $4.50 | Batch at 50% off · Flex at 50% off · Fast mode at 2× |
gpt-5.4-nanoDeprecated, shuts down April 1, 2027 | $0.20 | $0.02 | $1.25 | Batch at 50% off · Flex at 50% off |
gpt-5.4-pro | $30.00 | — | $180.00 | Batch at 50% off · Above 272K input tokens: $60.00 in / $270.00 out |
gpt-5.5 | $5.00 | $0.50 | $30.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2.5× · Above 272K input tokens: $10.00 in / $45.00 out |
gpt-5.5-cyber | $12.50 | $1.25 | $75.00 | No published price above 272K input tokens |
gpt-5.5-pro | $30.00 | — | $180.00 | Batch at 50% off · Above 272K input tokens: $60.00 in / $270.00 out |
gpt-5.6-cyber | $12.50 | $1.25 | $75.00 | Above 272K input tokens: $25.00 in / $112.50 out · Cache writes $15.625 |
gpt-5.6-lunaPricing details → | $0.20 | $0.02 | $1.20 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $0.40 in / $1.80 out · Cache writes $0.25 |
gpt-5.6-solPricing details → | $4.00 | $0.40 | $20.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $8.00 in / $30.00 out · Cache writes $5.00 |
gpt-5.6-terraPricing details → | $2.00 | $0.20 | $12.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $4.00 in / $18.00 out · Cache writes $2.50 |
gpt-6-astraPricing details → | $10.00 | $1.00 | $50.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $20.00 in / $75.00 out · Cache writes $12.50 |
gpt-6-cyber | $20.00 | $2.00 | $100.00 | No published price above 272K input tokens · Cache writes $25.00 |
gpt-6-lunaPricing details → | $0.10 | $0.01 | $0.50 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $0.20 in / $0.75 out · Cache writes $0.125 |
gpt-6-solPricing details → | $2.00 | $0.20 | $10.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $4.00 in / $15.00 out · Cache writes $2.50 |
gpt-6.1-solPricing details → | $2.00 | $0.10 | $10.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $4.00 in / $15.00 out · Cache writes $2.50 |
gpt-6.1-terraPricing details → | $1.00 | $0.05 | $5.00 | Batch at 50% off · Flex at 50% off · Fast mode at 2× · Above 272K input tokens: $2.00 in / $7.50 out · Cache writes $1.25 |
o1Shut down October 23, 2026 | $15.00 | $7.50 | $60.00 | Batch at 50% off |
o1-proShut down October 23, 2026 | $150.00 | — | $600.00 | Batch at 50% off |
o3Deprecated, shuts down December 11, 2026 | $2.00 | $0.50 | $8.00 | Batch at 50% off · Flex at 50% off · Fast mode at 1.75× |
o3-miniShut down October 23, 2026 | $1.10 | $0.55 | $4.40 | Batch at 50% off |
o3-proDeprecated, shuts down December 11, 2026 | $20.00 | — | $80.00 | Batch at 50% off |
o4-miniShut down October 23, 2026 | $1.10 | $0.275 | $4.40 | Batch at 50% off · Flex at 50% off |
Anthropic Frontier
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
claude-3-5-haiku-20241022Shut down February 19, 2026 | $0.80 | $0.08 | $4.00 | Batch at 50% off · Cache writes $1.00 (5 min) / $1.60 (1 h) · Web search $10.00 per 1,000 |
claude-3-5-haiku-latestShut down February 19, 2026 | $0.80 | $0.08 | $4.00 | Batch at 50% off · Cache writes $1.00 (5 min) / $1.60 (1 h) · Web search $10.00 per 1,000 |
claude-fable-5 | $10.00 | $1.00 | $50.00 | Batch at 50% off · Cache writes $12.50 (5 min) / $20.00 (1 h) · Web search $10.00 per 1,000 |
claude-fable-5-1 | $10.00 | $0.25 | $50.00 | Batch at 50% off · Cache writes $12.50 (5 min) / $20.00 (1 h) · Web search $10.00 per 1,000 |
claude-haiku-4-5Snapshot: claude-haiku-4-5-20251001 | $1.00 | $0.10 | $5.00 | Batch at 50% off · Cache writes $1.25 (5 min) / $2.00 (1 h) · Web search $10.00 per 1,000 |
claude-haiku-5-5 | $0.10 | $0.01 | $0.50 | Batch at 50% off · Above 100K input tokens: $0.50 in / $2.50 out · Cache writes $0.125 (5 min) / $0.20 (1 h) · Web search $10.00 per 1,000 |
claude-mythos-5 | $10.00 | $1.00 | $50.00 | Batch at 50% off · Cache writes $12.50 (5 min) / $20.00 (1 h) · Web search $10.00 per 1,000 |
claude-mythos-5-1 | $10.00 | $0.25 | $50.00 | Batch at 50% off · Cache writes $12.50 (5 min) / $20.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4Snapshot: claude-opus-4-20250514Shut down June 15, 2026Pricing details → | $15.00 | $1.50 | $75.00 | Batch at 50% off · Cache writes $18.75 (5 min) / $30.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4-1Snapshot: claude-opus-4-1-20250805Shut down August 5, 2026Pricing details → | $15.00 | $1.50 | $75.00 | Batch at 50% off · Cache writes $18.75 (5 min) / $30.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4-5Snapshot: claude-opus-4-5-20251101Pricing details → | $5.00 | $0.50 | $25.00 | Batch at 50% off · Cache writes $6.25 (5 min) / $10.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4-6Pricing details → | $5.00 | $0.50 | $25.00 | Batch at 50% off · Cache writes $6.25 (5 min) / $10.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4-7Pricing details → | $5.00 | $0.50 | $25.00 | Batch at 50% off · Cache writes $6.25 (5 min) / $10.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-4-8Pricing details → | $5.00 | $0.50 | $25.00 | Batch at 50% off · Fast mode $10.00 in / $50.00 out · Cache writes $6.25 (5 min) / $10.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-5Pricing details → | $5.00 | $0.50 | $25.00 | Batch at 50% off · Fast mode $10.00 in / $50.00 out · Cache writes $6.25 (5 min) / $10.00 (1 h) · Web search $10.00 per 1,000 |
claude-opus-5-5Pricing details → | $4.00 | $0.20 | $20.00 | Batch at 50% off · Fast mode $8.00 in / $40.00 out · Cache writes $5.00 (5 min) / $8.00 (1 h) · Web search $10.00 per 1,000 |
claude-sonnet-4Snapshot: claude-sonnet-4-20250514Shut down June 15, 2026Pricing details → | $3.00 | $0.30 | $15.00 | Batch at 50% off · Cache writes $3.75 (5 min) / $6.00 (1 h) · Web search $10.00 per 1,000 |
claude-sonnet-4-5Snapshot: claude-sonnet-4-5-20250929Deprecated, shuts down November 30, 2026Pricing details → | $3.00 | $0.30 | $15.00 | Batch at 50% off · Cache writes $3.75 (5 min) / $6.00 (1 h) · Web search $10.00 per 1,000 |
claude-sonnet-4-6Pricing details → | $3.00 | $0.30 | $15.00 | Batch at 50% off · Cache writes $3.75 (5 min) / $6.00 (1 h) · Web search $10.00 per 1,000 |
claude-sonnet-5Pricing details → | $2.00 | $0.20 | $10.00 | Batch at 50% off · Cache writes $2.50 (5 min) / $4.00 (1 h) · Web search $10.00 per 1,000 |
claude-sonnet-5-5Pricing details → | $2.00 | $0.10 | $10.00 | Batch at 50% off · Cache writes $2.50 (5 min) / $4.00 (1 h) · Web search $10.00 per 1,000 |
Google Gemini Frontier
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
gemini-2.5-flashPricing details → | $0.30 | $0.03 | $2.50 | Batch at 50% off, cached input $0.03 · Flex at 50% off · Priority at 1.8× · Search grounding $35.00 per 1,000 |
gemini-2.5-flash-litePricing details → | $0.10 | $0.01 | $0.40 | Batch at 50% off, cached input $0.01 · Flex at 50% off · Priority at 1.8× · Search grounding $35.00 per 1,000 |
gemini-2.5-proPricing details → | $1.25 | $0.125 | $10.00 | Batch at 50% off, cached input $0.125 · Flex at 50% off · Priority at 1.8× · Above 200K input tokens: $2.50 in / $15.00 out · Search grounding $35.00 per 1,000 |
gemini-3-flash-previewPricing details → | $0.50 | $0.05 | $3.00 | Batch at 50% off, cached input $0.05 · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-3.1-flash-liteDeprecated, shuts down as early as May 7, 2027Pricing details → | $0.25 | $0.025 | $1.50 | Batch at 50% off · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-3.1-pro-previewPricing details → | $2.00 | $0.20 | $12.00 | Batch at 50% off, cached input $0.20 · Flex at 50% off · Priority at 1.8× · Above 200K input tokens: $4.00 in / $18.00 out · Search grounding $14.00 per 1,000 |
gemini-3.1-pro-preview-customtools | $2.00 | $0.20 | $12.00 | Batch at 50% off, cached input $0.20 · Flex at 50% off · Priority at 1.8× · Above 200K input tokens: $4.00 in / $18.00 out · Search grounding $14.00 per 1,000 |
gemini-3.5-flash | $1.50 | $0.15 | $9.00 | Search grounding $14.00 per 1,000 |
gemini-3.5-flash-litePricing details → | $0.30 | $0.03 | $2.50 | Batch at 50% off, cached input $0.02 · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-3.6-flashPricing details → | $0.75 | $0.075 | $3.75$1.50 / $7.50 from Jan 1, 2027 | Batch at 50% off · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-3.8-flashPricing details → | $0.75 | $0.075 | $3.75$1.50 / $7.50 from Jan 1, 2027 | Batch at 50% off · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-4-argonPricing details → | $2.00 | $0.10 | $10.00$4.00 / $20.00 from Dec 1, 2026 | Batch at 50% off · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
gemini-flash-latest | $0.75 | $0.075 | $3.75$1.50 / $7.50 from Jan 1, 2027 | Alias of gemini-3.8-flash · Batch at 50% off · Flex at 50% off · Priority at 1.8× · Search grounding $14.00 per 1,000 |
Perplexity Search
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
sonar | $1.00 | — | $1.00 | Request fee from $5.00 per 1,000 |
sonar-pro | $3.00 | — | $15.00 | Request fee from $6.00 per 1,000 |
Together AI Open models
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $0.13 | $3.96 | — |
deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $0.006 | $1.20 | — |
meta-models/Muse-Spark-Open-816B-A42B | $1.25 | $0.15 | $4.25 | — |
MiniMaxAI/MiniMax-M3.1-Flash | $0.15 | $0.015 | $0.60 | — |
moonshotai/Kimi-K3 | $3.00 | $0.30 | $15.00 | — |
nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.02 | $0.50 | — |
openai/gpt-oss-120b | $0.15 | — | $0.60 | No cache discount |
Qwen/Qwen3.5-9B | $0.17 | — | $0.25 | No cache discount |
Qwen/Qwen3.8-Flash | $0.15 | — | $0.47 | No cache discount |
zai-org/GLM-5.3 | $1.40 | $0.26 | $4.40 | — |
zai-org/GLM-5.3-Flash | $0.15 | $0.03 | $0.50 | — |
Fireworks Open models
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
accounts/fireworks/models/deepseek-v4p1-flash | $0.30 | $0.006 | $1.20 | — |
accounts/fireworks/models/deepseek-v4p1-flash-1017 | $0.30 | $0.006 | $1.20 | — |
accounts/fireworks/models/glm-5p3 | $1.40 | $0.26 | $4.40 | — |
accounts/fireworks/models/glm-5p3-flash | $0.15 | $0.03 | $0.50 | — |
accounts/fireworks/models/gpt-oss-120b | $0.15 | $0.015 | $0.60 | — |
accounts/fireworks/models/kimi-k3 | $3.00 | $0.30 | $15.00 | — |
accounts/fireworks/models/minimax-m3 | $0.30 | $0.06 | $1.20 | — |
accounts/fireworks/models/muse-spark-open | $1.25 | $0.15 | $4.25 | — |
accounts/fireworks/models/nemotron-3-ultra-nvfp4 | $0.60 | $0.12 | $2.40 | — |
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b | $0.05 | $0.01 | $0.20 | — |
accounts/fireworks/models/qwen3p8-max | $2.00 | $0.25 | $6.00 | — |
DeepInfra Open models
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
deepseek-ai/DeepSeek-R1-0528 | $0.50 | $0.35 | $2.15 | — |
deepseek-ai/DeepSeek-V3 | $0.32 | — | $0.89 | No cache discount |
deepseek-ai/DeepSeek-V3.1 | $0.25 | $0.13 | $0.95 | — |
deepseek-ai/DeepSeek-V3.2 | $0.26 | $0.13 | $0.38 | — |
deepseek-ai/DeepSeek-V4-Flash | $0.09 | $0.018 | $0.18 | — |
deepseek-ai/DeepSeek-V4-Flash-0731 | $0.06 | $0.015 | $0.18 | — |
deepseek-ai/DeepSeek-V4-Pro | $1.30 | $0.10 | $2.60 | — |
google/gemma-3-12b-it | $0.05 | — | $0.15 | No cache discount |
google/gemma-3-27b-it | $0.08 | — | $0.16 | No cache discount |
google/gemma-3-4b-it | $0.05 | — | $0.10 | No cache discount |
google/gemma-4-26B-A4B-it | $0.07 | — | $0.34 | No cache discount |
google/gemma-4-31B-it | $0.20 | — | $0.40 | No cache discount |
google/gemma-4-31B-it-turbo | $0.09 | $0.05 | $0.34 | — |
google/gemma-4-31B-it-Ultra | $0.27 | — | $0.76 | No cache discount |
meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.10 | — | $0.32 | No cache discount |
meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.10 | — | $0.30 | No cache discount |
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.02 | — | $0.04 | No cache discount |
microsoft/phi-4 | $0.07 | — | $0.14 | No cache discount |
mistralai/Mistral-Nemo-Instruct-2407 | $0.029 | — | $0.03 | No cache discount |
mistralai/Mistral-Small-24B-Instruct-2501 | $0.05 | — | $0.08 | No cache discount |
mistralai/Mistral-Small-3.2-24B-Instruct-2506 | $0.075 | — | $0.20 | No cache discount |
moonshotai/Kimi-K2.6 | $0.75 | $0.15 | $3.50 | — |
moonshotai/Kimi-K3 | $2.85 | $0.285 | $14.25 | — |
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | $0.085 | — | $0.40 | No cache discount |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.50 | $0.10 | $2.20 | — |
nvidia/NVIDIA-Nemotron-3.5-Lightning | $0.06 | $0.03 | $0.16 | — |
nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.02 | $0.50 | — |
Qwen/Qwen2.5-72B-Instruct | $0.36 | — | $0.40 | No cache discount |
Qwen/Qwen3-14B | $0.12 | — | $0.24 | No cache discount |
Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.09 | — | $0.55 | No cache discount |
Qwen/Qwen3-30B-A3B | $0.12 | — | $0.50 | No cache discount |
Qwen/Qwen3-32B | $0.08 | — | $0.28 | No cache discount |
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.30 | $0.10 | $1.00 | — |
Qwen/Qwen3-Next-80B-A3B-Instruct | $0.09 | — | $1.10 | No cache discount |
Qwen/Qwen3-VL-235B-A22B-Instruct | $0.20 | $0.11 | $0.88 | — |
Qwen/Qwen3-VL-30B-A3B-Instruct | $0.15 | — | $0.60 | No cache discount |
Qwen/Qwen3.5-27B | $0.26 | — | $2.60 | No cache discount |
Qwen/Qwen3.5-35B-A3B | $0.14 | $0.05 | $1.00 | — |
Qwen/Qwen3.5-397B-A17B | $0.45 | $0.22 | $3.00 | — |
Qwen/Qwen3.5-9B | $0.10 | — | $0.15 | No cache discount |
Qwen/Qwen3.6-27B | $0.32 | — | $3.20 | No cache discount |
Qwen/Qwen3.6-35B-A3B | $0.10 | — | $0.95 | No cache discount |
Qwen/Qwen3.7-Max | $2.50 | $0.50 | $7.50 | — |
Qwen/Qwen3.8-Max | $1.65 | $0.206 | $4.951 | — |
Baseten Open models
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
deepseek-ai/DeepSeek-V4-Flash-0731 | $0.13 | $0.028 | $0.26 | — |
deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $0.007 | $1.20 | — |
deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.30 | $0.007 | $1.20 | — |
deepseek-ai/DeepSeek-V4.1-Flash-Fast | $0.60 | $0.014 | $2.40 | — |
deepseek-v4-pro-0813 | $1.32 | $0.132 | $3.96 | — |
meta-models/muse-spark-open | $1.25 | $0.15 | $4.25 | — |
moonshotai/Kimi-K3 | $3.00 | $0.30 | $15.00 | — |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.60 | $0.12 | $2.40 | — |
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | $0.20 | $0.04 | $0.50 | — |
openai/gpt-oss-120b | $0.10 | — | $0.50 | No cache discount |
reflection/Beam-1.0 | $0.40 | $0.04 | $1.20 | — |
zai-org/GLM-5.2 | $1.40 | $0.14 | $4.40 | — |
zai-org/GLM-5.2-Fast | $2.10 | $0.21 | $6.60 | — |
zai-org/GLM-5.3 | $1.40 | $0.14 | $4.40 | — |
zai-org/GLM-5.3-Fast | $2.10 | $0.21 | $6.60 | — |
zai-org/GLM-5.3-Flash | $0.15 | $0.03 | $0.50 | — |
Sarvam Indian languages, billed in rupees
| Model ID | Input | Cached input | Output | Also priced |
|---|---|---|---|---|
deepseekv4-pro | $1.2121 | $0.0422 | $3.689 | Billed in rupees: ₹115 in / ₹4 cached / ₹350 out, at ₹94.876 per $1, excluding GST |
deepseekv4.1-flash-1017 | $0.2635 | $0.0053 | $1.1067 | Billed in rupees: ₹25 in / ₹0.5 cached / ₹105 out, at ₹94.876 per $1, excluding GST |
gemma4 | $0.3689 | $0.1054 | $0.9486 | Billed in rupees: ₹35 in / ₹10 cached / ₹90 out, at ₹94.876 per $1, excluding GST |
glm5.3 | $1.328 | $0.2108 | $4.1106 | Billed in rupees: ₹126 in / ₹20 cached / ₹390 out, at ₹94.876 per $1, excluding GST |
glm5.3-flash | $0.1423 | $0.0264 | $0.4743 | Billed in rupees: ₹13.5 in / ₹2.5 cached / ₹45 out, at ₹94.876 per $1, excluding GST |
kimi-k3 | $2.8458 | $0.2846 | $14.2291 | Billed in rupees: ₹270 in / ₹27 cached / ₹1,350 out, at ₹94.876 per $1, excluding GST |
mimo-v2.6-flash | $0.1318 | $0.0026 | $0.2635 | Billed in rupees: ₹12.5 in / ₹0.25 cached / ₹25 out, at ₹94.876 per $1, excluding GST |
mimo-v2.6-pro | $0.4216 | $0.0032 | $0.8432 | Billed in rupees: ₹40 in / ₹0.3 cached / ₹80 out, at ₹94.876 per $1, excluding GST |
sarvam-105b | $0.1581 | $0.0527 | $0.6324 | Billed in rupees: ₹15 in / ₹5 cached / ₹60 out, at ₹94.876 per $1, excluding GST |
sarvam-105b-conversations | $0.1581 | $0.0527 | $0.6324 | Billed in rupees: ₹15 in / ₹5 cached / ₹60 out, at ₹94.876 per $1, excluding GST |
sarvam-prism | $0.0422 | — | $0.00 | Billed in rupees: ₹4 in / ₹0 out, at ₹94.876 per $1, excluding GST · No cache discount |
Sarvam speech, translation and documents Billed per unit, in rupees
Sarvam bills in rupees, excluding GST. Ganivra keeps each call's rupee cost and converts it at ₹94.876 per $1, the RBI reference rate for 2 November 2026, so it adds up with your other AI costs. Pay-as-you-go rates: on a Pro, Growth or Business plan, add your plan's rates as contract rates.
| Model ID | Price | In USD | Send in usage_details |
|---|---|---|---|
bulbul:v3 | ₹3 per 1,000 characters | $0.0316 | characters |
bulbul:v4-flash | ₹1 per 1,000 characters₹2 per 1,000 characters from Nov 13, 2026 | $0.0105 | characters |
mayura:v1 | ₹2 per 1,000 characters | $0.0211 | characters |
saaras:v3 | ₹0.49 per minute of audio₹0.59 per minute of audio with diarization | $0.0052$0.0062 | audio_seconds (seconds)diarized_audio_seconds (seconds) |
saaras:v3-realtime | ₹0.49 per minute of audio₹0.59 per minute of audio with diarization | $0.0052$0.0062 | audio_seconds (seconds)diarized_audio_seconds (seconds) |
saaras:v4 | ₹0.49 per minute of audio₹0.59 per minute of audio with diarization | $0.0052$0.0062 | audio_seconds (seconds)diarized_audio_seconds (seconds) |
saarika:v2.5 | ₹0.49 per minute of audio₹0.59 per minute of audio with diarization | $0.0052$0.0062 | audio_seconds (seconds)diarized_audio_seconds (seconds) |
sarvam-translate:v1 | ₹2 per 1,000 characters | $0.0211 | characters |
sarvam-vision | ₹1 per page extracted₹0.5 per page parsed | $0.0105$0.0053 | extraction_pagespages |
text-lid | ₹0.35 per 1,000 characters | $0.0037 | characters |
transliterate | ₹2 per 1,000 characters | $0.0211 | characters |
How these rates are used
Price changes reprice history
When a provider changes a price, calls are charged at the rate in effect on the day they ran. Adding a rate for a model that was unpriced reprices its earlier calls.
Your own rates win
Negotiated discounts, Bedrock, Vertex AI, Azure and self-hosted models take a contract rate in your workspace, which overrides the list price. A provider-reported cost overrides both.
Missing a model? Tell us and we will add it, or set your own rate in the meantime. To start sending usage, see the integration guide.